Planner Agent

Urban environments are shaped by design choices with long-term implications for health, safety, and quality of life, yet evaluating proposed interventions remains costly, time-consuming, and often impractical. Existing geospatial vision methods largely focus on monitoring urban indicators from aerial and street-view imagery, rather than proposing interventions and estimating their effects on such indicators. Moving beyond recognition, we introduce the problem of discovering interventions that improve target indicators for a given aerial or street-view image. We argue that a black-box indicator model, combined with a generative editing model, can serve as an implicit digital twin for testing intervention hypotheses. We present VIDA-Geo , a multi-agent system that explores this intervention space by coordinating segmentation, diffusion-based inpainting, and indicator scoring models to produce interventions that are both perceptually realistic and aligned with real-world policies. We evaluate our system on 8 indicators across aerial and street-view imagery, measuring changes in factors such as perceived safety and greenery. Our approach outperforms existing baselines in many cases, achieving up to 2X higher perceptual quality and policy alignment scores. Finally, our model provides users with multiple candidate interventions, supporting an expert city-planner-in-the-loop workflow.

Streaming video generators allow users to dynamically modulate video synthesis via mid-stream prompt switching. Existing streaming methods can respond to the updated instruction while still cutting corners, prematurely realizing goals or taking heuristic shortcuts that bypass necessary intermediate state changes needed for a plausible transition. In this study, we present SEGUE, a novel framework that makes this process explicit and trains the generator to execute these transitions faithfully. At each switch, a training-free planner parses the latest frame and prompts, writes a few segue prompts with roles and durations, and then hands control back to the user's prompt. Furthermore, to address the inherent difficulty of training causal models on short-lived temporal schedules without corrupting preparatory supervision, we introduce SPANDMD, which evaluates each active prompt using the full rollout as temporal context while retaining its DMD residual only within the prompt's assigned span. On OpenTrans-360, a benchmark of 1,800 switches that scores how the old state exits and the new one begins, SEGUE ranks first on all eight transition metrics and raises the overall score over the strongest baseline from 0.866 to 0.887. It also ranks first on four of six instruction-response metrics of StreamAV-Bench, while the planner transfers to frozen autoregressive generators without retraining.

The rapid progression of large language models is extending AI from passive content generation into the active workflows of engineering and scientific discovery. This shift raises a compelling question: can AI be both the object of development and an active participant in building next-generation AI systems? We explore this question by building Qwen-Planner-Agent within a closed-loop AI-for-AI framework for scalable development and iterative improvement. Mobile planning offers a demanding test of this approach: complex, long-horizon tasks challenge agent reliability, while costly real-device interaction limits development scalability. The framework connects data production, model training, and deployment through a shared action-feedback-verification contract. (i) AI for Data builds a human-gated agentic data flywheel in which specialized agents construct tasks, collect interaction trajectories, curate and balance training data, and use training feedback to guide subsequent data generation. (ii) AI for Training combines a supervised planning cold start with hybrid-environment online agentic reinforcement learning, where we introduce Competence-Aware Reward-and-Advantage Engineering (CARE) to reduce reasoning and tool-use costs while preserving task performance. (iii) AI drives model--harness co-evolution through an execution-evidence-driven loop that orchestrates memory, skills, and tools at runtime and feeds structured action feedback and preserved failure traces back into coordinated model and harness adaptation. Qwen-Planner-Agent achieves the best overall performance among all evaluated models and systems on MobilePA-Bench, improving over its base model across tool use, memory, skills, and sub-agent coordination. Further evaluations of our model show improvements across non-mobile agentic benchmarks while largely preserving general capabilities.

We present S2Planner, a trajectory planner that combines three front-facing cameras with ego-motion history and the current driving command. A fine-tuned DINOv3 backbone and a Spatial Tuning Adapter produce multi-scale image features; a coarse-to-fine decoder then uses trajectory self-attention and camera-projected cross-attention to refine candidate waypoints. The contribution is the integration of ego-conditioned trajectory initialization with iterative, geometry-guided sampling of multi-scale image features, rather than a new visual backbone or attention operator. On the NAVSIM v1 non-reactive evaluation, the previously reported navtest run obtained 88.03 PDMS. Because that run was selected using navtest performance, this number is exploratory and cannot be interpreted as an unbiased test estimate. Validation-selected evaluation on unexposed data, repeated runs, and computational measurements are needed to establish generalization and efficiency.

Large language models can decompose mobile-manipulation goals into long action sequences, but the resulting plans remain reliable only while their world context is current. A fixed scene description becomes stale when objects are discovered, moved, or completed while retaining every observation instead produces a growing history with redundant and conflicting state. To resolve this tension, we present an LLM-guided planning framework ADM-Planner with attention-enhanced dynamic memory (ADM). Persistent workspace knowledge is separated from object-centric state, asynchronous observations and action outcomes update that state, and a bounded retriever exposes only the entries that can affect the next decision. The LLM replans when an update invalidates the remaining plan. Across 1,500 task-simulator episodes, the proposed ADM achieved 100% full-task success in the 14-container noisy dynamic setting, compared with 62% for static memory and 97% for unfiltered dynamic memory, while reducing the context-size proxy by 95.8% relative to the latter. In a six-episode live GPT-5 Mini planner, both dynamic memory variants completed every mission, while ADM reduced provider-reported input tokens by 14.4% and mean planner calls from 7.0 to 6.0. A separate 60-trial PyBullet study retained 100% success for ADM, compared with 50% for static memory. Finally, the mobile manipulator with ADM-Planner completed various missions in indoor and outdoor physical experiments while incorporating targets revealed after execution began. The results show that selective state maintenance with ADM, rather than prompt history alone, is a practical basis for long-horizon planning in changing environments. Project page: https://xjp99v5.github.io/ADM-Planner

Navigation world models plan by foresight, predicting the future that each candidate action sequence produces and selecting the best, rather than mapping observations to actions directly. Unlike urban settings where a predicted scene is a sufficient proxy, off-road navigation hinges on the robot--terrain interaction, so the prediction must cover not only what the camera will see but what the robot will feel. However, existing scene-focused models do not predict how much the robot will slip, tilt or shake along a planned trajectory. Proprioception captures these dynamics directly and, when used as input, improves the prediction of the physical future. We present Feel-WM, the first off-road navigation world model that conditions on proprioception and predicts what the robot will feel alongside what the camera will see. The physical future takes the form of a future proprioceptive state and a failure risk, both learned from the robot's own experience without human labels. The planner rolls out the physical future alongside the scene and weighs the predicted failure risk against goal similarity in a separable score. Experiments on real off-road data and in simulation demonstrate that Feel-WM outperforms visual-only navigation world models in open-loop planning and closed-loop rough-terrain navigation across wheeled and legged platforms. Deployed on a Husky on mountain trails, Feel-WM plans onboard, predicts rough ground ahead and steers around it, completing courses that an end-to-end policy fails.

Work zones alter lane geometry through temporary traffic controls and closures that may be absent from on-board maps, challenging autonomous vehicle (AV) perception and planning. Generalization is also limited by scarce public datasets with structured geometric supervision. We present WorkZonePlan, a dataset comprising 149K+ synthetic and 5K+ real-world multimodal samples with 3D annotations for lane boundaries, work zone boundaries, and driving trajectory options. It also provides 76 closed-loop CARLA scenarios replayed under three weather conditions, yielding 228 Bench2Drive-format evaluation routes. We introduce WAVE (Work-zone-focused AV data generation in Virtual and rEal Environments), a semi-automated pipeline for creating the dataset, and BoundaryFormer (BF), a transformer-based model that jointly predicts lane and work zone boundary polynomials and driving trajectories. BF uses slot attention for boundary prediction. Ablations show that a separate trajectory decoder using boundary slot features substantially improves trajectory prediction over a slot-attention-only approach. Building on this finding, BF++ offers Camera and Camera+LiDAR variants with metric ground-plane encoding, typed boundary/trajectory queries, long-range point anchors, image-space curve refinement, and conservative gated LiDAR fusion. On the 211 routes common to all four models at the evaluation freeze, BF++-Camera and BF++-Camera+LiDAR achieve Driving Scores of 63.0 and 64.4, respectively, compared with 59.3 for SimLingo and 26.1 for TransFuser++ (TF++). BF++ is 40 times smaller than SimLingo and more than 10 times smaller than TF++, while achieving higher Driving Scores. These results support jointly predicting lane boundaries, work zone boundaries, and driving trajectories as a promising direction toward safer AV operation in work zones. Code and dataset: https://github.com/Nishad-Sahu/WZPlanner.

Robotic additive manufacturing (AM) extends material-extrusion printing beyond gantry kinematics but makes process planning robot-dependent. A slicer-generated plan that appears favorable in part coordinates can become infeasible or robotically unfavorable on a manipulator because slicer-process decisions and part orientation determine the generated path, while part orientation and workspace placement affect its kinematic realization. Existing AM tools, large language model (LLM)-based decision-support methods, and digital-shadow systems do not provide integrated pre-execution evaluation of these coupled decisions. This paper presents agentic robotic additive manufacturing (A-RAM), an agent-specialist-tool framework that converts user intent and a part file into traceable, execution-ready plans. The LLM interprets manufacturing objectives and constraints, identifies prescribed and searchable planning variables, and encodes this reasoning in a schema-constrained request; a deterministic Planning Agent instantiates the corresponding search workflow, while domain tools compute quantitative evidence for slicing, placement, inverse kinematics, trajectory timing, Joint-6 jerk, and extrusion. The framework is evaluated on a six-axis robotic-arm AM cell through three case studies covering expert-specified planning, goal-only planning, objective-dependent infill screening, and geometry-dependent orientation-placement selection. Across the evaluated candidate sets, selected plans achieve up to 53.5% lower maximum Joint-6 jerk and 48.3% lower mean absolute Joint-6 jerk than the least favorable valid candidates, while objective-specific infill screening yields motion-plan completion times up to 40.1% shorter and extrusion paths up to 12.7% shorter than the corresponding least favorable screened patterns.

Recent advancements in large language models have significantly enhanced the capabilities of agents in modeling long-term conversations. Despite these successes, existing approaches typically adopt a static heuristic paradigm, where information is passively archived without adaptive memory valuation. Consequently, these methods fail to self-evolve or align their memory management with evolving user needs. To address this, we propose ICML (InteraCtive Memory Learning), a multi-agent framework that transforms the memory mechanism from a passive archive into a learnable, interactive memory policy. Specifically, we first employ a session synthesis pipeline to generate expert data, facilitating rapid test-time adaptation in unseen scenarios. Building on this, ICML utilizes an online reinforcement learning mechanism where a Planner agent selectively encodes high-value information and a Trigger agent dynamically retrieves it to optimize response quality, whereby the two agents co-evolve through continuous interaction feedback. Crucially, both agents are synchronized through a delayed reward mechanism that propagates future feedback back to earlier storage decisions, ensuring memory policies are precisely aligned with user expectations. Experimental results demonstrate that ICML significantly outperforms strong baselines, exhibiting the unique capability to continuously improve response quality as interactions accumulate.

Ensuring the safety of autonomous driving is a critical challenge. Scenario-based testing is a systematic process used to validate Autonomous Driving Systems (ADSs), but it remains a fragmented modular pipeline in which scenario generation, retrieval, modification, ADS execution, and results analysis are performed by separate tools with little interaction. Large Language Model (LLM) agents have shown promise across ADS sub-systems such as perception, planning, and control. However, no prior work covers the whole scenario-based testing pipeline for ADSs with a unified LLM-agent framework. We present PlannerForge, an LLM-agent framework that extends all scenario-based testing stages (from Scenario Generation to ADS Assessment) and adds two further LLM-enhanced stages: ADS Enhancement and ADS Benchmarking. We evaluate PlannerForge with 10 off-the-shelf LLMs across all tasks (Generation, Selection, Modification, Module Routing, Planner Testing, and Enhancement) under 5 prompt conditions. Best-per-task scores range from 0.88 to 1.00, and open-source 20-35B backends match commercial APIs on most tasks. Open-source models such as Qwen3.6:35B match commercial APIs on three of the five tasks. Chaining the modules end-to-end retains 83% / 78% of seed queries (commercial / open). It outperforms Scenario Factory 2.0 (Finkeldei et al., 2025) on natural-language generation (193 vs. 144 executable of 200) and realises 92-96% of requested city, road and vehicle attributes. It outperforms BM25 (Robertson and Zaragoza, 2009) at rank 1 selection (92.0% vs. 67.5%) and From-Words-to-Collisions (Gao et al., 2025) on physically valid edits (>=94% vs. 31%). At N=400, cost-tuning lifts planner success from 50.4% to 70.2% and cuts collisions from 19.0% to 8.4%, without domain-specific fine-tuning.

A model that inherits one-line memories may pull one archived source record before acting; a directive in the store can steer that pull: a pointer, a criterion or both. Across sixteen registered studies (179,352 attempts) we measured where the request goes under each form; every result is descriptive, with registered intervals, no mechanism claim. A length-matched criterion exceeded a bare id on six direct-provider models (D) and failed its registered superiority rule on a nine-model OpenRouter panel (E). On generated worlds (K2-K5): the two registered signatures held on Opus 5 and Fable 5.1, Fable 5 followed the same sign, Haiku 4.5 reversed, and Sonnet 5, the GPT-5.6 endpoints and GPT-6 Astra lay near zero (K2). With a defensive adapter at five gains, the 70B rule for a gain-dependent change of the composite - criterion contrast was not met (K3 and K4); under the 8B attenuation rule (0.95 intervals: slope below zero; change beyond the margin), the 8B change of -17.5 [-26.7, -8.1] did not meet it on 36 families (K4) and at registered power on 337 families -16.6 [-19.4, -13.8] did (realised one-sided error at the margin 1.8 to 3.2% per corner of a finite grid, nominal 2.5%, not a uniform-error guarantee; K4's status stands; K5, first ladder), while a second SecAlign++ adapter under the imposed Meta-SecAlign template did not (-11.8 [-14.3, -9.3]; K5, second ladder); no NOT-MET is a statement that the contrast was unchanged; their difference (+4.7 [+2.3, +7.2]) describes two fixed execution paths, licenses no superiority, equivalence or 'significant difference' claim; nothing follows from the statuses differing (K5). Intervals describe family-reweighting stability conditional on the execution, not reproducibility across engine executions; audit replays were neither substituted for nor averaged into outcomes; no missingness gate fired and directional completions changed no status.

PixelGoal navigation specifies targets directly in the agent's camera view, providing a natural interface between high-level visual reasoning and low-level navigation. Depth can lift a visible target pixel into a metric PointGoal, but this estimate becomes unreliable under occlusion or sensor noise. Moreover, a PointGoal alone does not encode traversability or feasible paths around obstacles. We present OccPlanner, a goal-aware occupancy-conditioned diffusion planner that learns complementary egocentric goal and planning-oriented 3D representations through metric target and occupancy prediction, respectively. These representations condition a diffusion trajectory module to generate target-directed, obstacle-aware trajectories. For scalable geometric supervision, we introduce L3ROcc, which converts monocular RGB navigation videos into aligned 3D occupancy and trajectory annotations. We train OccPlanner on L3ROcc-processed InternData-N1 and evaluate it in closed-loop simulation across four unseen InternScenes categories and two goal-distance ranges. Across all eight settings, OccPlanner substantially outperforms existing open-source PixelGoal approaches and achieves competitive performance against PointGoal planners with direct metric-goal inputs.

The rapid growth of LLM inference is shifting sustainability concerns from one-time training to continuous serving, where infrastructure decisions shape energy use, carbon emissions, water consumption, and service quality. Yet operators often need to compare deployment alternatives before large-scale infrastructure is built, making direct measurement costly, slow, and sometimes infeasible. We present InFactPlanner, a trace-driven decision-support framework for what-if analysis of sustainable AI data center deployment for LLM inference across single and geo-distributed sites. InFactPlanner combines query traces, hardware-model profiles, candidate site configurations, PUE/WUE parameters, renewable generation models, and time-varying grid carbon intensity to estimate power, energy, carbon emissions, water use, latency, and server utilization. The framework abstracts low-level serving effects into configurable hardware-model profiles, enabling rapid comparison of site selection, capacity placement, hardware, model, renewable integration, and routing choices. We validate the energy accounting pipeline by reproducing reference LLM inference energy estimates with less than 10% deviation, evaluate scalability across multiple data centers and server counts, and demonstrate scenario-driven decision analyses for hardware selection, renewable placement, geographic deployment, and carbon-aware routing. Our results show that sustainability-optimal choices can differ from latency-optimal ones, and that the carbon value of deployment depends strongly on the local grid mix.

This paper presents a real-time Plan-and-Avoid (PAA framework for coordinating cooperative multi-agent airspace operations around a declared priority trajectory. The priority trajectory represents an aircraft flight plan that must be preserved because of constrained maneuverability, an emergency, a mission-critical task, or assigned operational priority. The framework predicts uncertainty-aware, well-clear separation violations with surrounding traffic and, when the priority plan alone cannot maintain separation, generates vehicle-constrained unilateral advisories that modify nearby aircraft trajectories to maintain well-clear separation for all traffic. The approach is applicable to any declared priority trajectory. This paper demonstrates the Plan component using a contingency landing planner to generate candidate priority trajectories. PAA then identifies nearby aircraft passing too close to this priority trajectory and issues Avoid resolution advisories to these aircraft. The framework is tested using real-world Automatic Dependent Surveillance-Broadcast (ADS-B) traffic from the Washington, D.C., airspace across more than 900 forced-landing cases, totaling over 140 hours of simulated flight. The PAA framework generates feasible cooperative advisories for all 575 unique conflict encounters, with a worst-case end-to-end response time of 5.7 s on a personal computer, including priority trajectory planning, advisory generation, and 1 s two-way datalink delay. In total, 93.5% of generated advisories satisfy the 35 s RTCA DO-365 Detect-and-Avoid temporal threshold. These results demonstrate low-latency coordination for preserving priority trajectories while maintaining well-clear separation through real-time automated advisory generation. Future work will quantify advisory-induced delays and their operational impacts.

We present GASP, a GPU-Accelerated Safe Planner for real-time, collision-aware joint-space motion generation in known environments. GASP combines a clamped B-spline trajectory parameterization with a convolutional residual neural network that predicts the free interior control points, while analytically inserted boundary control points enforce initial and final derivative constraints for collision-aware planning under non-stationary conditions. A conditional variational autoencoder samples multiple trajectory candidates, which are decoded and validated in parallel on the GPU, yielding a batched planner for collision-aware coupled joint-space motion with near-millisecond inference. We validate GASP as an online motion-generation module, where it achieves analytical-level success rates with high collision-aware feasibility and substantially reduces inference time relative to GPU-based trajectory optimization. We further deploy GASP as a reinforcement-learning reset planner in competitive robotic table tennis, matching the baseline return rate while roughly halving training-time collisions.

Integrating heterogeneous industrial knowledge, including factual relations and decision constraints, remains a core challenge in industrial information systems. Machining process planning exemplifies this problem because engineers must select operations by combining material properties, feature characteristics, and quality requirements. Existing methods rely mainly on similarity retrieval or classification, without a unified ranking objective or standardized evaluation. We propose PCA-GAT, which formulates machining process plan recommendation as a knowledge graph enhanced collaborative filtering problem. Bayesian Personalized Ranking provides the learning objective, while Recall@K and NDCG@K define evaluation. The knowledge graph supplies semantic structure when collaborative signals are sparse. Four domain constraints, material compatibility, precision requirements, feature applicability, and operation sequencing, are introduced as attention biases during graph propagation. Type-specific weights learn their importance, and an adaptive gate adjusts their influence using local context. On a real aerospace dataset with 115 parts and 507 plans, PCA-GAT achieves Recall@1 = 0.9087 and strong cold-start robustness, with about half the degradation of the strongest baseline under severe sparsity. Ablation studies show that knowledge graph enrichment is essential, constraints add value, and ungated constraint injection can hurt performance. The learned weights identify material-operation compatibility as the dominant factor, consistent with domain expertise. Results on three public benchmarks show no degradation when constraints are absent, supporting generalization beyond manufacturing. This study establishes a standardized recommendation protocol for engineering process planning and benchmarks seven methods across three categories, showing that knowledge representation is the main bottleneck.

Plan Modes have become standard features in agentic programming tools, allowing users to gain transparency and control by working with the agent to develop a plan before task execution. However, it remains unclear whether the benefits of this feature translate to end-user programming environments such as spreadsheets. Since spreadsheet programmers tend to work iteratively and care less about technical correctness, upfront planning may not fit into their workflows as easily. In this paper, we build a prototype of a Plan Mode for spreadsheet programming and evaluate it against a non-planning baseline through a within-subjects user study (N=24). We found that despite similar task outcomes with both tools, using Plan Mode led to a reduction in refinement and a better perception of the tool across dimensions of creativity support and human-machine collaboration. We discuss the implications of these results for the future design of Plan Modes, and for the broader role of human-AI planning in end-user programming.

Two structural insights have been overlooked in automated residential floor plan generation. First, design is inherently progressive. Architects begin with rough strokes and refine them over time, whereas existing methods typically require their conditioning representation to be fully specified before generation, a fundamental mismatch with how design actually works. Second, the 2D floor plan is not an optional intermediate but an irreplaceable spatial contract. Once room boundaries, doors, and windows are fixed, furnishing reduces from open-ended spatial reasoning to bounded constraint satisfaction. Bypassing this contract, as existing 3D systems do by delegating layout to language models, yields overlapping rooms and implausible proportions; directly calling general-purpose language models likewise produces geometrically invalid layouts. Guided by these insights, we present PlanCraft. SketchPlan supplies the missing training signal by replaying the architect's drawing process on 80K real floor plans, producing partial sketches at every completeness level. PlanCraft-Diff progressively sharpens an incomplete sketch into a geometrically precise, vectorizable floor plan through a coarse-to-fine strategy. With the spatial contract established, PlanCraft-Agent then furnishes the scene within well-defined room boundaries. Experiments show that PlanCraft achieves a 61.1% lower FID than the best existing 2D method and surpasses existing 3D systems by 15 points in expert-rated spatial rationality, with a sketch at only 25% completion already outperforming all fully specified baselines.

Current video generation models achieve impressive results in single-shot generation, yet remain limited in cinematic video generation, where coherent narratives and effective multi-shot composition require explicit shot planning. To address this challenge, we propose ShotPlan, a framework for explicit multi-shot cinematic video generation built upon a video diffusion foundation model. Our method introduces learnable planning tokens that capture shot-level transition cues and can be seamlessly integrated with the original video generation tokens to control transition timestamps. Unlike standard video generation tokens, the proposed planning tokens are equipped with Fractional Temporal Rotary Position Embedding (FRoPE), enabling shot transitions to be modeled at the frame level. Experiments demonstrate that ShotPlan significantly outperforms existing cinematic video generation methods, offering more flexible shot management and stronger inter-shot consistency.

Latent world models are trained to predict future states in a learned representation and are then deployed inside a planner that selects actions by simulating them forward. Current practice adopts the prediction error, the single- or multi-step rollout loss on held-out data, as the training and model-selection objective, on the assumption that a lower prediction error yields better control. We show that this assumption is unreliable for a structural reason: a planner does not query the model on the training distribution but on the states that its candidate actions reach, which generally leave the data manifold, so an error averaged over the data cannot by itself govern control. We therefore reframe the objective as the discrepancy between the predicted and the true plan-cost at the plan the planner commits to, and prove that the planner's suboptimality is bounded by twice this discrepancy, whereas the data-averaged prediction error neither bounds nor tracks it. Under a linear-control premise the discrepancy separates into two terms. The first is a small on-manifold residual, on which the predicted and true dynamics agree and which a spectral tax prices through the non-normality of the latent transition operator. The second is an off-manifold divergence, on which an action carries the state off the manifold and the two dynamics diverge; this divergence is the binding term and is bounded by no data-averaged error. Synthetic operators confirm the pricing formulas, and latent model-predictive control experiments confirm the decoupling: across seeds, the single-step validation error is essentially uncorrelated with control success, whereas a fidelity score on the planner-reachable measure tracks it.

Safety evaluations of multi-agent LLM systems often compare a direct prompt with a planner-executor pipeline and report the difference as a single "pipeline effect." We argue that this aggregate is difficult to interpret because it conflates three mechanisms: harmful intent may be reframed as plausible operational work, the planner may refuse or transform the request, and the executor may act under delegation prompts implying prior approval. To separate these factors, we introduce a five-condition controlled contrast design, evaluated on 30 synthetic harmful scenarios and an exploratory external validation set from four agent-safety benchmarks using LLM-judged compliance. Our results show that aggregate pipeline safety is not a stable architectural property. Operational reframing is the most portable risk signal, increasing compliance for GPT, Gemini, and DeepSeek across both scenario sets, while Claude is comparatively resistant. Planner behavior can offset this risk mainly through refusal; however, when the planner produces executable steps, the executor may become more compliant than under the direct operational baseline. Approval-framed delegation is sensitive to prompt design, model pairing, and scenario source, and a skeptical executor prompt sharply reduces compliance. Raw-direct model rankings can also mispredict deployed planner-executor behavior. Gemini is safest under raw direct prompts in the primary set yet shows the largest amplification with a Claude planner, rising from 8.9 percent to 38.9 percent compliance. GPTs near-zero aggregate pipeline effect instead hides a reframing increase canceled by planner refusal. These findings suggest that multi-agent safety evaluations should report reframing, planner behavior, delegation framing, and model pairing separately before attributing failures to architecture itself.

i-EXAM is a planning-powered tool that helps system administrators to create security profiles of complex networks and perform what-if analyses to identify network hardening strategies. It leverages planning compilation that provides soundness and completeness guarantees to identify attack paths, evaluate security metrics, generate diverse hardening strategies, and explain these strategies in natural language using Large Language Models.

Slide design requires personalizing both deck themes and page layouts. Yet, current AI agent-based methods struggle with fine-grained, page-level design. Solely relying on prespecified templates or user verbose instructions, they fail to capture latent design intents, leaving Page-level Slide Personalization (PSP) unresolved. To close this gap, this work formulates PSP as an inverse planning problem. We propose to learn a design intent without assuming any knowledge of the specific executing tools (e.g., PowerPoint, Beamer) being used. However, relinquishing control over these tools makes the problem intractable to optimize end-to-end. To overcome this, we propose SPIRE, a principled framework to solve PSP approximately. By intentionally corrupting the visual structures of clean slides, SPIRE creates a verifiable task to denoise the corruption, whereby two agents learn to collaboratively refine executable designs via reinforcement learning (RL). We present a proof that structural denoising is a consistent surrogate for PSP, and that the multi-agent formulation strictly reduces policy gradient variance in RL. Extensive experiments demonstrate the superiority of SPIRE.

Large language models can write plausible CAD scripts, but reliable industrial CAD modeling requires more than syntactically valid code: every feature, placement, and assembly relation must be accepted by an exact geometric kernel while remaining editable as parametric boundary representation geometry. We present Embodied CAD, solver-grounded LLM agents for parametric B-Rep assembly modeling. Instead of generating a complete script in one pass, the agent iteratively selects actions from a stratified L0-L4 CAD skill library, resolves them into typed geometric operations, executes them in a CAD backend, and uses solver feedback to plan, repair, and learn. The framework combines action grammar constraints, deterministic parameter resolution, and solver-derived rewards for supervised warm-up and GRPO-style refinement. We evaluate Embodied CAD on multi-step mechanical, industrial equipment, and mold-oriented assembly tasks using solver-aligned metrics: executable rate, skill accuracy, operation-family accuracy, exact policy accuracy, and task completion success. The results show that solver-grounded planning executes all strong-planner workflows in the current benchmark, while learned controllers reach high executable rates and expose the remaining gap between valid tool calls and exact long-horizon policy prediction.

Large language model (LLM) multi-agent systems increasingly depend not only on how individual agents reason, but also on how agents are connected. This paper introduces QueenBee Planner, a framework that treats inter-agent communication topology as a retrievable and self-improving design skill. A pool of worker agents, the task adapter, and the scoring function are frozen; only an outer LLM planner learns to generate temporal communication DAGs specifying who sends information to whom, in which round, who merges messages, and who emits the final answer. Execution traces are distilled into evidence-backed design rules with three actions: \emph{Preserve}, \emph{Modify}, and \emph{Avoid}. To prevent self-evolution from turning lucky runs or plausible but false explanations into policy, QueenBee uses held-out acceptance gates, variance-aware credit, motif-level attribution, transfer trust, insight falsification, and structural deduplication. We evaluate the method on Count-Frequency aggregation and Silo-Bench-style distributed coordination tasks. With fixed workers, self-evolved graph generation produces communication structures that improve over fixed topologies and cold generation. In the CF fulltest setting, the best generated graph reduces RMSE from 12.53 for the strongest fixed topology to 7.87 while also reducing messages, model calls, and token cost; Silo-style results show the same direction of improvement over cold and fixed-topology baselines. These results suggest that multi-agent systems can learn reusable architectural design knowledge rather than merely memorizing task answers.

Personalized public transit routing in public transit systems remains challenging due to the difficulty of capturing and integrating diverse user preferences into routing algorithms. This paper presents ChatPlanner, a novel framework that leverages Large Language Models (LLMs) to enable preference aware public transit routing. Our approach employs fine-tuned LLMs with Retrieval-Augmented Generation (RAG) to extract routing parameters and interpret nuanced user preferences from natural language queries, subsequently integrating these preferences into the objective function of a public transit routing algorithm. This study designs preference aware datasets incorporating eight personas and five contexts to establish scoring standards for both fine-tuning and RAG. This work conducted three experiments to validate the solutions' feasibility, extraction of routing information and preferences, and solution set quality and completeness. Results demonstrate that ChatPlanner generates feasible solutions reliably. Fine-tuning enforces the required output structure and learns general preference patterns, while RAG provides query-specific context to resolve imprecise or conversational expressions and calibrate continuous scores. The combination of both achieves the highest accuracy in routing information extraction and user preference interpretation. Results based on selected case studies show that by capturing user preferences, ChatPlanner identifies valuable solutions across different dimensions that existing route planners overlook, generating more valuable route alternatives. This research establishes a new paradigm for integrating natural language understanding into transportation optimization.

Published agent capability scores conflate what a model can do with what its scaffold lets it do, and the magnitude of this elicitation gap is not well characterized under controlled conditions. This study executes a pre-registered controlled comparison of three scaffolds (ReAct, a Planner-Actor-Rater multi-agent design, and planner-then-executor) across five models from three providers (Claude Opus 4.7, Sonnet 4.6, Haiku 4.5; Gemini 3.1 Pro Preview; GPT-5.5) on GAIA validation Levels 1 and 2, holding tasks and conditions fixed, with three attempts per question. Scaffold choice alone moves measured accuracy by as much as 28 percentage points within a single model (Opus, Level 2, robust slice), confirming the pre-registered hypothesis that scaffold variation produces gaps of at least 10 points. The pre-registered prediction that more capable models would be less scaffold-sensitive is rejected in direction: scaffold effects vary significantly by model in every dataset slice, but the most capable Anthropic model gains the most from structured scaffolds at the harder level, and tier-scaling holds only at Level 1 under the robust slice. The multi-agent advantage over ReAct at Level 2 appears within the Anthropic family but not for the cross-provider models, making model family rather than capability tier the conditioning variable, and the predicted planner-executor advantage on file-reading tasks is falsified. Structured scaffolds make fewer tool calls yet recover more often from mid-trajectory errors at the harder level, and a single cell (Gemini with planner-then-executor) is the cheapest at both levels and the most accurate at Level 2. These results indicate that single-scaffold capability numbers are scaffold-conditional estimates and that the elicitation gap is not guaranteed to shrink as models improve.

Reinforcement learning (RL) has emerged as a standard post-training paradigm for shaping large language models (LLMs) into capable agents. In agentic RL, the rollout stage generates trajectories while invoking tools, producing long-tailed and non-stationary workloads that expose two fundamental challenges. First, due to the long-tailed response distribution, a small fraction of trajectories dominates rollout makespan.Second, rollout and training differ in their compute patterns, memory demands, and sensitivity to sequence length. As the policy evolves, shifts in the workload distribution further change their relative resource demands, making it difficult to maintain balanced execution across the two stages. We present Libra, an adaptive runtime for agentic RL post-training with two complementary components: (1) intra-stage scheduling via a Causality-Guided Bucket Scheduler that routes requests across execution buckets with different parallelism configurations, reducing delays from rollout stragglers; and (2) cross-stage coordination that dynamically reallocates workers between rollout and training as the workload changes. It moves workers between the two stages through a non-blocking protocol without interrupting ongoing training. Evaluated on a 48x NVIDIA A800 GPU cluster and a 160x Ascend 910B3 NPU cluster across three agentic benchmarks, Libra achieves up to 4.2x higher throughput and up to 2.7x faster reward convergence

LLM agents now draw on growing skill libraries to handle complex tasks. However, injecting more skills does not always improve task completion and can even degrade it. Existing methods still treat skill injection as a static step, selecting skills with fixed criteria, fixing the budget in advance, and leaving descriptions unchanged. We argue that this static treatment can undermine the utility of skills, because which skills are exposed, how many are included, and how they are presented all affect downstream performance. We propose SkillsInjector, a two-stage adaptive method that jointly addresses these decisions. First, a context planner learns execution-grounded skill preferences and admits an adaptive number of skills for each task. A set-aware renderer then tailors how selected descriptions are presented relative to their co-injected neighbors. Across tau2-bench, SkillsBench, and ALFWorld, SkillsInjector achieves the highest score, improving over the strongest baseline by 3.9, 6.1, and 7.3 percentage points, respectively. Ablation studies show that skill selection, adaptive budgeting, and set-aware rendering each contribute to the gain. These results show that skill-augmented agents benefit from optimizing the injected context itself. Code will be released upon publication

Autonomous UAV flight in confined, wall-dense environments requires low-latency and reliable motion planning under strict safety constraints. Traditional optimization-based planners suffer from mapping latency and easily fall into local minima when navigating through dense structural obstacles. Meanwhile, existing end-to-end learning methods struggle to extract fine-grained geometric features from raw depth images and lack hard kinodynamic constraints, leading to unpredictable collisions near walls. To address these issues, we propose KIO-planner, an attention-guided single-stage trajectory planning framework. First, we integrate a Convolutional Block Attention Module (CBAM) into the perception backbone to adaptively focus on critical structural edges and traversable space. Second, we introduce a novel Dual Mapping mechanism--comprising physical bounds activation and a deterministic Geometric Safety Shield in the depth-pixel space--to enforce kinodynamic feasibility and collision-free flight without global map fusion. Extensive high-fidelity simulated experiments demonstrate that KIO-planner enables highly agile navigation at speeds up to 3.0 m/s. Compared to the state-of-the-art baseline, KIO-planner achieves lower inference latency (approximately 24 ms) and generates significantly smoother trajectories, reducing control cost by 28.4%. Most notably, our Dual Mapping substantially increases the worst-case safety margin, measured by minimum distance to obstacles, from 0.48 m to 0.76 m, ensuring fast, smooth, and safer navigation in highly constrained environments.

In flexible assembly systems, existing task planning methods require a time-consuming configuration process by multiple experts to establish a production line for a new product. To address this challenge, we propose a multi-agent based task planning framework for flexible assembly systems, denoted as AssemPlanner. It takes tasks described in natural language as input, which are then converted into actionable sequential production operations. It comprises several specialized agents, including SchedAgent , KnowledgeAgent, LineBalanceAgent, and a scene graph. Within the proposed framework, SchedAgent serves as the central reasoning engine. Departing from traditional static pipelines, AssemPlanner utilizes a ReAct-based SchedAgent to adaptively adjust actions via multi-agent feedback. By observing the feedback from KnowledgeAgent, LineBalanceAgent, and the scene graph, it autonomously resolves complex industrial process constraints. To facilitate reproducibility, all code and datasets are released at https://github.com/chz332/Assemplanner.

HTN planning is a variation of classical planning where, instead of searching for a linear sequence of actions, an algorithm decomposes higher-level tasks using a method library until only executable actions remain. On one hand, this allows one to introduce domain knowledge that can speed up the search for a solution through the method library. On the other hand, it creates challenges that go beyond those of classical state-space search. While recent research produced a number of heuristics and novel algorithms that speed up HTN planning, these heuristics are not yet as informative as those available in classical planning algorithms. We investigate whether large language models (LLMs) can generate effective search heuristics for HTN planning, extending the methodology of Corrêa, Pereira, and Seipp (2025) from classical to hierarchical planning. Using the Pytrich planner on six standard total-order HTN benchmark domains, we evaluate heuristics generated by nine LLMs under domain-specific prompting and compare them against the TDG and LMCount domain-independent baselines and the PANDA planner. Our results show that LLM-generated heuristics nearly match the coverage of the best available HTN planner, while substantially reducing search effort on 83% of shared problems.

Integrating Large Language Models (LLMs) into complex software systems enables the generation of human-understandable explanations of opaque AI processes, such as automated task planning. However, the quality and reliability of these explanations heavily depend on effective prompt engineering. The lack of a systematic understanding of how diverse stakeholder groups formulate and refine prompts hinders the development of tools that can automate this process. We introduce COMPASS (COgnitive Modelling for Prompt Automated SynthesiS), a proof-of-concept self-adaptive approach that formalises prompt engineering as a cognitive and probabilistic decision-making process. COMPASS models unobservable users' latent cognitive states, such as attention and comprehension, uncertainty, and observable interaction cues as a POMDP, whose synthesised policy enables adaptive generation of explanations and prompt refinements. We evaluate COMPASS using two diverse cyber-physical system case studies to assess the adaptive explanation generation and their qualities, both quantitatively and qualitatively. Our results demonstrate the feasibility of COMPASS integrating human cognition and user profile's feedback into automated prompt synthesis in complex task planning systems.

This report describes a Ref-VOS pipeline centered on Sa2VA and organized with explicit agent roles. The key idea is that Sa2VA should provide the first dense semantic hypothesis, while an agent loop decides whether that hypothesis should be accepted, revised, or refined. The pipeline starts with a target-presence judgment stage. If the referred object does not exist in the video, the system directly outputs zero masks. Otherwise, Sa2VA receives the video and referring prompt and produces a coarse mask trajectory over the full video. This trajectory is treated as a semantic prior rather than a final answer. A planner agent decomposes the query, temporal partition agents identify informative blocks, scout agents search for anchor frames, and refinement agents convert reliable Sa2VA masks into boxes and points for SAM3 propagation. A critic scores candidate trajectories, a reflection controller repairs weak hypotheses, and a collaboration controller reconciles multiple agent branches. The result is a Ref-VOS system in which Sa2VA is responsible for dense grounded understanding, while the agent layer handles presence verification, temporal search, confidence-aware revision, and final mask refinement.

Planning requires a transition model that predicts how each action changes the current state. When a large language model (LLM) plays this role, every next state is generated token by token, which makes searching over many possible futures slow and expensive. Existing alternatives either still query an LLM at every step or require a symbolic model of the domain. We propose EmbedPlan, a transition model built on frozen text embeddings: it embeds natural language descriptions of the state and the action with a frozen LLM, predicts the embedding of the next state with a lightweight learned network, and returns the closest real state. Because this network can be trained on top of any encoder, EmbedPlan also provides a controlled way to compare text representations for learning transitions. We evaluate it on 9 classical planning domains, under six settings that hold out progressively more of the data, from transitions to entire domains, and against baselines ranging from predicting no change to learning symbolic action rules. On planning problems seen during training, EmbedPlan almost always ranks the true next state among its top five guesses, still does so for most queries even when every observed state is a candidate, and retains 92-99% of its single-step accuracy when predicting several steps ahead from its own outputs. Given the same candidate states as GPT-5.4, it picks the true next state more often while taking about 0.17 ms per transition with cached embeddings. Accuracy is lower on unseen problems and near chance on unseen domains, and the controlled comparison traces this limit to the state representation rather than to the learned transition.

Multi-agent systems based on large language models, particularly centralized architectures, have recently shown strong potential for complex and knowledge-intensive tasks. However, central agents often suffer from unstable long-horizon collaboration due to the lack of memory management, leading to context bloat, error accumulation, and poor cross-task generalization. To address both task-level memory inefficiency and the inability to reuse coordination experience, we propose StackPlanner, a hierarchical multi-agent framework with explicit memory control. StackPlanner addresses these challenges by decoupling high-level coordination from subtask execution with active task-level memory control, and by learning to retrieve and exploit reusable coordination experience via structured experience memory and reinforcement learning. Experiments on multiple deep-search and agent system benchmarks demonstrate the effectiveness of our approach in enabling reliable long-horizon multi-agent collaboration.