Guidance

Follow this topic Ask about this topic

Momentum

19 papers in the last four weeks, up 12% on the four weeks before. 0.2% of all new papers.

Jul 6Week of Sep 21

Latest papers 172

Oct 1, 2026cs.CV

DecomVoxel: Harnessing 3D-Native Priors with Guided In-situ Denoising Optimization for Decompositional Scene Reconstruction

Decompositional scene reconstruction aims to reconstruct high-quality objects and background, yet existing methods still struggle with the level of quality under heavy occlusions. While generative priors offer a potential solution, 2D image-based priors often suffer from multi-view inconsistency due to a lack of 3D awareness. Conversely, 3D-native priors provide stronger structural inductive biases but frequently lead to spatial drift and misalignment within complex scenes. To address these issues, we propose DecomVoxel, formulating object completion as a guided in-situ denoising optimization that bridges 3D-native priors with neural scene reconstruction. Our framework introduces a reformulated epsilon-based distillation loss to ensure stable latent refinement, alongside adaptive spatial guidance that utilizes occupied and vacant anchors with temporal annealing to suppress generative hallucinations and mitigate spatial drift. Experiments on Replica and ScanNet++ show that DecomVoxel significantly outperforms state-of-the-art methods while faithfully preserving the original spatial layout, structural fidelity, and style-consistent texture. Our method pushes the boundary of decompositional reconstruction by delivering high-quality textured meshes with clean topology, geometry, and appearance, providing a robust solution for the decompositional reconstruction of complex real-world scenes. Code is available at https://github.com/DecomVoxel/DecomVoxel.

Junfeng Ni, Zirui Zhou, Yixin Chen +5

Tsinghua University, State Key Laboratory of General Artificial Intelligence, BIGAI, China · Peking University, China

Scene Reconstruction Voxel 3D Priors Completion Dataset Distillation Guidance

Oct 1, 2026cs.RO

LiDARFlow: Real-Time Panel-Based MAV Guidance in Unknown Environments

This paper presents a guidance algorithm for micro aerial vehicles operating in unknown, cluttered environments using only onboard sensing. The method is based on a panel formulation originally derived from aerodynamic potential-flow theory and generates smooth, collision-free guidance vectors from locally perceived obstacles. The approach is extended to unknown environments by constructing and updating the obstacle representation online from onboard LiDAR measurements. The resulting obstacle-avoidance field is integrated with a nominal guiding vector field to produce the final control input. The system is experimentally validated in indoor flight tests under two scenarios: waypoint navigation and directional guidance. In both cases, the vehicle successfully completes its task while avoiding all obstacles in real time using only onboard perception. The results demonstrate that the method is computationally lightweight and suitable for onboard implementation, with pointcloud processing identified as the main practical limitation. These results support the feasibility of lightweight onboard guidance in unknown environments.

João Machado, Zeynep Bilgin, Matthieu Verdoucq +1

ENAC-LAB · ENAC

Unmanned Aerial Vehicles Obstacle Avoidance Dynamic Environments Collision-Free Trajectories Guidance Real-Time Systems+1

Oct 1, 2026cs.RO

Completion Aware Guidance for World Action Models

World Action Models (WAMs) predict visual futures and robot actions, yet they remain susceptible to task-incomplete imagination, where plausible, action-consistent predictions omit the transition needed for task completion. In this paper, we show that this failure is not inherent to the world model backbone, but emerges when adapted for short-chunk control, which can repeatedly favor plausible local continuations over task-completing transitions. To address this, we introduce Completion Aware Guidance (CAG), a training-free sampling method that guides generation toward task completion. Across representative WAMs, CAG improves success from 64% to 70% on a RoboTwin 2.0 subset and from 69% to 75% in zero-shot simulation, while reducing task-incomplete imagination from 79% to 40%.

Seungyeon Kim, Junhoo Lee, Baekseung Kim +2

Seoul National University · KAIST

Efficient World-Action Model World Models Imagination Guidance

Oct 1, 2026cs.LG

Learned End-to-End Guidance Schedules for Diffusion Models

Diffusion models are a powerful generative paradigm used across multimedia and scientific applications. Guided diffusion methods impose requirements on the generation by adding the gradient of a differentiable loss (the guidance function) as a drift term during inference. The weight of this drift (the guidance scale) is critical for the trade-off between data quality and requirement satisfaction. To achieve both of these goals, guided diffusion must resort to small guidance scales and lengthy sampling, incurring high computational costs. This work proposes learned end-to-end guidance schedules (LEEGS) to achieve these objectives with fewer sampling steps. LEEGS trains a time-dependent schedule by minimizing the guidance function over a small set of examples using stochastic gradient descent. Backpropagating through guided sampling is computationally expensive, so LEEGS uses an approximation of the gradient that cuts training time by a factor of 4. We evaluate LEEGS on diverse guidance tasks, including (a) image inpainting, (b) noisy image inverse problems, (c) face-ID-guided generation, and (d) forward and inverse PDE problems, outperforming baselines at equal budget (50 or 100 NFEs), or matching constant guidance with only 10% of the steps.

Aneesh Barthakur, Mathias Niepert, Luiz F. O. Chamon

University of Stuttgart · École polytechnique, Institut Polytechnique de Paris

Diffusion Models Guidance Stochastic Gradient Descent

Oct 1, 2026cs.AI

A Multi-Agent LLM Framework for Personalized Health Checkup Interpretation and Guidance

Personalized interpretation of health checkup results requires reasoning across longitudinal records, medical knowledge, lifestyle guidance, and healthcare navigation. We present a multi-agent large language model (LLM) system that identifies multiple intents, maps each to a task-specific agent, executes them in parallel, and synthesizes their outputs. We compared answers generated in Single Agent and Multi Agent settings on 120 Korean compound queries combining two to four requirements, using synthetic health checkup records. The Multi Agent improved the weighted LLM-judge score from 1.695 to 1.797 (p = 0.027), and three additional LLM judges showed consistent improvements (

Δ

= +0.111 to +0.186, all p < 0.05). The gains came from usefulness, consistency, and the handling of every requirement in compound queries, whereas numerical accuracy and grounding improved significantly under only one of the four judges and medical safety did not differ, and critical failures occurred at similar rates (Single Agent 15.0% vs. Multi Agent 13.3%). Two human evaluators preferred Multi Agent in 66.7% and 68.3% of pairwise comparisons. Multi Agent execution increased latency and cost by 1.31

\times

and 2.02

\times

, respectively. In exploratory subgroup analyses, the improvement was concentrated in queries involving personal-record lookup.

HyungJun Kim, Taehan Lee, Soojin Cheon

DaNaA Data Co., Ltd.

Multi-Agent Large Language Model Systems Llm-As-A-Judge Guidance

Sep 30, 2026cs.CV

VR-JEPA: Learning Contrastive-State Latent Guidance for Generation-based Video Reasoning

Reasoning through video generation offers a promising path toward visual intelligence by modeling latent visual states and their dynamics. However, current video generation models often lack explicit guidance on how these states should evolve, leaving generated trajectories prone to physical and structural inconsistencies that undermine reasoning reliability. While the Video Joint-Embedding Predictive Architecture (V-JEPA) provides rich spatiotemporal priors learned through latent prediction, these general priors do not naturally adapt to the logical reasoning capabilities required for complex visual tasks. To bridge this gap, we propose VR-JEPA, a framework that aligns the V-JEPA predictor with task-specific reasoning logic through localized contrastive-state learning and uses its predicted latent trajectories to guide video generation for visual reasoning. Specifically, (i) we pair successful trajectories with generated alternatives under the same input conditions and use discrepancies in their V-JEPA representations to identify informative states and tokens for localized contrastive supervision. (ii) We further equip the V-JEPA predictor with skill-specific experts trained on anchor-task data, allowing the model to adaptively specialize its shared spatiotemporal priors across diverse cognitive domains. Together with skill-specific experts, this contrastive supervision enables VR-JEPA to predict latent trajectories that provide task-specific logical guidance for video generation. Comprehensive experiments on the large-scale VBVR-Pro-Bench dataset demonstrate that VR-JEPA achieves an

11.33\%

relative improvement over the cutting-edge generation-based reasoning baseline, significantly mitigating physical artifacts and enhancing logical consistency.

Zehua Ma, Kun Xiang, Yunshuang Nie +9

Shenzhen Campus of Sun Yat-sen University · Tsinghua Shenzhen International Graduate School · Shenzhen Loop Area Institute +3

Latent Visual Reasoning Video Generation Video Agent Reasoning Skills Guidance Joint-Embedding Predictive Architectures

Sep 30, 2026math.ST

WEIRDO: WEak resIdual Regularized DOob's h-transform diffusion alignment

We study the problem of estimating the guidance that steers the distribution learned by a diffusion generative model toward a tilted target

q_0 \propto w\,p_0

at inference time. Relying on the stochastic optimal control approach, we observe that the exact drift correction is the gradient of the logarithm of Doob's

h

-function, and we study the problem of estimating it from a sample. In the present paper, we assume that the score of the pretrained model is available, that the tilting weight is bounded and positive, and that the reference distribution has a bounded support, no smoothness of the weight is required. Introducing a penalized least-squares risk in which the penalty is the residual of the space-time harmonicity equation satisfied by the

h

-function, measured in a dual Sobolev norm, we derive high-probability bounds on the squared error of the resulting guidance estimate. Since the penalty vanishes at the target, the estimator is free of regularization bias, and in favourable scenarios its rate of convergence is faster than the minimax rate of estimating first-order derivatives of a smooth regression function. Assuming that

w

is bounded and positive with

\mathbb{E}_{p_0}[w^{-\mathrm{s}}] < \infty

for some

\mathrm{s} \in (0,\infty]

, and that the reference data are compactly supported, we prove that the guidance is estimable in squared

L^2

at rate

\varepsilon_n^{\mathrm{s}/(\mathrm{s}+4)}

, where

\varepsilon_n = n^{-2(β-1)/(2(β-1)+d)}.

We also transfer the obtained bounds to the total variation distance between the marginals of the estimated and the exactly guided samplers, and illustrate the performance of the suggested approach with numerical experiments.

Denis Suchkov

HSE University, Russian Federation

Diffusion Alignment Wasserstein Gradient Flows Regularization Guidance Stochastic Optimal Control Generative Models

Sep 30, 2026cs.HC

NarrativeSteward: Coordinating Delegation, Guidance, and Verification in Agent-Assisted Interactive Narrative Authoring

Autonomous AI agents can turn authors' goals into interactive narratives by independently organizing and carrying out generation and revision. As agents generate and revise extensive content, authors struggle to grasp its overall structure, local details, and relationships, complicating continued guidance. We present NarrativeSteward, an authoring environment that organizes outlines, worldbuilding, and narrative graphs as linked artifacts for agent implementation and author guidance. Agent dialogue and project-wide structural review help authors understand the evolving work and guide local and cross-layer revisions, while change records and execution verification help authors assess the resulting work. Technical tests validated the system's change records, recovery mechanisms, and execution diagnostics. In a 12-participant within-subject study, NarrativeSteward supported easier formulation of revision requests and inspection of changes, and greater perceived understanding of changes and story structure, than general-purpose agents. Qualitative findings show how reviewing the work and feedback helps authors develop requirements and guide subsequent delegation. We open-source NarrativeSteward at https://github.com/Tencent/NarrativeSteward.

Wenjin Wang, Jiazhen Lei, Yuxin Sha +6

Interactive Entertainment Group, Tencent Inc Shanghai, China

Narratives Delegation Guidance Cross-Layer Interactions

Sep 30, 2026stat.ML

Steepest Guidance: A Practical and Principled Approach to Inference-Time Alignment of Flow and Diffusion-based Models

Inference-time alignment of flow and diffusion-based models is critical for achieving flexible generative modeling. Theoretically, Doob's

h

-transform provides an elegant solution to this problem, and most existing methods are based on this principle. However, in practice, estimating the optimal guidance derived from Doob's

h

-transform at inference time is challenging. To deal with this issue, we regard inference-time alignment as a sequential optimization problem in the space of probability measures and propose a novel framework called Steepest Guidance, based on the principle of maximizing local improvement in the objective. We provide a theoretical analysis of the proposed method and demonstrate its effectiveness through extensive experiments.

Shokichi Takakura, Akifumi Wachi, Rei Higuchi +2

LY Corporation · The University of Tokyo · RIKEN AIP

Diffusion Alignment Diffusion Models Generative Models Guidance Robust Optimization Principles

Sep 29, 2026cs.LG

Multi-Agent Flow Matching with Decoupled Generative Guidance

Generative modeling is widely used for producing diverse objects from complex, multimodal distributions. However, its expressivity does not, in general, come with formal guarantees that the generated objects satisfy hard constraints or requirements. In multi-agent generation, this problem becomes more challenging because a hard requirement can depend on multiple agents, while each agent may need to determine its own guidance input without relying on the simultaneously computed guidance inputs of other agents. To this end, we introduce DeGG-Flow, a general framework for multi-agent flow matching with decoupled generative guidance. By representing the generative process as a control-affine dynamical system, we develop guidance conditions for two classes of coupled requirements: shared requirements whose satisfaction depends on multiple agents together, and private requirements associated with each individual agent dependent on its neighbors. For both classes, we establish feasibility conditions and finite-horizon convergence guarantees. We further derive a Wasserstein bound that characterizes the distributional deviation induced by the guidance. We demonstrate DeGG-Flow on multi-robot collaboration for crossing a spatial gap by reconfiguring the environment, and on multi-object scene generation with affordance requirements. Across both applications, DeGG-Flow directly generates objects that satisfy all corresponding hard requirements, including at team sizes unseen during training.

Ruoyu Lin, Magnus Egerstedt, Fabio Pasqualetti

Department of Electrical Engineering and Computer Science, University of California, Irvine, Irvine, CA 92697 USA · University of North Carolina at Chapel Hill, Chapel Hill, NC 27599 USA

Conditional Flow Matching Generative Processes Indoor Scene Generation Guidance

Sep 29, 2026cs.AI

Guide, Then Let Go: Gap-Adaptive Teacher Scheduling for Sparse-Reward Agentic RL

Reinforcement learning for long-horizon agents typically relies on sparse outcome-based rewards. This leads to a severe cold-start problem, as early-stage policies often fail to solve sampled tasks, leaving little useful reward signal for learning. To mitigate this problem, we use on-policy distillation (OPD) to provide token-level guidance on the student's own rollouts. We find that the benefit of this guidance depends on the performance gap between the teacher and the student. When the teacher substantially outperforms the student, distillation helps guide the student through the early training stage where outcome rewards provide little learning signal. As the gap narrows and eventually reverses, however, continued distillation becomes less beneficial and may hinder further improvement. Motivated by this observation, we propose Gap-Adaptive Teacher Scheduling (GATS), which augments the student's RL objective with an OPD term whose weight adapts to the teacher-student performance gap. Specifically, GATS gradually reduces teacher guidance as the student approaches the teacher's reference performance and withdraws it once that reference is reached. This enables GATS to leverage task-trained teachers smaller than the student, since teacher guidance is primarily needed during early training. Across ALFWorld, WebShop, and ScienceWorld with three Qwen2.5 teacher-student configurations, GATS achieves the highest average success rate among the compared methods in all three configurations, improving over reward-only GRPO by 4.37%-11.87% under matched student rollout budgets. Code is available at https://github.com/Ricardo-H/guide-then-let-go.

Youling Huang, Tiankuo Xu, Jiaji Liu +10

DUT · Kuaishou · XJTU +5

Repair-Based Group-Relative Policy Optimization Teacher Reward Signal Guidance

Sep 29, 2026cs.RO

PreferenceFlow: Test-Time Guidance of Flow-Matching Robot Policies from Human Interventions

Flow-matching policies can represent complex robot behaviors but remain susceptible to local errors under distribution shift at deployment. Many reinforcement learning approaches to policy improvement require reward signals that are difficult to specify or obtain in real-world manipulation. We present PreferenceFlow, a framework for improving a pretrained flow policy at test time without environment rewards or updates to the base policy. Human intervention chunks are paired with robot chunks generated from the same initial conditioning state to train a preference model. During infer- ence, we adopt the QGF sampling update, replacing its value gradient with the preference gradient evaluated at an estimated clean action. A gradient-cap loss penalizes excessive gradients on intervention pairs, while a zero-gradient loss discourages guidance near actions from expert demonstrations. On four real-world precision insertion tasks with a Franka robot, Pref- erenceFlow achieves a mean success rate of 90.5%, compared with 69% for the frozen policy. Ablations support the roles of gradient regularization and correctly ordered preference labels in the evaluated settings. These results demonstrate the utility of human interventions as local preference supervision for guiding frozen generative robot policies.

Yiqi Tang, Diyuan Shi, Runze Li +1

Westlake University

Flow Policies Robot Policies Flow-Matching Vision-Language-Action Reinforcement Learning From Human Feedback Robot Systems Preference Alignment Learning+2

Sep 28, 2026cs.AI

Why Deterministic PRM Guidance Underperforms in Discrete Diffusion Reasoning

Discrete diffusion language models (dLLMs) expose a denoised solution at every step, which makes process reward model (PRM) guidance look like a way to spend compute at test time. We show that once denoising, PRM scoring, and outcome reward model (ORM) scoring are charged in the same budget of forward passes, its deterministic form loses to a much simpler baseline. Our PRMs score intermediate denoising states and are trained on the correctness of the final answer. On Dream-v0-Instruct-7B with 8 candidates per GSM8K problem, keeping the candidate with the highest PRM score at every scoring step reaches 65.18%, while independent sampling plus an ORM reranker trained for the task reaches 75.13%. The gap grows to 12.69 percentage points (pp) with 32 candidates, and is 9.85 pp on MATH and 12.16 pp on MBPP. We trace it to two separable failures. First, guidance prunes on a weak signal: on GSM8K, PRM ROC-AUC falls from 0.77 to 0.54 as the mask ratio rises, a decay that persists when states are relabeled with fresh rollouts, and pruning lowers the best accuracy reachable from the candidate pool from 81.05% for independent samples to 67.30%. Second, on GSM8K and MATH, the PRM is a poor final judge: a sequential Monte Carlo sampler at the same budget restores that ceiling to 77.89%, yet selecting with the PRM gives 65.48%, on par with deterministic guidance, while a PRM retrained on final states matches the ORM on identical candidates. MBPP separates the two: there the PRM reaches 65.47% when reranking finished programs, on par with the ORM, but 50.88% when it guides denoising. The results point to two targets for dLLM guidance: keep correct partial solutions alive through early denoising, and leave the final choice to a verifier trained on final states. We release the corpus of denoising states with outcome labels and evaluation toolkit for reproducible comparisons at matched compute.

Yan Zhan, Shaobo Liu, Zhijun Gao

Peking University · Shenzhen University

Diffusion Language Models Process Reward Model Score-Based Diffusion Model Guidance Iterative Denoising Methods

Sep 28, 2026cs.CV

Domain-adaptive Zero-Shot Image Enhancement via Locality-Constrained Diffusion Guidance

Denoising Diffusion Probabilistic Models have shown remarkable performance in unconditional image generation. In order to generate images with desired semantics, recent works have restricted the solution space by using guidance constraints in the diffusion sampling process. However, for image enhancement across different domains, these methods struggle to balance two main requirements: looking realistic in the target domain (photorealistic images) and preserving relevant features of the source domain, e.g., low-quality renderings or art paintings. Here, small local changes can alter the fidelity of the image completely, while large changes in other regions might be insignificant. We introduce LocDiff, a locality-constrained guidance method for image enhancement, which serves as a zero-shot extension to pre-trained diffusion models, ensuring the preservation of critical features during domain adaptation. In this way, we retain important local features, while allowing less critical regions to remain unconstrained and not interfere with the guidance process for relevant regions. We evaluate our method on two different domain-shift tasks: For art-to-photo translation, we apply the method in a fully zero-shot setting, preserving facial identity from paintings while generating photorealistic details. For enhancing low-quality fetal ultrasound renderings, we demonstrate zero-shot inference with auxiliary prior alignment. Here, the objective is to artificially add high-resolution characteristics and produce photorealistic ultrasound renderings, a target domain for which no ground truth distribution exists. Our experimental results demonstrate that LocDiff achieves favorable realism-faithfulness trade-offs compared to state-of-the-art methods, enabling controllable cross-domain enhancement.

Theresa Neubauer, Dimitrios Lenis, Astrid Berg +7

VRVis GmbH, Vienna, Austria

Image Enhancement Multi-Reference Image Generation Guidance Fidelity Ultrasound

Sep 28, 2026cs.LG

Adjoint Guidance Flow: Amortized Critic Guidance for VLA Policies

Flow-based Vision-Language-Action (VLA) policies are typically trained by behavior cloning and thus do not explicitly optimize long-term task return. Critic guidance steers generation toward higher-value actions, but existing methods differentiate the critic through a one-step surrogate of the sampler and back-propagate a critic ensemble at every flow step. In contrast, here we propose Adjoint Guidance Flow (AGF), which amortizes trajectory-aware critic guidance into a lightweight guidance network while preserving the pretrained VLA policy. Specifically, we formulate critic-guided flow generation as a deterministic optimal control problem, whose optimal guidance is a costate that carries the terminal critic gradient back through the remaining flow, and regress the guidance network onto this costate while keeping both the VLA and critic frozen. This design provides favorable memory and throughput scaling during training, and inference needs one guidance-network forward pass per step, without the critic ensemble, back-propagation, or adjoint computation. Across LIBERO, RoboCasa, and LIBERO-Pro, AGF consistently improves pretrained VLAs, remains competitive with critic-guidance and policy-fine-tuning baselines, and is the most robust method when a single guidance strength is deployed across tasks. Compared with QGF, AGF runs

3.6\times

faster per guidance step with

7.0\times

fewer parameters, with comparable and even better performance, showing that critic guidance can be trajectory-aware and lightweight.

Jeongsol Kim, Youngjun Jun, Kyumin Choi +6

KAIST · SKKU · GIST

Flow-Matching Vision-Language-Action Critic-Free Reinforcement Learning Reinforcement Fine-Tuning Guidance Trajectory-Aware Hidden-State Analyses Critic

Sep 28, 2026cs.AI

SkillRubric: Co-Evolving Actor Guidance and Evaluator Rubrics for Multimodal Agents

Recent work incorporates reusable skills distilled from past interactions into multimodal agent training, providing procedural guidance for long-horizon planning and tool use. However, policy optimization in these methods remains driven primarily by sparse outcome rewards, providing little supervision for intermediate decisions. Rubric-based rewards address this limitation through explicit intermediate criteria, but reliable rubrics are difficult to construct at scale and often disconnected from the procedure followed by the actor. We observe that a well-structured skill naturally specifies both how to act and what successful execution should achieve. Based on this insight, we introduce SkillRubric, which represents each skill through aligned actor-facing guidance and an evaluator-facing rubric. A multimodal verifier evaluates skill-defined goals using screenshots and tool outputs, assigning completion and progress rewards to the responsible turns. We further introduce an alternating co-evolution scheme that validates guidance revisions through paired rollouts under a frozen policy and rubric revisions offline under fixed guidance. Experiments across diverse multimodal agent benchmarks demonstrate consistent performance gains, while controlled paired rollouts further show that evolved skills provide more effective guidance for planning and tool use than their preceding versions.

Bingqing Jiang, Guoxi Zhang, Jasper Wang +7

The University of Hong Kong · WeChat, Tencent · Peking University +2

Multimodal Agents Task-Specific Rubrics Rubrics Subgoals Guidance

Sep 28, 2026cs.LG

Learn Now, Use Next, Trust Later: Prequential Test-Time Learning for LLM Agents

Adapting large language model agents during deployment requires not only retaining past experience, but also turning new observations into timely guidance. Many test-time learning methods, however, acquire knowledge from completed episodes. Feedback from an ongoing interaction may therefore not be distilled into knowledge soon enough to help the next decision. Acquiring knowledge at the granularity of individual transitions could reduce this delay, but raises a separate challenge: a rule that is useful within one episode may not be reliable enough to guide future episodes. Waiting for validation can forfeit immediate benefits, whereas unrestricted reuse can propagate accidental or misattributed guidance. We introduce StepLearn, a nonparametric framework that separates immediate use from persistent trust. It turns informative transitions into hypotheses that can guide the next step, while requiring prospective validation before reuse across episodes. Their predicted effects are checked against subsequent observations outside the source episodes, and only sufficiently supported hypotheses become available for persistent guidance. This process updates external knowledge while keeping all model parameters fixed. Over five rounds on WebArena-Lite and ALFWorld, StepLearn achieves average success rates of 59.9% and 84.0% with GPT-5-mini, and 57.8% and 88.1% with Qwen3.5-35B-A3B, respectively. It outperforms EvoTest, the strongest baseline, by 2.2-12.7 percentage points across the four settings. Learning dynamics further shows that these gains are not restricted to the final repetition, with advantages already present on first task attempts in most settings.

Tong Zhao, Reed Li, Yuyang Hu +5

Renmin University of China · Tencent

Large Language Model Agents Next Preliminary Study AI Trustworthiness Guidance

Sep 28, 2026cs.CL

Reciprocal Guidance: Orchestrating Draft and Verify Budgets for Advancing the Diffusion-AR Self-Speculation Frontier

Diffusion drafting with autoregressive (AR) verification has emerged as a promising paradigm for efficient speculative decoding. Recent self-speculation models, represented by Nemotron-Labs-Diffusion, further simplify the speculative pipeline by unifying drafting and verification within a shared backbone, while enabling longer acceptance lengths. However, the Pareto frontier between aggregate and per-request throughput remains underexplored. At low concurrency, sequential draft-verify execution requires two model forward passes per round, limiting the effective tokens per forward (TPF). By contrast, at high concurrency, longer drafts incur increasingly expensive computation, forcing individual requests to operate under constrained speculation budgets and preventing full exploitation of the full-backbone drafter. Our key observation indicates that drafting and verification exhibit reciprocal predictability. Draft logits can anticipate likely verification mismatches, while recent verification outcomes predict future drafting utility and suitable block sizes. Building on this observation, we introduce Reciprocal Guidance (RecGuide), a runtime draft-verify orchestration framework that adapts speculative decoding to varying serving loads. RecGuide exploits spare compute capacity through verification-overlapped drafting at low concurrency, while dynamically allocating request-specific draft block sizes as the workload becomes increasingly compute-intensive. Experiments across a wide range of concurrency levels demonstrate consistent throughput improvements over vanilla self-speculation, achieving up to

1.8\times

speedup.

Linye Wei, Shutian Zheng, Haoyu Zeng +1

Institute for Artificial Intelligence, Peking University · School of Integrated Circuits, Peking University · College of Engineering, Peking University +2

Block-Diffusion Drafter Speculative Decoding Drafter Drafts Token Budget Allocation Orchestration+2

Sep 27, 2026cs.LG

Theory Guided and Interpretable Neural Operator Design for Partial Differential Equation Learning

Accurate numerical solutions of partial differential equations (PDEs) are crucial in numerous science and engineering applications. In this work, we introduce a novel neural PDE solver named AFDONet, which incorporates neural operator learning and adaptive Fourier decomposition (AFD) theory for the first time into a specifically designed variational autoencoder (VAE) structure, to solve a general class of nonlinear PDEs on smooth manifolds. AFDONet is the first neural PDE solver whose architectural and component design is fully guided by an established mathematical framework (in this case, AFD theory), turning neural operator design from an art to a science. Thus, AFDONet also exhibits exceptional mathematical explainability and groundness, and enjoys several desired properties. Furthermore, AFDONet achieves outstanding solution accuracy and competitive computational efficiency in several benchmark problems. In particular, thanks to its deep connections with AFD theory, AFDONet shows superior performance in solving PDEs on i) arbitrary (Riemannian) manifolds, and ii) datasets with sharp gradients. Overall, this work presents a new paradigm for designing explainable neural operator frameworks.

Zeyuan Song, Zheyu Jiang

Oklahoma State University Stillwater, OK 74078

Neural Partial Differential Equation Solvers Neural Operators Fourier Guidance

Sep 27, 2026cs.AI

DISCERN: Can AI Agents Work Like Scientists and Guide Discovery?

Reliable automated research requires agents to vet data, verify analyses, and generate hypotheses grounded in trustworthy evidence, potentially reducing routine scientific workload while allowing scientists to focus on interpretation and discovery. Existing benchmarks often only assess analytical task completion or hypothesis generation separately rather than testing whether reliable evidence supports valid and novel claims. We introduce DISCERN (Data Integrity and Scientific Capability: Evidence, Reasoning, and Novelty), a controlled benchmark on real, publicly available datasets that evaluates three key levels of an automated research workflow. The first two levels test data integrity and analysis verification under confounds and tool traps, while the third tests hypothesis generation and revision under adversarial review, including counterfactual cases in which evidence consistent with real data and documented scientific phenomena conflicts with established expectations, motivating alternative explanations and testable hypotheses. Across 203 tasks, eight life-science tracks, and eight models, DISCERN shows that strong aggregate performance can mask level-specific weaknesses. Agents earn perfect scores in only 60.8% of Level 1, 34.2% of Level 2, and 0.6% of Level 3 evaluations, with penalties attributed to rejection of sound data, failure to carry recognized limitations into conclusions, and wide variation in hypothesis production. Cross-track rankings by token and code use are substantially more stable than rankings by evidence judgment, suggesting greater consistency in computational effort than in evidence-based reasoning. These profiles identify opportunities for supervised scientific assistance, but current agents do not yet demonstrate reliable autonomous analysis or discovery. Code and data: https://huggingface.co/datasets/discern-bench-anon/discern-benchmark

Nan Huang, Mario Tapia-Pacheco, Kun Zhou +4

University of California San Diego · Independent Researcher

Scientific Agents Data Science Agents Discovery Artificial Intelligence Agents Guidance

Sep 23, 2026cs.CL

Guides That Cause Actions: An Offline Study of Guide-Action Mutual Reinforcement in Multimodal Web Agents

Web agents are usually evaluated in live environments, where environment state and judge models drift between runs, so the same checkpoint rarely reproduces the same score, making controlled studies of training phenomena impractical. We present WebMRE, an offline benchmark of 541 tasks and 5,293 steps derived from successful WebArena trajectories, with fully audited test labels and a deterministic protocol that scores a checkpoint identically on every run without any environment. Each step pairs a human oriented guide sentence with a grounded action, enabling the first study of the mutual reinforcement effect between them in web agents. Averaged over three seeds the effect holds for both models in both decoding orders and grows with scale: jointly decoding a guide lifts element selection over an action only reference by 0.9 and 0.2 points for Qwen3.5-4B and by 1.7 and 2.2 points for Qwen3.5-9B. A mediation analysis shows that the guide is a causal channel rather than commentary: forcing the gold guide as a decoding prefix lifts action accuracy from .422 to .684, another step's guide collapses it to .055, and a paraphrase that renames the target still recovers half of the gain, so the channel carries instruction meaning and not only the label string. The same channel yields an offline reward that only a replayable protocol makes computable, though optimizing it from a strong checkpoint brings no gain yet. Our fine tuned models outperform GPT-5.5, Claude Opus 4.8, and Gemini 3.5 Flash, run zero shot, on every offline metric.

Chengguang Gan, Yunhao Liang, QingHao Zhang +1

Independent Researcher

Web Agents Guidance

Sep 22, 2026eess.SY

Impact-Time Guidance via Normal Contraction to a Time-to-Go Isochron

We develop a contraction-based perspective on impact-time guidance that augments a baseline homing command with a timing bias. The proposed perspective treats the prescribed schedule as a moving time-to-go isochron and regulates motion normal to that set through velocity-normal lateral acceleration while the interceptor's speed remains constant. We derive a transport equation that characterizes homing-compatible time-to-go coordinates and define a predictor defect that quantifies the mismatch of approximate maps. We show that the scalar timing channel induces a coordinate-invariant rank-one metric on the normal quotient. To account for bounded lateral acceleration, we formulate a robust scalar filter and derive a necessary and sufficient condition for pointwise feasibility. We then show that terminal calibration and funnel invariance establish first interception at the prescribed time under the stated assumptions. We also develop a preterminal alignment and homing handover that avoids singular inversion as lateral timing authority vanishes near collision-course alignment. The proposed perspective accommodates analytic, numerical, and learned time-to-go maps that satisfy the required calibration and regularity conditions.

Shivam Bajpai, Abhinav Sinha

Guidance, Autonomy, Learning, and Control for Intelligent Systems (GALACxIS) Lab, Department of Aerospace Engineering and Engineering Mechanics, University of Cincinnati, Cincinnati, OH, 45221, USA

Conditional Velocity Acceleration Collision Prediction Guidance

Sep 22, 2026cs.LG

Learning to Defer with Guidance on Real World Medical Data

Medical image interpretation is high-volume and time-consuming, and while AI interpretation can reduce workload, fully autonomous deployment carries potential safety concerns and low specificity may in practice lead to increased clinician workload. Learning to Defer (L2D) addresses this by selectively routing cases between autonomous prediction and human experts by learning from input features and AI model and human performance. While theoretical guarantees have been proven for L2D, its performance has not been validated on real-world medical datasets with human reader annotations. We evaluate the predictor-rejector formulation of two-stage L2D, where the AI predictor model is fixed and separate from the trainable routing or rejector model, on Collab-CXR, a multilabel chest X-ray dataset with multiple human annotations per case. This is the first work to look at L2D in the context of real-world medical imaging data with human annotations. We further introduce a new setup, L2D with Guidance, where the decision space is extended to three choices: predict autonomously, defer to a human expert, or defer to a human expert and provide AI guidance. We compare multiple rejector architectures and loss functions, and different input feature availabilities. This is reproduced on two larger datasets, VinDr-CXR and CheXpert. Our results show that two-stage L2D with Guidance outperforms classic two-stage learning to defer, as well as human-alone, AI-alone and AI-guided human baselines. Notably, this performance is achieved with simpler loss functions compared to formally defined L2D surrogate loss functions in current literature.

Emma Sun, Joshua Strong, Alison Noble

Department of Engineering Science, University of Oxford, UK

Human Annotations Multi-Stage Training Guidance

Sep 21, 2026cs.CV

Classifier-Free Guidance in Flow Matching: Non-Autonomous Potentials, Overshoot, and Posterior-Mean Control

Classifier-free guidance (CFG) improves conditional generation in Flow Matching, but strong guidance can distort the generated distribution and reduce diversity. We provide a geometric account of this behavior by viewing Flow Matching as a time-varying gradient flow and characterizing how CFG reshapes its underlying potential. This view explains how stronger alignment can be accompanied by mean displacement and trajectory concentration, and motivates controlling guidance through the model-implied terminal posterior mean. We therefore propose Posterior-Mean-Capped CFG (PMC-CFG), a training-free, per-sample method that adaptively retains the strongest feasible guidance without additional network evaluations. Experiments on synthetic and large-scale image-generation benchmarks show that PMC-CFG limits guidance-induced distortion and concentration while improving the alignment--diversity trade-off, with particularly strong benefits when nominal guidance is large.

Jishen Peng, Zheng Ma

School of Mathematical Sciences, Shanghai Jiao Tong University, Shanghai, China · Institute of Natural Sciences, MOE-LSC, Shanghai Jiao Tong University, Shanghai, China · Qing Yuan Research Institute, Shanghai Jiao Tong University, Shanghai, China +1

Classifier-Free Guidance Wasserstein Gradient Flows Guidance

Sep 16, 2026cs.LG

How to Guide Your Language Flow

We introduce a new method to guide flow matching models. Our approach, which we call probe guidance, uses the frozen internal states of an existing diffusion model to construct a guidance signal. This works using a similar principle as autoguidance, but eliminates the need for an additional forward pass at inference time and provides a reliable path to ensure that the weak and strong model share similar dynamics. We apply and benchmark this method on continuous diffusion language models, where probe guidance sets a new state-of-the-art performance on unconditional generation. When applied to a 1.7B diffusion language model, probe guidance consistently improves on multiple choice question answering benchmarks. Using our probes, we study the traditional autoguidance setting where the strong model is a weak checkpoint, and find that the weak model must come from a low-entropy region of training. These findings both provide a practical way to improve diffusion language models and shed light on the actual mechanism behind autoguidance, which is currently poorly understood.

Rohit Dilip, Tianrong Chen, Yuyang Wang +3

Apple · Caltech

Diffusion Language Models Diffusion Models Guidance Fluency

Sep 14, 2026cs.LG

ProtoGuide: Prototype-Driven Guidance for Class-Conditional Graph Generation

Discrete diffusion models are a prominent family for graph generation, but standard class-conditional mechanisms embed the class signal in the denoiser during training, tying the conditioning mechanism to the trained model. Classifier guidance avoids this coupling in continuous domains by steering a frozen model with a classifier's gradient, but discrete graph diffusion samples discrete edge states, so gradients cannot propagate through the sampled graph. We introduce ProtoGuide, a post-hoc, backbone-agnostic framework that recovers an analogous mechanism. At each reverse step the denoiser's per-edge output is relaxed into a differentiable soft adjacency, embedded by a frozen Siamese graph neural network, and scored against a target-class prototype and its nearest competitor; the resulting per-edge gradient, damped by a cosine schedule, is injected back into the denoiser output. All components stay frozen, so guidance is retargeted by supplying a different prototype. On five classes of real-world networks and two architecturally different backbones, EDGE and DiGress, ProtoGuide raises macro classification accuracy from 50.7% to 73.5% and from 73.6% to 83.8%, and outperforms DiGress's built-in conditional training under our configuration. Gains are largest where the unguided models are weakest, and are not uniform across classes. Per-graph coverage remains high in most settings, while distributional effects are class-dependent. A Best-of-N selection baseline matches this accuracy given enough oversampling, but at a substantial cost in graph diversity. An independently initialized classifier, a directionality test, and a few-shot analysis support target-directed steering and robustness to very small support sets.

Salvatore Romano, Marco Grassia, Pietro Liò +1

Department of Electrical, Electronic and Computer Engineering, University of Catania, Italy · Department of Computer Science and Technology, University of Cambridge, UK · University Campus Bio-Medico of Rome, Italy

Physics-Guided Diffusion Learnable Prototypes Diffusion Sampling Guidance Data Generation

Sep 14, 2026cs.CV

Unsupervised Point Cloud Registration via Training-Time Semantic Guidance

Unsupervised registration of large-scale LiDAR point clouds remains challenging due to the geometric ambiguity inherent in outdoor scenes, which degrades pseudo-label quality and leads to suboptimal convergence, particularly for sparse, low-resolution scans such as those from nuScenes. We reveal that registration models intrinsically encode semantic awareness that strongly correlates with registration accuracy, albeit without explicit semantic supervision. However, this native awareness is fragile: noisy supervision arising from geometric ambiguity in unsupervised settings rapidly erodes the learned semantic structure, causing performance collapse. To this end, we propose CAESAR, a teacher-student framework guided by an off-the-shelf 3D segmentation model exclusively during training. We observe that potential inlier matches are often buried just beneath a few spurious neighbors in the noisy feature space, motivating Dual-Cue Guided Re-Matching to recover them through reselection rather than simply rejecting. Building on this, a train-only Semantic-Geometric Label Mining performs lightweight, batch-specific teacher refinement and mines reliable pseudo-labels under semantic guidance. We further introduce Semantic Predictive Distillation to consolidate the student's semantic awareness in the feature space. Extensive experiments on KITTI and nuScenes demonstrate state-of-the-art performance, with pronounced gains on the challenging nuScenes benchmark. Crucially, CAESAR incurs zero inference overhead and requires no semantic annotations on the registration data. Code will be released.

Kezheng Xiong, Shiyun Xu, Sheng Ao +3

Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, China · Fujian Key Laboratory of Urban Intelligent Sensing and Computing, Xiamen University, China

Point Cloud Registration Light Detection And Ranging Point Clouds Image Registration Geometric Machine Learning Guidance

Sep 14, 2026cs.CL

MUSE: A Theory-Harnessed Story Engine for Vibe Narrativizing

LLMs have been able to generate fluent prose, but high-quality stories also require coordinated decisions about plot, character, and language across planning, drafting, and revision. We formulate Vibe Narrativizing as turning natural-language writing requirements into a finished story. MUSE, a Theory-Harnessed Story Engine, addresses two bottlenecks: rule quality and sustained rule realization. Story theory supplies the rules, and a practical agent harness puts them to work. Knowledge engineering organizes Robert McKee's theory through rule atomization, semantic consolidation, mechanism abstraction, a single source of truth, and layered disclosure; typical examples clarify judgments that depend on context and aesthetic purpose. The harness preserves story decisions in intermediate deliverables across design, character performance, scene composition, and revision. Context engineering supplies each role with relevant guidance and decisions; a masterwork corpus provides inspiration and prose references. A worked example follows a requested object from its thematic role to climactic actions. Across four base models, MUSE improves WritingBench by 1.1 to 6.2 points over zero-shot generation; it is the only multi-stage system in our comparison to do so. It also raises LongStoryEval by more than ten points on three of the four models. ConStory-Bench consistency error density remains in the low single digits for all four models, below every reproduced story-system baseline on three of the four models. Ablations locate the largest quality contribution in structural design, voice-specific effects in the character path, and further gains in revision.

Jianxiang Ma, Xiaocui Yang, Daling Wang +4

School of Computer Science and Engineering, Northeastern University, Shenyang 110819, China · OranAI, Shenzhen 518057, China · OranAI Ltd., City of Industry, CA 91748, USA

Narrative Generation Narratives Guidance

Sep 14, 2026cs.LG

GUIDE: Generative Utility Inference and Decision Engine

Measuring the preferences of human users remains a fundamental challenge of AI alignment. Existing elicitation approaches struggle to efficiently discover multidimensional preferences or accurately ground these inferences in domain knowledge. To address this, we introduce GUIDE, an LLM-driven elicitation architecture that infers user preferences through conversations by combining Bayesian adaptive sampling for question selection and symbolic representation learning to initialize domain-specific preference models. GUIDE generalizes adaptive sampling to diverse elicitation questions through an extensible type system of transforms on a parameterized preference state. GUIDE produces domain-specific preference representations through an initialization process using symbolic rule-based learning to capture world knowledge and set priors over preference dimensions grounded in data about decision alternatives. The architecture provides observability and steerability to facilitate deployment and analyze elicitation processes. In silico experiments on investment portfolio optimization demonstrate that GUIDE improves cold-start and minimizes recommendation regret consistently within early elicitation interactions across user personas compared to prior work, LLM-only baselines, and ablated GUIDE versions.

Anagha Tiwari, Alexander G. Gray, Nick Feamster +3

Department of Computer Science, University of Chicago · Centaur AI Institute, University of Chicago · Heinz College & School of Computer Science, Carnegie Mellon University +1

Preference Alignment Learning Elicitation Artificial Intelligence Alignment Decisions Guidance Adaptive Sampling+1

Sep 12, 2026cs.RO

2AM: Grounding Agent-Side Memory as Guidance for Steerable Action Models in Long-Horizon Manipulation

Long-horizon robot manipulation requires memory, but not necessarily inside the action policy. To address such tasks, current agentic systems often combine VLAs with planners and geometric tools, sometimes using additional depth or calibrated geometry. These systems confound attribution: gains may come from richer observations or alternative motor tools, while failures may stem from either the policy or an under-specified language interface. We isolate this question through a deliberately constrained design: less tool breadth, but greater interface bandwidth. 2AM makes a multimodal Agent the sole holder of task memory and a single RGB-based, episodically stateless Action Model the sole executor of task-relevant motion. The Agent compiles interaction history into subtask language and optional 2D grasp, place, and move hints that bind its physical intention at different time scales. To teach this steerability to the VLA, we augment demonstrations with structured hint labels and train under condition dropout, spatial noise, and temporal jitter to tolerate imperfect Agent outputs. On LIBERO-Mem, without depth, online geometry, or planner-based object motion, 2AM reaches 76.3% average completion, a 61.5-point improvement over the strongest reported baseline of 14.8%, together with 63.0% relaxed and 11.8% strict success. These results show that task memory can remain Agent-side. They further show that Action Model capability depends not only on what the policy has learned, but on how precisely the Agent can steer it.

Yutong Hu, Fengjiao Chen, Xuezhi Cao +1

KU Leuven, Dept. Mechanical Engineering, Research unit Robotics, Automation and Mechatronics · Meituan Inc. · KU Leuven, Dept. Electrical Engineering, Research unit Processing Speech and Images

Action Expert Multimodal Agents Motion Planning Guidance

Sep 3, 2026cs.LG

Guide, Not Bind: Why Defeasible Priors Fail in Augmented Lagrangian Causal Discovery

Differentiable causal discovery methods increasingly encode expert priors as forbidden-edge constraints enforced by an Augmented Lagrangian (ALM) penalty, on the assumption that a data-adaptive relaxation mechanism will discount and eventually override a rule the data consistently contradicts. We show this design, which we call \emph{guide, not bind}, fails for two independent, precisely characterized reasons, and that directly repairing both restores it only partially. First, sequential penalty-ramping ALM suppresses a wrongly-forbidden true edge before any counterfactual check can detect it: we give three necessary conditions any adaptive relaxation must satisfy to avoid this (Proposition~\ref{prop:conditions}), prove that DADU---the natural relaxation rule this paper introduces as the object of study---violates all three (Corollary~\ref{cor:dadu_failure}), and confirm the failure across 3{,}072 training runs spanning graphs from 4 to 32 nodes, where a single wrong prior suppresses a true edge in 87--97% of trials under DADU. Second, and independent of any fix to the mechanism, we prove in closed form that the standard correlation-matching objective ties a true edge and its reverse to an identical cost of exactly

2r^2

(Lemma~\ref{lem:tie}), not because the underlying equal-variance model is unidentifiable, but because normalizing to correlation discards exactly the variance information that would make it identifiable; covariance matching instead separates the two directions by a provable margin of at least

w_0^4

(Lemma~\ref{lem:separation}).

Sairam Sundararaman, Sara Girdhar, Manit Narasimha Murthy +2

Department of Computer Science (AI & ML) PES University · Department of Computer Science2026 PES University · Department of Computer Science PES University

Causal Discovery Methods Prior Knowledge Integration Spurious Correlations Convex Relaxation Guidance

Sep 1, 2026cs.CL

StudentSim: Training LLM-based Student Simulators

AI tutors are most useful when they adapt to each student's strengths, weaknesses, and preferred guidance, but evidence about which guidance works for which student is sparse, slow, and costly to collect from real learners. Student simulators can provide this signal as a proxy, yet existing approaches are limited: state-tracking models fit student behavior but struggle to process explanations or corrections, while LLM role-play follows guidance fluently but does not reliably match the competence of the student being imitated. We present StudentSim, a training framework that turns sparse per-student data into individualized simulators through pooled training followed by per-student specialization. The resulting simulators both mirror a student's own responses and update them under tutor guidance. We also introduce StudentSimEval, a standardized protocol covering 60 students across chess, second-language English writing, and mathematics, using public learner datasets with de-identified records shared for research. StudentSimEval measures behavioral fidelity (F), or how well a simulator matches a student's responses, and guidance responsiveness (R), or how readily it updates under tutor guidance, with all methods fit and evaluated on the same records. Across all three domains, StudentSim outperforms GPT-5.4 on both metrics. In chess, StudentSim reaches F=0.51 and R=0.91, compared with 0.23 and 0.72 for GPT-5.4 and 0.45 and 0.27 for Maia2. As a proof of concept, using StudentSim as a reward model for tutor reinforcement learning produces a chess tutor that expert humans rate as more accurate, better-guided, and more personalized than a no-RL baseline and a tutor trained against a GPT-5.4 simulator reward. Code is available at https://github.com/microsoft/StudentSim.

Ke Yang, Chenglong Wang, Michel Galley +4

1Microsoft Research · University of Illinois Urbana-Champaign

Tutors User Simulation Student Guidance Offline Reinforcement Learning

Sep 1, 2026cs.RO

Accelerating Reinforcement Learning via MPC Solver-Gradient Guidance for Weights-varying MPC

In Model Predictive Control (MPC), cost-function weights shape closed-loop behavior, yet changing conditions often make fixed parametrizations suboptimal and motivate context-dependent online adaptation. Learning such policies is difficult because behavior depends implicitly on numerical MPC solutions, producing nonlinear, potentially nonsmooth, long-horizon dependencies on policy parameters. This creates a bias-variance tradeoff: Reinforcement Learning (RL) optimizes realized closed-loop return from environment samples but is sample-inefficient, whereas Gradient-Based Policy Learning (GB-PL) uses low-variance solver gradients from differentiable MPC to optimize surrogate losses on predicted trajectories but can be biased under model mismatch. We propose Solver-Gradient Guided Reinforcement Learning (SG-RL), a solver-sensitivity augmentation for RL-based online MPC cost-weight adaptation. SG-RL keeps sampled closed-loop return as the objective and uses bounded solver-derived gradients as auxiliary guidance to improve stability and sample efficiency. We instantiate SG-RL in Proximal Policy Optimization (PPO) with four modular algorithms that inject solver-gradient guidance into actor-update scaling, policy loss, advantage estimation, and value-function learning. On two full-scale autonomous racing platforms with intentional model mismatch, SG-RL reaches PPO's best closed-loop return with up to 70.6% fewer samples, outperforms GB-PL baselines by at least 54% in closed-loop return, and generalizes zero-shot to unseen environments.

Baha Zarrouki, Arslan Thobani, Jasper Hoffmann +6

Offline Reinforcement Learning Model Predictive Control Temporal Difference Gradient Guidance

Sep 1, 2026cs.CL

Trust Your Guide Only When Certain: Uncertainty-Aware Sparse Alignment at Inference Time

A prominent paradigm in inference-time alignment employs lightweight supervisors to steer Large Language Models (LLMs). Through empirical analysis, we identify a structural mismatch in this paradigm: weak supervisors exhibit pervasive high entropy across the vast majority of tokens, yet prevailing dense intervention approaches mandate supervision at every decoding step. This leads to frequent low-confidence interventions that can disrupt valid base-model reasoning and incur substantial utility costs. To resolve this, we propose TUSA (Trust-based Uncertainty Sparse Alignment). Moving away from continuous oversight, TUSA reframes alignment as a dynamic arbitration process, introducing an uncertainty-aware arbiter that authorizes intervention only when two conditions are met: the supervisor is confident and the token is semantically salient. This mechanism effectively filters out uncertainty-driven noise and redundant supervision. Extensive experiments across multiple models and benchmarks show that TUSA consistently improves both safety alignment and general helpfulness. By bypassing approximately 50% of alignment steps, it not only enhances safety preference by up to 15.6%, but also boosts general preference rates by up to 12.0% compared to the dense baseline, demonstrating that selective, high-precision alignment can outperform continuous supervision.

Zeen Zhu, Zhuo Li, Weiyang Guo +4

Harbin Institute of Technology, Shenzhen, China · Huawei Technologies Co., Ltd. · Beijing Academy of Artificial Intelligence, China.

Distributional Alignment Inference-Time Defense Inference-Time AI Trustworthiness Guidance

Aug 31, 2026cs.CL

GUIDE: Guiding Internal Evidence with Language Instructions

Large multimodal models follow instructions about what to generate, but not necessarily about what evidence to rely on. Hence, models may continue to depend on shortcut-associated cues even when instructions suggest otherwise. We introduce GUIDE, a framework for controlling internal evidence usage through language instructions. GUIDE combines grouped parameter-efficient adaptation with instruction-conditioned gating to modulate multimodal evidence pathways during reasoning and generation. We further introduce a pathway-level evaluation framework that characterizes instruction-conditioned evidence modulation through reliance sensitivity, controlled perturbation analysis, pathway modulation, and autoregressive decoding dynamics. Across multimodal reasoning, classification, and generation, GUIDE induces structured and instruction-aligned redistribution of evidence reliance while largely preserving task behavior. Experiments on GQA, TextVQA, MM-IMDb, CREMA-D, RAVDESS, and Flickr30K show that GUIDE improves robustness under targeted evidence perturbations and enables controllable modulation across diverse multimodal settings. This suggests that multimodal instruction following can extend beyond output control toward regulating how different evidence sources contribute to model predictions.

Soyeon Caren Han, Hyunsuk Chung, Jinwoo Kim +2

School of Computing and Information Systems, The University of Melbourne, Melbourne, Australia · Department of Computer Science and Engineering, Korea University, Seoul, Republic of Korea · Brain Science Institute, Korea Institute of Science and Technology, Seoul, Republic of Korea +1

Multimodal Model Guidance Instruction Shortcut Learning

Aug 31, 2026cs.LG

Online Estimation of Dynamic Origin-Destination Matrices Using Reinforcement Learning with Link-Flow Propagation Guidance

Online dynamic origin-destination (OD) matrix estimation (DODE) calibrates time-dependent OD demand to reproduce observed link-flow trajectories. In online, OD demand should be estimated from current observations and propagated network states while subsequent observations and stochastic dynamic network loading (DNL) outcomes remain uncertain. Recently, reinforcement learning (RL) has emerged as a promising alternative, reducing computational burden by replacing iterative algorithms while being applicable to stochastic environments. However, because the policy is trained offline and deployed online, it must handle varying target link-flow trajectories; since each target trajectory defines the link-flow error used in the reward, the same OD demand vector can require different adjustments, making conventional scalar feedback ambiguous. To address this gap, this study proposes LFPG-RL, which integrates link-flow propagation guidance (LFPG) into proximal policy optimization (PPO). LFPG combines link-flow error sensitivities with the contribution of each OD-time demand component to simulated link flows, transforming aggregate mismatch into OD-specific advantage shaping for PPO actor updates. At deployment, the policy requires only a single forward pass. LFPG-RL is developed and evaluated on 250 weekday trajectories of 15-min link-flow data from a Melbourne arterial network modeled by a link transmission model with stochastic route choice. On held-out trajectories, LFPG-RL achieved an RMSE of 4.69, MAPE of 20.15%, and Pearson correlation of 0.995. These results support the contention that our method is a more efficient and accurate online OD demand calibration method compared to existing ones.

Donggyu Min, Dong-Kyu Kim

Seoul National University · Seoul, 08826, South Korea

Origin Destination Flows Flow Policies Bellman Equation Propagation Guidance

Aug 31, 2026cs.CL

ALTSTEER: Selective Safety Steering for Moving Beyond Hard Refusals to Constructive Alternatives

Safety alignment is essential for deploying large language models, requiring systems to prevent harmful compliance while preserving helpfulness on benign requests. Activation steering offers a training-free inference-time approach to safety control, but effective safety steering requires addressing two coupled questions: when to intervene and how generation should be shaped after intervention. However, existing safety steering methods remain limited along both dimensions, as their triggering mechanisms can be unstable across domains and refusal-oriented steering often yields rigid refusals rather than constructive safe guidance. To address these limitations, we propose ALTSTEER, an inference-time framework that couples selective intervention with refusal-anchored constructive redirection within a single inference pass. ALTSTEER uses an internal refusal-relevant signal to decide when to steer, and applies staged steering to shift generation from refusal-oriented control toward constructive alternatives. Evaluations on Llama-3.1 and Qwen2.5 show that ALTSTEER preserves benign utility while improving constructive safe-completion behavior, especially on models that otherwise tend to produce short refusals for harmful requests.

Hoejoon Kwon, Byeonggeuk Lim, Kahyeon Kim +1

Department of Artificial Intelligence, Chung-Ang University · Graduate School of Advanced Imaging Science, Multimedia & Film, Chung-Ang University

Steering Refusals Alternative Guidance

Aug 26, 2026cs.CV

SMART: MLLM-guided Temporal Alignment for Unifying Sign Language Recognition and Spotting

Continuous sign language recognition (CSLR) aims to recognize gloss sequences from unsegmented sign videos under weak sequence-level supervision. However, existing methods rely on sentence-level gloss annotations, providing limited temporal and semantic guidance for fine-grained representation learning. Conventional video-text alignment also requires large batch sizes, making it inefficient for memory-intensive sign language video training. In this work, we propose SMART, an MLLM-guided temporal alignment framework for joint sign recognition and spotting. SMART uses MLLMgenerated motion descriptions as auxiliary semantic cues and performs stable videotext alignment under small-batch training. To improve temporal representation learning, we introduce a Multi-Scale Temporal Adapter that models temporal interactions during transformer encoding. For dense temporal localization, SMART incorporates CSFormer, a CSLR-guided spotting module that injects recognition-derived gloss evidence into a boundary-aware spotting network. This unified framework enables CSLR features to benefit spotting, while spotting supervision complements weak CTC-based recognition. Experiments on four sign language benchmarks, including PHOENIX14-T, CSL-Daily, Large-scale KSL, and Disaster and Safety KSL datasets, demonstrate the effectiveness of SMART across both recognition and spotting tasks.

Eunjee Choi, JungHoon Sung, Seongwhan Cho +2

Dankook University · Yongin, Korea

Sign Language Translation Guidance

Aug 26, 2026cs.CL

GUIDE: Generative Unsupervised Chinese Query Correction via Phonetic and Visual Shared-ID Encoding

Chinese query correction (CQC) is important for search and query recommendation on content platforms, but supervised methods rely on large annotated correction pairs that are costly to maintain as query vocabularies evolve. Unsupervised correction with language models is attractive, yet in the short-query setting, unconstrained generation often over-corrects ambiguous inputs toward high-frequency phrases, causing intent drift. We propose \textsc{GUIDE}, a generative unsupervised framework for CQC based on a confuse-then-clarify paradigm. \textsc{GUIDE} encodes phonetically or visually confusable characters with shared-IDs and reconstructs the original query with an encoder--decoder architecture, which constrains correction to plausible confusion neighborhoods while learning from unlabeled query streams. A time-decayed, query-frequency-weighted objective further supports adaptation to rapidly changing query vocabularies. Experiments on \textit{QSpell 250K} and a large-scale real-world dataset (\textit{KwaiSearch}) show that \textsc{GUIDE} consistently outperforms strong baselines, while online A/B testing further confirms gains in correction quality and downstream engagement.

Lei Yang, Binbin Huang, Jiwei Tan +4

Kuaishou Technology · School of Data Science, Fudan University

Grammatical Error Correction Text Corpora Guidance Generative Models Streaming

Aug 12, 2026cs.AI

GUIDE: Governed Unified Intelligence for Document-to-Artifact Generation in Enterprise Settings

Enterprise guideline documents are heterogeneous and multimodal, combining narrative text, complex tables, and embedded images. Existing LLM and VLM systems face hallucinated content, table structure degradation, and lack governed workflows extending beyond extraction to validation and artifact generation. This leaves enterprises to perform this manually, consuming 2-3 days per document. To address this, we introduce GUIDE, a governed multi-agent framework built on a shared versioned rule store with schema-validated inter-agent contracts and end-to-end provenance tracking. Six specialized agents handle parsing, VLM-driven extraction, consistency checking, evaluation, human-in-the-loop (HITL) escalation, and persona-tailored artifact synthesis. Evaluated on 120 real-world enterprise guideline documents, GUIDE achieves 96% document success, extracts 3,896 rules with 71.4% auto-approved, produces 812 deployment-ready artifacts, and reduces turnaround to 40-125 minutes per document.

Shivali Dalmia, Sumukha Thoppanahalli, Mohammadreza Sediqin +1

Centific Research Washington, USA

Enterprise Systems Guidance Contracts Intelligence

Aug 11, 2026cs.RO

Enabling Scalable Kinesthetic Teaching via Observer-based Hand-guiding with Active Support

Kinesthetic teaching through robot hand-guiding provides a natural interface for collecting demonstrations in imitation learning and programming-by-demonstration. However, extended sessions cause operator fatigue, reducing demonstration quality and limiting scalability. Current industrial hand-guiding approaches typically provide no active assistance, and alternatives require costly wrist-mounted force-torque sensors or rely on learned motion priors unavailable for new tasks. We propose RHOAS, a hand-guiding scheme that actively supports operator-intended motions using model-based force estimation without additional hardware. Our approach considers robot hand-guiding as an actively controlled interaction by the human operator, rather than an interaction with a passive environment. Standard methods used for hand-guiding typically rely on general passivity-based compliant control architectures that unnecessarily increase operator effort and limit the range of demonstrable motions without providing the intended stability guarantees in active interaction. Instead, our design utilizes model-based external torque estimation, internal joint torque sensing, and redundant robot kinematics to actively support human physical input within the human interaction frequency bandwidth. We address practical challenges of relying on observer-based force estimation, including suppression of unmodeled joint elastic dynamic effects and measurement noise in the feedback path, reduced estimate accuracy close to kinematic singularities, and static gravity compensation errors. In a user study with 16 participants on a KUKA LWR iiwa we demonstrate statistically significant reductions in physical effort, improved maneuverability for both precise and agile tasks, and clear user preference.

Anna Tuma, Giuseppe Monetti, Jochen J. Steil +1

Technology & Innovation Center, KUKA, Augsburg, Germany · Institute of Robotics and Process Control, Technische Universität Braunschweig, Braunschweig, Germany

Robotic Hands Ground Reaction Forces Robotic Manipulation Imitation Learning Guidance

Aug 11, 2026cs.CV

When Vision Becomes Text: Visual Token Pruning via Cross-Modal Residual Guidance in VLMs

Abundant visual information strengthens vision-language model (VLM) perception, yet massive visual tokens raise inference costs. Existing visual token pruning methods rely on similarity-based guidance, which exploits pairwise text-vision and vision-vision token correlations for compression. However, such methods only capture local layer-level signals and overlook the whole inference process in VLM. In this paper, we revisit VLM inference and present a new efficient guidance scheme that complements similarity-based guidance. In particular, we identify a key observation: as LLM layers deepen, text tokens continuously aggregate visual information via self-attention and progressively absorb partial visual content into textual representations. To quantify this phenomenon, we propose Cross Modal Absorption (CMA) from a geometric representation perspective to measure how much visual information is absorbed by text, revealing that more visual tokens in deeper layers can be approximately explained by the text subspace. We accordingly propose Cross Modal Residual (CMR). It projects visual tokens onto the text subspace via Tikhonov regularized least squares and exploits reconstruction residuals to quantify visual information that cannot be explained by text. Finally, based on CMR, we present SIEVE, a training-free visual token compression method that combines CMR, text-attention relevance, and residual-space diversity to retain task-relevant and complementary tokens. Experiments on diverse VLM architectures verify the effectiveness of SIEVE. For instance, on LLaVA-NeXT-7B, SIEVE keeps only

11.1\%

of visual tokens while preserving

97.5\%

of the original average performance, achieving

3.62\times

prefill speedup,

2.49\times

end-to-end speedup, and a

6.02\times

KV-cache reduction.

Congyang Ou, Ruike Song, Yang Zhou +3

Northwestern Polytechnical University · Chongqing University · MiLM Plus, Xiaomi Inc.

Visual Token Pruning Cross-Modal Text Analysis and Detection Subspace Guidance

Aug 10, 2026cs.RO

Graph-Guided Safe Diffuser: Topological Graph Guidance for Safe Diffusion Planning

Many diffusion-based planners enforce safety through inference-time guidance, but such interleaved trajectory deformations often degrade kinematic feasibility due to manifold rupture. We propose Graph-Guided Safe Diffuser (G2SD), a hierarchical framework that leverages a high-level topological graph planner to guide a low-level diffusion model. G2SD enforces safety at a structural level by abstracting the data manifold into a learned latent graph, on which high-level planning is performed. Continuous trajectories are generated by diffusion planners, which are conditioned on the graph node representations selected by the high-level planner. Theoretical analyses demonstrate conditions under which manifold rupture occurs in diffusion planners, and show that G2SD improves safety by reducing the constraint violation probability as the number of segments increases. Experiments demonstrate that G2SD substantially outperforms baselines, increasing goal-reaching rate without any collision from 40-50% to 98% in Maze2D navigation and also achieving superior task scores in locomotion.

Nakgyu Yang, KwangBin Lee, SooJean Han

School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST) Daejeon, Republic of Korea

Diffusion Planning Physics-Guided Diffusion Planning Guidance Maze Task Latent Variable

Aug 10, 2026cs.CV

Beyond Uniform Restoration: Empowering All-in-One Restoration with Pixel-Level Multimodal Guidance

All-in-one image restoration is a unified low-level vision task that aims to effectively recover high-quality images from inputs degraded by various types and levels of corruption using a single model. Recent works have achieved remarkable progress by learning degradation-adaptive prompts or network architectures. However, these methods typically apply a uniform restoration strategy across the entire image, neglecting the fact that different regions may suffer from distinct degradation types and varying degrees of severity. In contrast, we propose to perform restoration at the pixel level, thereby enabling more fine-grained and precise control over the restoration process. Specifically, we present MGN-AIR, a novel pixel-level restoration framework for all-in-one image restoration. Our approach first learns to estimate a pixel-level visual prompt. Then, it leverages both textual and visual prompts to provide global and local degradation cues, guiding the model on where to look and how to restore at each pixel. We conduct extensive experiments on multiple all-in-one image restoration benchmarks, covering a wide range of tasks including denoising, deraining, deblurring, dehazing, desnowing, and low-light enhancement. Experimental results demonstrate that our proposed method consistently and significantly outperforms existing approaches.

Chunxiao Liu, Wei Liu, Anbin Xiong +1

Xiaomi Corporation Beijing, China

Image Restoration Restoration Pixels Degradation Computer Vision Guidance

Aug 10, 2026cs.HC

Intuitive Hand Positional Guidance Using McKibben-Based Surface Tactile Sensations to Shoulder and Elbow

Hand positional guidance with intuitive perception is crucial for enhancing user interaction and task performance in immersive environments. However, conventional hand positional guidance methods, relying on tactile sensations, lack intuitiveness. Consequently, users require instruction on the relationship between the tactile sensation and target position of the guidance before using these methods. Additionally, the user needs training to become familiar with tactile sensations. This study presents a hand positional guidance system with intuitive perception that leverages McKibben-based surface tactile sensations directed to the shoulder and elbow. We developed a wearable fabric actuator that provides McKibben-based surface tactile sensations to induce six specific movements: elbow flexion, extension, shoulder abduction, adduction, horizontal abduction, and horizontal adduction. The effectiveness of the actuator was experimentally validated, demonstrating its high accuracy in intuitively inducing six movements. An algorithm based on the equilibrium point hypothesis and Weber-Fechner law was implemented to regulate the intensity of the tactile sensations for hand positional guidance. Furthermore, the accuracy and speed of the proposed system were compared with that of conventional guidance methods utilizing synthesized speech and vibrotactile guidance.

Kenta Yokoe, Yuki Funabora, Tadayoshi Aoyama

Department of Micro-Nano Mechanical Science and Engineering, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Aichi 464-8603, Japan · Japan Society for the Promotion of Science, Tokyo, 102-0083, Japan · Department of Information and Communication Engineering, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Aichi 464-8603, Japan +2

Tactile Wrist Hand Guidance

Aug 8, 2026cs.CL

Commitment Before Realization: When Classifier-Free Guidance Becomes Unnecessary in Masked Diffusion Language Models

Classifier-free guidance (CFG) is usually kept on throughout masked diffusion language model decoding, although its benefit varies across prompts and over time. We study when CFG is actually needed by comparing, from any partial output, the probability of eventual constraint satisfaction under continued CFG and under base-only continuation. Their difference defines the remaining value of guidance. Guidance dependence is highly prompt-specific. Many prompts already succeed without CFG, while for others it provides no measurable benefit or can be harmful. For prompts that do benefit, the gain is often concentrated early. We define the commitment horizon

\astar

as the earliest point from which switching all remaining decoding to the base model reduces final success by no more than a chosen tolerance. Under the base model, the corresponding success probability, or committor, is a martingale. To first order, CFG's per-step effect is governed by the covariance between the guidance logit direction and the successor committor. This gives a local account of when guidance can help, but it does not by itself locate the horizon. Among prompts with an observed preterminal horizon,

\astar

is usually early and varies more within constraint families than between them. Freezing each prompt at its own cross-fitted horizon is noninferior to full CFG on all 13 subtasks at the prespecified margin, even while many tokens remain masked. This separates commitment from realization. The boundary also identifies a later region in which higher parallelism adds only a small cost in constraint success, although fluency still degrades with parallel width. For failed trajectories, reopening committed positions improves recovery in both failure modes.

Fan Zhou, Weitian Wang, Tim Van de Cruys

KU Leuven, Belgium · Ruhr University Bochum, Germany

Classifier-Free Guidance Masked Diffusion Language Models Diffusion Language Models Guidance Commitment

Aug 7, 2026eess.IV

Structural Guidance for Unified Joint Demosaicing and Denoising

Joint demosaicing and denoising is a fundamental step in camera image signal processing, yet remains challenging because different Bayer-like color filter arrays (CFAs) and sensor noise jointly corrupt both color sampling and image content. Existing unified restoration networks explicitly model CFA geometry but are still driven primarily by pixel-level supervision, making them prone to structural degradation around edges, repetitive textures, and moiré patterns where local evidence is unreliable. We attribute this limitation partly to the absence of explicit structural guidance beyond pixel-level reconstruction supervision. Motivated by this observation, we propose a structural-guided unified restoration framework that injects pretrained structural knowledge into CFA-aware image restoration. Our model receives a unified five-channel observation consisting of the raw mosaic, CFA masks, and a noise-level map. A SwinIR restoration branch reconstructs pixel details under CFA-conditioned modulation, while a parallel structural reasoning branch extracts complementary structural cues from a sparse pseudo-RGB observation. To bridge the substantial domain gap between sparse noisy sensor data and the natural-image pretraining domain of the structural encoder, we introduce a lightweight trainable adapter before residually fusing structural and restoration features. A shared decoder jointly predicts the restored RGB image and an auxiliary clean mosaic, providing supervision in both image and sensor domains. Extensive experiments across multiple CFA patterns and noise levels demonstrate consistent improvements over state-of-the-art unified and CFA-specific methods, indicating that adapted structural priors can enhance robust camera image restoration. The source codes and dataset are provided in the supplementary material.

Qixin Zheng, Ping Chen, Qiangqiang Shen +1

Harbin Institute of Technology (Shenzhen), Shenzhen, China

Image Restoration Restoration Graph Signal Processing Guidance

Aug 6, 2026cs.CV

Toward surface-based registration of a virtual preoperative cutting guide onto the mandible for reconstruction surgery

Mandibular reconstruction restores facial continuity and oral function after segmental resection. Patient-specific cutting guides transfer a computed tomography (CT)-based plan to the operating room with three-dimensional information, but printed guides add cost and lead time, cannot adapt after fabrication, and may interrupt surgery if sterility is lost. We investigate a markerless augmented reality (AR) alternative that registers a virtual cutting guide to the exposed mandible from surface geometry. The method extends surface-based registration for the transoral setting, where teeth form the most distinctive visible surface. After camera calibration, a HoloLens 2 time-of-flight camera captures a partial intraoperative point cloud. The user supplies a rough head-based alignment only to crop the region of interest. A teeth-weighted global stage computes correspondences and solves a truncated least-squares rigid alignment. An asymmetric point-to-plane iterative closest point (ICP) stage refines the complete CT mandible against the partial depth cloud target. The guide-to-mandible transform places the guide in the HoloLens world frame, while pose updates and interpolation follow target motion. We define a blinded phantom protocol with 30 target registration error (TRE) points under full, intermediate, and teeth-only exposure, plus a motion-to-display latency test. Our median TRE is 4.05, 6.10, and 7.10 mm respectively, and median latency is 0.805 s. These values support the feasibility of using AR to replace physical prints. The workflow removes mounted fiducials and manual landmark selection and provides a testable path toward transoral cutting guidance.

Yue Yang, Jie Ying Wu

Vanderbilt University, Department of Computer Science, 1400 18th Avenue South, Suite A4004 Nashville, TN 37212, USA.

Augmented Reality Image Registration Occlusal Constraint Surgical Robots Point Clouds Guidance

Aug 5, 2026cs.AI

When Privileged Guidance Misaligns: State-Matched Routing and Contextualized Self-Distillation for Multi-Turn Agents

Privileged on-policy distillation provides dense supervision for multi-turn agents by allowing a synchronized teacher to re-score the student's response at every turn with access to training-only references, such as successful trajectories. In interactive environments, however, the student's preceding actions continually change the execution state. As the student takes different actions or completes subgoals in a different order, its rollout may reach states not covered by the reference, making the reference an unreliable source of guidance for the state actually reached. Applying privileged distillation indiscriminately therefore creates state--reference mismatch. This mismatch motivates a central objective: providing privileged reference guidance that remains compatible with the student's current execution state. We introduce State-Matched Routing and Contextualized Self-Distillation (SMRC-SD), which explicitly determines when and how a privileged trajectory should guide an on-policy student. At each turn, SMRC-SD verifies whether the student's current execution state matches a supported state along the reference trajectory. Distillation is applied only at matched states, filtering out turns for which the reference lacks locally compatible guidance. For each matched state, SMRC-SD further constructs state-conditioned teacher context from the successful trajectory, grounding supervision in the state actually reached. Across ALFWorld and WebShop, SMRC-SD consistently outperforms unconditional successful full-path distillation. With Qwen3-1.7B, it improves task success from

0.746

to

0.865

on ALFWorld and from

0.574

to

0.693

on WebShop. Controlled routing and context ablations support both selecting locally supported turns and constructing state-compatible teacher context as contributors to these gains. Code is available at https://github.com/liujunzhuo/SMRC-SD.

Junzhuo Liu, Weiwei Li, Jun Ling +1

University of Electronic Science and Technology of China

Self-Teacher Self-Distillation Framework Guidance Single Trajectory

Aug 4, 2026cs.AI

Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve

Chain-of-Thought (CoT) prompting remains the standard baseline for evaluating models' reasoning abilities. Originally, this technique was introduced to elicit step-by-step reasoning from large language models (LLMs), which would otherwise tend to directly output the final answer. However, many modern LLMs produce CoT-style responses \textit{natively} when presented with reasoning tasks, which made us revisit the effectiveness of standard CoT prompting. We evaluate several modern mid-sized language models on a math problem-solving task and find that models specialized for reasoning achieve better performance in a simple zero-shot setting than when using few-shot CoT examples - significantly surpassing officially reported results at no additional cost (e.g., from

\sim

77% to

\sim

84% for Mathstral on GSM8K). For the tested general-purpose model, a zero-shot CoT prompt is also sufficient to outperform a few-shot CoT baseline. We attribute this to a `guidance-distraction' tradeoff: standard CoT prompting also demands style adaptation, formatting compliance, and potentially undesired contextualization, which can distract models from the core reasoning task. Our findings suggest that using standard CoT prompting increasingly acts as a source of distraction as models grow stronger.

Denys Pushkin, Albert Q. Jiang, Aryo Lotfi +2

EPFL · Apple · Mistral AI

Chain-of-Thought Reasoning Instruction-Tuned Models Reasoning Skills Short Guidance

Aug 4, 2026cs.AI

Towards Robust Tool Use in Agents via Experience-Driven Adaptive Guidance

The performance bottleneck of agents is increasingly shifting from model capability to the robustness of their execution processes. Tools play a central role as the primary interface through which agents interact with external environments, yet existing methods rarely focus on ensuring robust tool use across diverse runtime conditions. To address this problem, we propose ExpG, a mechanism that builds and refines adaptive guidance capturing each tool's capability boundaries and best practices, thereby enabling agents to use tools more robustly and effectively. ExpG consists of three phases: (1) experience acquisition, which analyzes tool invocation quality from historical execution trajectories, producing structured learnable experiences through multi-aspect attribution; (2) experience distillation, which keeps the experience pool effective by filtering unhelpful experiences, selecting representative ones with an equivalence-class-based method, and summarizing them into generalizable guidance; and (3) experience reuse, which applies the guidance adaptively during future task solving. Extensive experiments show that ExpG brings consistent improvements across the tool selection, tool calling, and response generation tasks, enabling smaller agents to outperform larger ones that do not use ExpG. Moreover, ExpG achieves particularly strong gains in challenging settings, suggesting a promising path toward more robust tool use. Our code, experiments, and results are available.

Can Wang, Haoran Chen, Li Yu +4

1Shandong Key Laboratory of Digital Service Computing Technology and Systems · 2Alibaba Token Hub · Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University

Controlling Tool Use Tool Invocation Guidance

Aug 4, 2026cs.RO

Passively Safe Convex Guidance for Cislunar Rendezvous and Proximity Operations

This paper presents purely convex programs for passively safe impulsive rendezvous and proximity operations in cislunar orbits. Approach, arrival, and abort maneuvers are all designed and validated in the context of maneuver execution error and navigation uncertainty, and formulated for efficient onboard execution in the autonomous scenario. The outlined methods form the baseline onboard guidance routines for NASA's CAPSTONE 02 mission planned to demonstrate autonomous rendezvous and proximity operations capabilities in the southern 9:2 synodic near rectilinear halo orbit. High fidelity closed loop Monte Carlo simulations using the planned relative navigation sensor suite and measurement cadence verify the intended maneuver design performance.

Ian M. Down, Connor Plaks, Matthew Bolliger +1

Astrodynamics Engineer, Advanced Space, LLC, 1400 W 122nd Ave, Suite 200, Westminster, CO 80234 · Navigation Engineer, Advanced Space, LLC, 1400 W 122nd Ave, Suite 200, Westminster, CO 80234 · Senior Astrodynamics Engineer, Advanced Space, LLC, 1400 W 122nd Ave, Suite 200, Westminster, CO 80234 +1

Intent-Aligned Autonomous Spacecraft Guidance Advanced Jet Trainer Proximity Operations Geometric Guidance Guidance

Aug 4, 2026cs.CV

RIDGE: Re-Noising with Internal Dynamic Guidance for Image Editing

Inversion-free flow-based image editing avoids latent inversion, but still requires a target-side state at every editing step. The widely used equal-displacement construction keeps the displacement between the noisy source state and the target-side state unchanged across noise levels. This is inconsistent with noising, under which the displacement between two clean states noised with the same noise level and noise sample should contract as the noise level increases. Thus, it can lead to overly aggressive updates at high noise levels. We introduce RIDGE: Re-Noising with Internal Dynamic Guidance for Image Editing, an inversion-free and training-free method that maintains the edited state as an evolving approximation to the unavailable clean target state. RIDGE re-noises this approximation using the same noise level and noise sample as the clean source state, allowing their noisy displacement to decrease naturally with increasing noise. Since the edited state initially contains limited target semantics, RIDGE further applies internal dynamic guidance during the early high-noise steps. A clean target state prediction guides the provisional edited state through a soft dynamic mask derived internally from the model, focusing guidance on regions that require modification without external segmentation or detection models. Experiments on two benchmarks using two backbones, SD3 Medium and FLUX.1-dev, show that RIDGE offers a favorable aggregate trade-off among source preservation, target alignment, and perceptual quality.

Ruiliang Gong, Zhen Wang, Yanghao Wang +1

Department of Computer Science and Engineering The Hong Kong University of Science and Technology

Diffusion-Based Image Editing Image Editing Guidance Noisy Data Ridge Value Alignment

Aug 3, 2026cs.AI

Is More Privileged Information Better? From Solution Traces to Problem-Solving Structure in Self-Distilled Reasoning

On-policy self-distillation (OPSD) improves reasoning by using a privileged view of a model conditioned on reference solutions to supervise a student view that observes only the question. However, the teacher-provided token-level targets may depend on reference-specific information unavailable at inference time. We propose Problem-Space-Guided OPSD (PS-OPSD), which replaces the complete solution with trajectory-grounded guidance describing the initial state, goal conditions, constraints, and a selected state-transition path. The student rollout and OPSD objective remain unchanged. Across three mathematical reasoning benchmarks and model scales ranging from 1.7B to 8B, PS-OPSD achieves the highest aggregate question-only accuracy among the compared methods. Controlled experiments further indicate that guidance relevance and path coherence contribute to these gains, highlighting the representation of privileged information as an important design choice in OPSD.

Xuyang Zhao, Liting Zhang, Zichen Xu +4

1TMCC, College of Computer Science, Nankai University, Tianjin, China · 2Huawei Technologies Ltd., Beijing, China

Mathematical Reasoning Benchmarks Privileged Context Problem Solving Capability Guidance Traces

Aug 1, 2026cs.CV

GuideGround: VLM-guided Semantic Understanding and Viewpoint-aware Reasoning for 3D Visual Grounding

3D visual grounding aims to localize the target object in a 3D scene from a natural language query, requiring both fine-grained semantic understanding and viewpoint-dependent spatial reasoning. Existing methods typically formulate semantic understanding as an auxiliary closed-set object classification task and rely on multi-view feature aggregation for viewpoint reasoning, limiting semantic generalization and weakening viewpoint-specific evidence. We observe that vision-language models naturally provide complementary capabilities through open-vocabulary semantic understanding and global scene perception. Based on this insight, we propose GuideGround, a VLM-guided framework that complements rather than replaces task-specific grounding models by leveraging VLMs for semantic enhancement and viewpoint-specific hypothesis verification. Specifically, we replace auxiliary closed-set object classification with VLM-generated object semantic descriptions to enhance semantic understanding. Meanwhile, instead of directly aggregating multi-view representations, we preserve viewpoint-specific grounding hypotheses through per-view grounding and explicitly verify them using VLMs across candidate viewpoints. Extensive experiments on the ReferIt3D benchmark demonstrate that GuideGround consistently outperforms previous state-of-the-art methods. Comprehensive ablation studies further confirm the effectiveness of both the proposed semantic understanding and viewpoint reasoning strategies.

Yiwen Wang, Yuyang Deng, Yihao Long +1

Xi’an Jiaotong University

3D Visual Grounding Grounding Spatial Reasoning Guidance

Jul 30, 2026math.DG

A user's guide to PINNs in geometric analysis: lessons from the asymptotic Plateau problem

This proceedings contribution elaborates on the findings of arXiv:2605.26234v2: a joint work with Marco Usula, where we introduced a machine learning framework based on physics-informed neural networks (PINNs), aimed at constructing near-minimal discs in hyperbolic space asymptotic to a prescribed knot at infinity. We used this method to provide numerical evidence for a conjecture of Joel Fine relating minimal surfaces in

H^{4}

to the coefficients of the HOMFLY polynomial. This is a methodological companion to that paper, based on a presentation given at the 2026 edition of the workshop "DANGER: Data, Numbers, and Geometry". Rather than reviewing the results, which are presented extensively in the preprint above, we discuss the two aspects of the framework which, in our experience, determined whether the method worked at all. First, the geometry of the problem must be encoded in the architecture of the model, so that the boundary condition and asymptotics at infinity hold exactly for every value of the learnable parameters - leaving us with a single-component loss function; second, the evaluation of the PDE residual must be engineered with care to ensure that complete trainings can be performed in a reasonable time. On the latter point, we describe two implementation techniques which are not spelled out in detail in the original paper: replacing nested reverse-mode automatic differentiation with the forward propagation of second-order jets, and compiling the computational graph of the residual once instead of rebuilding it at every optimisation step. Together, on identical hardware, these two changes reduce the cost of a training step by a factor of roughly forty to fifty. We hope these methodological discussions can be useful for researchers in differential geometry and geometric analysis who wish to deploy PINNs on problems of their own.

Tancredi Schettini Gherardini

University of Bonn and Max Planck Institute for Mathematics, Bonn, Germany.

Parametric Physics-Informed Neural Network Polynomials Finite Time Analysis Guidance

Jul 29, 2026cs.LG

Q-Steer: Action-Value Guidance for Molecular Policy Optimization

Oracle-limited molecular optimization gives reward only after a complete molecule is generated, while each rollout requires many local next-token decisions. This delayed-feedback interface makes molecular policy optimization myopic: an optimizer can learn that a molecule was good without knowing which intermediate actions made it good. We introduce Q-Steer, a rollout-time action-value steering primitive for molecular language models. Q-Steer uses an offline-trained and frozen prefix-action value scorer, PAVS-Q, that estimates the downstream reward of taking a candidate next token under a partial SMILES prefix, then adds a normalized value bonus to sampling logits. The optimizer update rule and online oracle budget are unchanged; the claim is fixed-online-oracle performance, not equal total compute. On PMO23 with a fixed 10,000-call online budget, complete factorial studies across two molecular language-model backbones and four optimizers show that Q-Steer improves mean valid-unique score in all eight backbone-optimizer cells, with positive macro mean-score gains between +0.033 and +0.049 and 18-20 task wins per cell. Mechanism controls show that action identity matters: prefix-broadcast values are nearly neutral, while shuffled action values harm performance. These results support Q-Steer as a reusable rollout-time action-value wrapper that improves average molecular optimization reward across optimizer families and policy backbones without changing the online oracle budget.

Xinyu Wang, Jinbo Bi, Minghu Song

Department of Computer Science and Engineering, University of Connecticut · 1Storrs, CT 06269, USA · Institute of Health and Medicine, Hefei Comprehensive National Science Center +1

Molecular Optimization Frictive Policy Optimization Autoregressive Rollout Steering Guidance

Jul 27, 2026cs.RO

Learning Adaptive Multi-Task Guidance, Navigation, and Control via Hypernetworks

Autonomous free-flying robots in orbital environments require controllers that are both versatile and resource-efficient, yet maintaining a separate, task-specific policy for each mission profile is architecturally brittle and limits operational flexibility as requirements evolve. We introduce HYPER-GNC, a multi-task reinforcement learning framework in which a hypernetwork maps physics-informed task embeddings to the weights of a shared actor-critic policy, enabling a single compact controller to master four distinct GNC tasks: velocity tracking, docking, inspection, and navigation with obstacle avoidance. The continuous embedding space allows the controller to generalize to novel mission configurations at deployment time without any retraining. Extensive experiments demonstrate that HYPER-GNC achieves sample efficiency comparable to single-task specialists while maintaining stability under significant inertial perturbations and external body wrenches. We further validate the framework on a physical satellite emulator, successfully bridging the simulation-to-reality gap across all mission profiles. Code, trained models, and deployment scripts are made publicly available to support reproducibility.

Ricard Marsal I Castan, Aman Arora, Antoine Richard +3

University of Luxembourg · 2Georgia Institute of Technology

Quadrotor Robust Trajectory Aerial Robots Multi-Turn Reinforcement Learning Hypernetwork Navigation+3

Jul 26, 2026cs.LO

An Unofficial FastLAS Tutorial: A Programmer's Guide

FastLAS is a scalable system for Inductive Logic Programming (ILP): you give it some background knowledge, a language bias, and a set of examples, and it searches for a set of logic program rules (a hypothesis) that explains the examples. These notes are a hands-on introduction to writing FastLAS programs. They are organised as a programmer's guide: syntax first, then a ladder of worked, numbered examples of increasing difficulty. Every self-contained example here has been run against FastLAS 2.2.0 and shows the tool's actual output. We keep theory to the minimum needed to write correct programs; throughout, set-off notes flag where FastLAS differs from its sibling system ILASP, and where the two learning algorithms (--opl and --nopl) behave differently. The document is intended as an unofficial tutorial to FastLAS 2.2.0, not as an official language specification.

Fabio Aurelio D'Asaro

University of Verona, Italy · University College London, United Kingdom

Induction Logit Lens Guidance

Jul 26, 2026cs.CV

Multi-Modal Object Re-Identification with Prompt-S6 and Semantic-Aware Knowledge Guidance

Multi-modal object Re-Identification (ReID) aims to retrieve specific objects by integrating complementary information from multiple modalities. However, existing multi-modal ReID methods do not effectively address background interference suppression or achieve tri-modal alignment, instead focusing on pairwise feature fusion. Moreover, many current aggregation approaches suffer from high computational complexity. To address these limitations, we propose PRISM, a novel multi-modal ReID framework built upon Prompt-S6 (PS6) and semantic-aware knowledge guidance. PS6 maintains the linear complexity and strong sequence modeling capability of Mamba while enabling efficient cross-modal interaction. Leveraging these advantages, we design two key components: Semantic-Driven Token Pruning (SDTP) and Progressive Fusion Network (PFN). Parsing semantic priors from the segmentation foundation models, the SDTP then leverages these priors and applies dynamic token pruning to suppress background noise and refine feature representations. The PFN progressively aggregates multi-modal features to achieve tri-modal alignment and fully exploit modality complementarity. With the proposed modules, PRISM generates more robust multi-modal representations under complex scenarios. Extensive experiments on four multi-modal object ReID benchmarks demonstrate the effectiveness and efficiency of our approach. The source code is available at https://github.com/zw-absin/PRISM.

Weixiang Zhou, Jiabei Zuo, Yuhao Wang +3

School of Mathematical Sciences and the Key Laboratory for Computational Mathematics and Data Intelligence of Liaoning Province, Dalian University of Technology, Dalian, 116024, China · School of Computer Science and Technology, Dalian University of Technology, Dalian, 116024, China · School of Future Technology, School of Artificial Intelligence, Dalian University of Technology, Dalian, 116024, China +1

Re-Identification Prism Prior Knowledge Integration Guidance