Large Language Model Reasoning

Causal reasoning in natural language requires identifying relevant variables, understanding their interactions, and reasoning about effects and interventions, often under noisy or ambiguous conditions. While large language models (LLMs) exhibit strong general reasoning abilities, they struggle to disentangle correlation from causation, particularly when observations are partially incorrect or irrelevant information is present. In this work, we introduce NoisyCausal, a new benchmark designed to evaluate causal reasoning under structured noise. Each instance is generated from a ground-truth causal graph and contextualized with a natural language scenario by injecting controllable forms of noise, such as irrelevant distractors, value perturbations, confounding, and partial observability. Moreover, we propose a modular reasoning framework that combines LLMs with explicit causal structure to address these challenges. Our method prompts the LLM to extract variables, construct a causal graph from context, and then reformulates the reasoning task as a structured prompt grounded in this graph. Rather than relying on statistical patterns alone, the LLM is guided by symbolic structure, enabling more interpretable and robust inference. Experimental results show that our method significantly outperforms standard prompting and reasoning baselines on NoisyCausal. Furthermore, it generalizes well to external benchmarks such as Cladder without task-specific tuning. Our findings highlight the importance of combining causal abstractions with language-driven reasoning to achieve faithful and robust causal understanding in LLMs.

Despite significant advances, large language models (LLMs) continue to exhibit brittle performance on complex temporal reasoning tasks. This failure mode is widely attributed to inherent deficits in autoregressive logical deduction. In this paper, we challenge this prevailing narrative, demonstrating that temporal reasoning is not the fundamental bottleneck; rather, the locus of failure lies in unstructured text-to-event representation. We introduce a novel neuro-symbolic question-answering framework governed by a Probabilistic Inconsistency Signal (PIS) that explicitly isolates perceptual errors from reasoning failures. By lifting unstructured text into explicit event graphs and interval constraints, our architecture strictly decouples semantic extraction from a symbolic reasoning engine. To robustly detect structural breaks, the PIS elegantly unifies symbolic credal intervals with epistemic neural uncertainty extracted via Evidential Deep Learning on LLM hidden states. Empirical evaluations reveal a striking paradigm shift: when provided with correct structural representations, our system's explicit proof traces achieve perfect 1.0 accuracy (4000/4000) and strictly zero false positives/negatives on temporal arithmetic benchmarks. On broader, noise-injected QA settings, the framework maintains a competitive 75.1% accuracy while enabling deterministic, step-level failure localization. Ultimately, by isolating the representation bottleneck from the reasoning substrate, this work reframes temporal QA from an algorithmic reasoning challenge to a structural alignment problem, charting a verifiable path forward for reliable neuro-symbolic AI.

Inductive Logic Programming (ILP) aims to learn interpretable first-order rules from data, but existing symbolic and neuro-symbolic approaches struggle to scale to noisy and probabilistic settings. Classical ILP relies on discrete combinatorial rule search and is brittle under uncertainty, while differentiable ILP methods typically depend on predefined rule templates or inaccurate fuzzy operators that suffer from vanishing gradients or poor approximation of logical structure when reasoning over probabilistic predicate valuations. This paper proposes an Attention-based Neuro-symbolic Differentiable Rule Extractor (ANDRE), a novel ILP framework that learns first-order logic programs by optimizing over a continuous rule space with attention-based logical operators. ANDRE replaces both rule templates and logical operators with fully differentiable, attention-driven conjunction and disjunction operators that approximate logical min-max semantics, enabling accurate, stable, and interpretable reasoning over probabilistic data. By softly selecting, negating, or excluding predicates within each rule, ANDRE supports flexible rule induction while preserving symbolic structure. Extensive experiments on classical ILP benchmarks, large-scale knowledge bases, and synthetic datasets with probabilistic predicates and noisy supervision demonstrate that ANDRE achieves competitive or superior predictive performance while reliably recovering correct symbolic rules under uncertainty. In particular, ANDRE remains robust to moderate label noise, substantially outperforming existing differentiable ILP methods in both rule extraction quality and stability.

Reinforcement learning with verifiable rewards has become a common way to improve explicit reasoning in large language models, but final-answer correctness alone does not reveal whether the reasoning trace is faithful, reliable, or useful to the model that consumes it. This outcome-only signal can reinforce traces that are right for the wrong reasons, overstate reasoning gains by rewarding shortcuts, and propagate flawed intermediate states in multi-step systems. To this end, we propose TraceLift, a planner-executor training framework that treats reasoning as a consumable intermediate artifact. During planner training, the planner emits tagged reasoning. A frozen executor turns this reasoning into the final artifact for verifier feedback, while an executor-grounded reward shapes the intermediate trace. This reward multiplies a rubric-based Reasoning Reward Model (RM) score by measured uplift on the same frozen executor, crediting traces that are both high-quality and useful. To make reasoning quality directly learnable, we introduce TRACELIFT-GROUPS, a rubric-annotated reason-only dataset built from math and code seed problems. Each example is a same-problem group containing a high-quality reference trace and multiple plausible flawed traces with localized perturbations that reduce reasoning quality or solution support while preserving task relevance. Extensive experiments on code and math benchmarks show that this executor-grounded reasoning reward improves the two-stage planner-executor system over execution-only training, suggesting that reasoning supervision should evaluate not only whether a trace looks good, but also whether it helps the model that consumes it. Our code is available at: https://github.com/MasaiahHan/TraceLift

Large Language Models (LLMs) are increasingly explored as high-level reasoning engines for cyber-physical systems, yet their application to real-time UAV swarm management remains challenging due to heterogeneous interfaces, limited grounding, and the need for long-running closed-loop execution. This paper presents a mission-agnostic, agent-enhanced LLM framework for UAV swarm control, where users express mission objectives in natural language and the system autonomously executes them through grounded, real-time interactions. The proposed architecture combines an LLM-based Agent Core with a Model Context Protocol (MCP) gateway and a Web-of-Drones abstraction based on W3C Web of Things (WoT) standards. By exposing drones, sensors, and services as standardized WoT Things, the framework enables structured tool-based interaction, continuous state observation, and safe actuation without relying on code generation. We evaluate the framework using ArduPilot-based simulation across four swarm missions and six state-of-the-art LLMs. Results show that, despite strong reasoning abilities, current general-purpose LLMs still struggle to achieve reliable execution - even for simple swarm tasks - when operating without explicit grounding and execution support. Task-specific planning tools and runtime guardrails substantially improve robustness, while token consumption alone is not indicative of execution quality or reliability.

Recent advances in Large Reasoning Models (LRMs) trained with Long Chain-of-Thought have demonstrated remarkable capabilities in code generation and mathematical reasoning. However, their potential in multi-turn Text-to-SQL tasks remains largely underexplored. Existing approaches typically rely on unstable API-based inference or require expensive fine-tuning on small-scale models. In this work, we present Rose-SQL, a training-free framework that leverages small-scale LRMs through in-context learning to enable accurate context-dependent parsing. We introduce the Role-State, a fine-grained representation that bridges the structural gap between schema linking and SQL generation by serving as a structural blueprint. To handle conversational dependencies, Rose-SQL traces the evolution of Role-State through historical context via structural isomorphism checks, guiding the model to infer the possible SQL composition for the current question through verified interaction trajectories. Experiments on the SParC and CoSQL benchmarks show that, within the Qwen3 series, Rose-SQL outperforms in-context learning baselines at the 4B scale and substantially surpasses state-of-the-art fine-tuned models at the 8B and 14B scales, while showing consistent gains on additional reasoning backbones.

Parameter-efficient fine-tuning (PEFT) has become a practical route for adapting large language models to downstream tasks, with LoRA-style methods being particularly attractive because they are inexpensive to train and easy to deploy. Most LoRA variants, however, revise the update rule within the weight space of each layer and leave the intermediate representations formed by deeper layers largely unused. We propose Echo-LoRA, a cross-layer representation injection method for parameter-efficient fine-tuning. During training, Echo-LoRA collects boundary hidden states from deeper source layers, aggregates them into a sample-level echo representation, and uses lightweight projection and gating networks to inject the resulting signal into shallow LoRA or DoRA modules. Answer-only masking, masked distillation, and stochastic routing are used to keep this auxiliary path stable and to reduce the gap between training and inference. On eight commonsense reasoning benchmarks, Echo-LoRA exceeds the reported LoRA baselines by 5.7 percentage points on average across LLaMA-7B, LLaMA2-7B, and LLaMA3-8B. Under reproduced LoRA baselines in our unified implementation, the average gain is 3.0 points; when combined with DoRA, the gain is 2.7 points. The Echo path is discarded after training, so the deployed model keeps the original low-rank LoRA/DoRA form and adds neither inference-time parameters nor inference computation.

Multidimensional human understanding is essential for real-world applications such as film analysis and virtual digital humans, yet current LVLM benchmarks largely focus on single-task settings and lack fine-grained, human-centric evaluation. In this work, we introduce MHPR, a comprehensive benchmark for joint perception-reasoning over human-centric scenes spanning individual, multi-person, and human-object interaction dimensions. MHPR comprises a multi-level data design-Captioned Raw Data (C-RD), Supervised Fine-Tuning Data (SFT-D), Reinforcement Learning Data (RL-D), and Test Data (T-D)-together with an automated caption/VQA generation pipeline (ACVG) that performs category-wise attribute decomposition, attribute-specific rewriting, and multi-model voting to ensure high-quality, scalable annotations. We evaluate state-of-the-art vision-language models on fine-grained attributes (appearance, clothing, pose, parts) and high-level semantics (social relations, action semantics, spatial relations, intent and functionality). Our findings show that: 1) format-aligned SFT data substantially improves instruction following and stability; 2) challenge-focused RL data derived from bad-case analysis further enhances perception and reasoning on difficult instances; and 3) training Qwen2.5-VL-7B with MHPR yields significant gains, achieving near-parity with considerably larger models. We release ACVG and MHPR to facilitate reproducible, extensible research on human-centric perception and reasoning.

Time series (TS) reasoning models (TSRMs) have shown promising capabilities in general domains, yet they consistently fail in the financial domain, which exhibits unique characteristics. We propose a general 2 x 2 capability taxonomy for TSRMs by crossing 1) single-entity vs. multi-entity analysis with 2) assessment of the current state vs. prediction of future behavior. We instantiate this taxonomy in the financial domain-where the distinction between deterministic assessment and stochastic prediction is particularly critical-as ten financial reasoning tasks, forming the FinTSR-Bench benchmark based on S&P stocks. To this end, we propose FinSTaR (Financial Time Series Thinking and Reasoning), trained on FinTSR-Bench with distinct chain-of-thought (CoT) strategies tailored to each category. For assessment, which is deterministic (i.e., computable from observable data), we employ Compute-in-CoT, a programmatic CoT that enables models to derive answers directly from raw prices. For prediction, which is inherently stochastic (i.e., subject to unobservable factors), we adopt Scenario-Aware CoT, which generates diverse scenarios before making a judgment, mirroring how financial analysts reason under uncertainty. The proposed method achieves 78.9% average accuracy on FinTSR-Bench, substantially outperforming LLM and TSRM baselines. Furthermore, we show that the four capability categories are complementary and mutually reinforcing through joint training, and that Scenario-Aware CoT consistently improves prediction accuracy over standard CoT. Code is available at https://github.com/seunghan96/FinSTaR.

As multimodal content continues to expand at a rapid pace, audio retrieval has emerged as a key enabling technology for media search, content organization, and intelligent assistants. However, most existing benchmarks concentrate on semantic matching and fail to capture the fact that real-world queries often demand advanced reasoning abilities, including negation understanding, temporal ordering, concurrent event recognition, and duration discrimination. To address this gap, we introduce ReasonAudio, the first reasoning-intensive benchmark for Text-Audio Retrieval, comprising 1,000 queries and 10,000 composite audio clips across five fundamental reasoning tasks: Negation, Order, Overlap, Duration, and Mix. Despite their intuitive nature for humans and straightforward construction, these tasks pose significant challenges to current models. Our evaluation of ten state-of-the-art models reveals the following findings: All models struggle with reasoning-intensive audio retrieval, performing particularly poorly on Negation and Duration while showing relatively better results on Overlap and Order. Moreover, Multimodal Large Language Model-based embedding models fail to inherit the reasoning capabilities of their backbones through contrastive fine-tuning, suggesting that current training paradigms are insufficient to preserve reasoning capacity in retrieval settings

Retrieval-augmented generation (RAG) has proven effective for knowledge-intensive tasks, but is widely believed to offer limited benefit for reasoning-intensive problems such as math and code generation. We challenge this assumption by showing that the limitation lies not in RAG itself, but in the choice of corpus. Instead of retrieving documents, we propose retrieving thinking traces, i.e., intermediate thinking trajectories generated during problem solving attempts. We show that thinking traces are already a strong retrieval source, and further introduce T3, an offline method that transforms them into structured, retrieval-friendly representations, to improve usability. Using these traces as a corpus, a simple retrieve-then-generate pipeline consistently improves reasoning performance across strong models and benchmarks such as AIME 2025--2026, LiveCodeBench, and GPQA-Diamond, outperforming both non-RAG baselines and retrieval over standard web corpora. For instance, on AIME 2025-2026, RAG with traces generated by Gemini-2-thinking achieves relative gains of +56.3%, +8.6%, and +7.6% for Gemini-2.5-Flash, GPT-OSS-120B, and GPT-5, respectively, even though these are more recent models. Overall, our results suggest that thinking traces are an effective retrieval corpus for reasoning tasks, and transforming them into structured, compact, or diagnostic representations unlocks even stronger gains. Code available at https://github.com/Narabzad/t3.

Reinforcement learning is crucial for aligning large language models to perform complex reasoning tasks. However, current algorithms such as Group Relative Policy Optimization suffer from coarse grained, sequence level credit assignment, which severely struggles to isolate pivotal reasoning steps within long Chain of Thought generations. Furthermore, the standard unbounded Kullback Leibler divergence penalty induces severe gradient instability and mode seeking conservatism, ultimately stifling the discovery of novel reasoning trajectories. To overcome these limitations, we introduce Distribution Guided Policy Optimization, a novel critic free reinforcement learning framework that reinterprets distribution deviation as a guiding signal rather than a rigid penalty. DGPO replaces the volatile KL divergence with the bounded Hellinger distance to safely quantify token level exploration without the risk of gradient explosion. To effectively distinguish genuine reasoning breakthroughs from hallucinatory noise, we propose an entropy gating mechanism that scales this deviation by the policy`s epistemic uncertainty. By dynamically redistributing the coarse sequence-level advantage to individual tokens based on these gated scores, DGPO heavily incentivizes critical exploratory steps while suppressing unwarranted, low-entropy deviations. Consequently, DGPO completely eliminates the traditional token-level KL penalty and achieves fine-grained credit reallocation without the computational overhead of an additional value network. Extensive empirical evaluations demonstrate that DGPO sets a new state-of-the-art for critic free alignment. Notably, on the Qwen2.5-32B architecture, DGPO achieves 60.0% Avg@32 accuracy and 46.0% Avg@32 accuracy on the challenging AIME2024 and AIME2025 benchmarks respectively, substantially outperforming competitive baselines like DAPO.

In single-stream autoregressive interfaces, the same tokens both update the model state and constitute an irreversible public commitment. This coupling creates a silence tax: additional deliberation postpones the first task-relevant content, while naive early streaming risks premature commitments that bias subsequent generations. We introduce Side-by-Side (SxS) Interleaved Reasoning, which makes disclosure timing a controllable decision within standard autoregressive generation. SxS interleaves partial disclosures with continued private reasoning in the same context, but releases content only when it is supported by the reasoning so far. To learn such pacing without incentivizing filler, we construct entailment-aligned interleaved trajectories by matching answer prefixes to supporting reasoning prefixes, then train with SFT to acquire the dual-action semantics and RL to recover reasoning performance under the new format. Across two Qwen3 architectures/scales (MoE Qwen3-30B-A3B, dense Qwen3-4B) and both in-domain (AIME25) and out-of-domain (GPQA-Diamond) benchmarks, SxS improves accuracy--content-latency Pareto trade-offs under token-level proxies such as inter-update waiting.

Travel planning serves as a critical task for long-horizon reasoning, exposing significant deficits in LLMs. However, existing benchmarks and evaluations primarily assess final plans in an end-to-end manner, which lacks interpretability and makes it difficult to analyze the root causes of failures. To bridge this gap, we decompose travel planning into five constituent atomic sub-capabilities, including \emph{Constraint Extraction}, \emph{Tool Use}, \emph{Plan Generation}, \emph{Error Identification}, and \emph{Error Correction}. We implement a decoupled evaluation protocol leveraging oracle intermediate contexts to rigorously isolate these components, thereby measuring the atomic performance boundary without the noise of cascading errors. Our results highlight a clear contrast in performance: while LLMs are proficient in extracting explicit constraints, they struggle to infer implicit, open-world requirements. Furthermore, they exhibit structural biases in plan generation and suffer from ineffective self-correction, characterized by excessive sensitivity and erroneous persistence. These findings offer precise directions for improving LLM reasoning and planning abilities.

Large Language Models (LLMs) have demonstrated strong capabilities in natural language understanding and reasoning. However, their ability to perform exact, deterministic computation remains unclear. In this work, we systematically evaluate multiple prompting strategies, including Chain-of-Thought (CoT), Least-to-Most decomposition, Program-of-Thought (PoT), and Self-Consistency (SC), on tasks requiring precise and error-free outputs, including binary counting, longest substring detection, and arithmetic evaluation. To support this study, we introduce a synthetic dataset with diverse natural language instructions, enabling controlled evaluation of exact computation across multiple task types. Our results show that standard prompting methods achieve only moderate accuracy on sequence-based tasks. CoT provides limited improvement, while Least-to-Most suffers from error accumulation. In contrast, PoT achieves perfect accuracy by generating executable code and delegating computation to an external interpreter. Self-Consistency improves robustness through majority voting, but incurs substantial computational overhead. We further train a small domain-specific model (CodeT5-small) to generate executable programs, which achieves perfect accuracy on held-out synthetic test data across all tasks with minimal training cost. Overall, our findings suggest that LLMs may simulate reasoning patterns rather than reliably perform exact symbolic computation. For deterministic tasks, combining LLMs with external tools or using specialized models provides a more reliable and efficient solution.

Millions of users turn to AI models for their information needs. It is conceivable that a large number of user queries contain assumptions that may be factually inaccurate. Prior work notes that large language models (LLMs) often fail to challenge such erroneous assumptions, and can reinforce users' misinformed opinions. However, given the recent advances, especially in model's reasoning capabilities, we revisit whether large reasoning models (LRMs) can reason about the underlying assumptions and respond to user queries appropriately. We construct queries with varying degrees of presuppositions spanning health, science, and general knowledge, and use it to evaluate several widely-deployed models When compared to non-reasoning models, we find that reasoning models achieve a slightly higher accuracy (2-11%), but they still fail to challenge a large fraction (26-42%) of false presuppositions. Further, reasoning models remain susceptible to how strongly the presupposition is expressed.

Vision-Language-Action (VLA) models aim to provide a single generalist controller for robots, but today's systems fall short on the criteria that matter for real-world deployment. Frontier models are closed, open-weight alternatives are tied to expensive hardware, reasoning-augmented policies pay prohibitive latency for their grounding, and fine-tuned success rates remain below the threshold for dependable use. We present MolmoAct2, a fully open action reasoning model built for practical deployment, advancing its predecessor along five axes. We introduce MolmoER, a VLM backbone specialized for spatial and embodied reasoning, trained on a 3.3M-sample corpus with a specialize-then-rehearse recipe. We release three new datasets spanning low-to-medium cost platforms, including MolmoAct2-BimanualYAM, 720 hours of teleoperated bimanual trajectories that constitute the largest open bimanual dataset to date, together with quality-filtered Franka (DROID) and SO100/101 subsets. We provide OpenFAST, an open-weight, open-data action tokenizer trained on millions of trajectories across five embodiments. We redesign the architecture to graft a flow-matching continuous-action expert onto a discrete-token VLM via per-layer KV-cache conditioning. Finally, we propose MolmoThink, an adaptive-depth reasoning variant that re-predicts depth tokens only for scene regions that change between timesteps, retaining geometric grounding at a fraction of prior latency. In the most extensive empirical study of any open VLA to date, spanning 7 simulation and real-world benchmarks, MolmoAct2 outperforms strong baselines including Pi-05, while MolmoER surpasses GPT-5 and Gemini Robotics ER-1.5 across 13 embodied-reasoning benchmarks. We release model weights, training code, and complete training data. Project page: https://allenai.org/blog/molmoact2

Continuous latent-space reasoning offers a compact alternative to textual chain-of-thought for multimodal models, enabling high-dimensional visual evidence to be integrated without explicit reasoning tokens. However, we identify a previously overlooked optimization pathology in existing latent visual reasoning methods: although visual latents become semantically enriched during training, their contribution to final answer prediction is systematically suppressed. Within the shared parameter space, the autoregressive objective favors shortcut reliance on direct visual input, driving latent tokens toward transition-like states rather than informative reasoning content. We term this phenomenon Silenced Visual Latents. To address it, we disentangle the two conflicting objectives by directly optimizing the latent reasoning at inference time, keeping backbone parameters frozen. In Stage I, visual latents are warmed up via query-guided contrastive latent--visual alignment, improving semantic quality while preventing latent collapse. In Stage II, the latent reasoning is further optimized via a confidence-progression reward, which incentivizes predicted token distributions along the latent span to become progressively more concentrated, routing predictions through the latent reasoning rather than bypassing it. Experiments across eight benchmarks and four model backbones show that inference-time latent optimization, without any parameter updates, effectively unleashes the suppressed reasoning capacity of visual latents.

While Large Language Models (LLMs) and Vision-Language Models (VLMs) demonstrate remarkable capabilities in high-level reasoning and semantic understanding, applying them directly to contact-rich manipulation remains a challenge due to their lack of explicit physical grounding and inability to perform adaptive control. To bridge this gap, we propose CoRAL (Contact-Rich Adaptive LLM-based control), a modular framework that enables zero-shot planning by decoupling high-level reasoning from low-level control. Unlike black-box policies, CoRAL uses LLMs not as direct controllers, but as cost designers that synthesize context-aware objective functions for a sampling-based motion planner (MPPI). To address the ambiguity of physical parameters in visual data, we introduce a neuro-symbolic adaptation loop: a VLM provides semantic priors for environmental dynamics, such as mass and friction estimates, which are then explicitly refined in real time via online system identification, while the LLM iteratively modulates the cost-function structure to correct strategic errors based on interaction feedback. Furthermore, a retrieval-based memory unit allows the system to reuse successful strategies across recurrent tasks. This hierarchical architecture ensures real-time control stability by decoupling high-level semantic reasoning from reactive execution, effectively bridging the gap between slow LLM inference and dynamic contact requirements. We validate CoRAL on both simulation and real-world hardware across challenging and novel tasks, such as flipping objects against walls by leveraging extrinsic contacts. Experiments demonstrate that CoRAL outperforms state-of-the-art VLA and foundation-model-based planner baselines by boosting success rates over 50% on average in unseen contact-rich scenarios, effectively handling sim-to-real gaps through its adaptive physical understanding.

Large language models (LLMs) can generate syntactically valid optimization programs, yet often struggle to reliably choose an effective modeling strategy, leading to incorrect formulations and inefficient solver behavior. We propose SAGE, a strategy-aware framework that makes Modeling Strategy explicit in both data construction and post-training. SAGE builds a solver-verified multi-strategy dataset and trains a student model with supervised fine-tuning followed by Segment-Weighted GRPO using a composite reward over format compliance, correctness, and solver efficiency. Across eight benchmarks spanning synthetic and real-world settings, SAGE improves average pass@1 from 72.7 to 80.3 over the strongest open-source baseline. With multiple generations, SAGE discovers more distinct correct formulations and improves component-level diversity at pass@16 by 19-29%. At the largest scale, SAGE produces more compact constraint systems with 14.2% fewer constraints than the baseline, consistent with solver-efficient modeling. Overall, these results show that making Modeling Strategy explicit improves automated optimization modeling. Code is available at https://github.com/rachhhhing/SAGE.

Autonomous data analysis agents are increasingly expected to conduct exploratory analysis with limited human guidance about data. However, existing benchmarks typically evaluate such agents in prior-guided settings, providing selected data sources, explicit data schemas, or cleaned data, thereby understating the exploratory burden. To evaluate this realistic exploratory data analysis task, we introduce DataClawBench, a benchmark built from financial think-tank consulting scenarios where agents must independently explore unfamiliar, noisy, cross-domain data and produce verifiable conclusions. DataClawBench provides a unified real-world data environment with approximately 2.06 million records across enterprise, industry, and policy domains, with native data noise preserved. On top of this data environment, it defines 492 multi-step cross-domain tasks, each annotated with intermediate milestones that diagnose exploration and reasoning failures beyond outcome accuracy. A systematic evaluation of eight advanced LLMs under the OpenClaw agent reveals that exploratory data analysis breaks agent reliability: more exploration does not reliably translate into task-relevant progress or correct final answers.

Legal texts often contain computational legal clauses--provisions whose understanding requires complex logic. While frontier Large Reasoning Models (LRMs) can describe such clauses, building production-ready systems is limited by reasoning errors and the high cost of inference. We propose Amortized Intelligence, a neuro-symbolic approach where we use an LLM once to translate a legal text into Deterministic Autonomous Contract Language (DACL): a typed graph intermediate representation. Adjudication then relies on deterministic graph executions with a visually auditable trace. In comparison against runtime LRM baselines (including GPT-5.2 and Gemini 3 Pro), our DACL-based Agent achieves near-perfect consistency and mitigates the "reasoning cliff" observed in probabilistic models. The system reduces compute costs by over 90% in high-volume workflows while satisfying the strict auditability requirements of legal adjudication.

With the rapid advancement of large language models (LLMs), classic graph learning tasks have greatly benefited from LLMs, including improved encoding of textual features, more efficient construction of graphs from text, and enhanced reasoning over knowledge graphs. In this paper, we ask a complementary question: How can graphs help LLMs? We address this question from three perspectives: 1) graphs provide an up-to-date knowledge source that helps reduce LLM hallucinations, 2) graph-based prompting techniques-such as Chain-of-Thought (CoT), Tree-of-Thought (ToT), and Graph-of-Thought (GoT)-enhance LLM reasoning capabilities, and 3) integrating graphs into LLMs improves their understanding of structured data, expanding their applicability to domains such as e-commerce, code, and relational databases (RDBs). We further outlook some future directions including designing sparse LLM architectures based on graphs and brain-inspired memory systems.

In this paper, we offer a guide for researchers on evaluating reasoning in language models, building the case that reasoning should be assessed through evidence of adaptive, multi-step search rather than final-answer accuracy alone. Under an evaluation-oriented definition, reasoning requires selecting intermediate steps and halting according to input-dependent conditions, which we formalize as a search-like procedure. We show that single forward passes in scalable architectures are structurally limited in their ability to realize such variable-depth computation, motivating intermediate decoding and externalized reasoning traces as appropriate evaluation interfaces. Central to our argument is that final-answer accuracy alone is an insufficient measure of reasoning, because it provides little ability to diagnose or debug the underlying processes that produce individual solutions in frontier models. We therefore argue for a shift toward process-based evaluation, in which reasoning is assessed through the faithfulness and validity of intermediate reasoning traces as first-class evaluation targets.

Recent advances in agentic harness with orchestration frameworks that coordinate multiple agents with memory, skills, and tool use have achieved remarkable success in complex reasoning tasks. However, the underlying mechanism that truly drives performance remains obscured behind intricate system designs. In this paper, we propose HeavySkill, a perspective that views heavy thinking not only as a minimal execution unit in orchestration harness but also as an inner skill internalized within the model's parameters that drives the orchestrator to solve complex tasks. We identify this skill as a two-stage pipeline, i.e., parallel reasoning then summarization, which can operate beneath any agentic harness. We present a systematic empirical study of HeavySkill across diverse domains. Our results show that this inner skill consistently outperforms traditional Best-of-N (BoN) strategies; notably, stronger LLMs can even approach Pass@N performance. Crucially, we demonstrate that the depth and width of heavy thinking, as a learnable skill, can be further scaled via reinforcement learning, offering a promising path toward self-evolving LLMs that internalize complex reasoning without relying on brittle orchestration layers.

Process reward models (PRMs) require supervision that identifies not only whether a reasoning trajectory is correct, but also where the reasoning process first becomes unsupported by its prefix. We frame this requirement as verifiable counterfactual process supervision with paired correct and erroneous trajectories in which the first invalid transition is known, the error mechanism is controlled, and the downstream continuation remains coherent under the corrupted state. Starting from a verified symbolic reasoning chain, our method injects a template-aware error at a selected intermediate step, recomputes all subsequent steps under the corrupted state, and verifies that the injected step is not derivable from its original prefix. The resulting trajectories provide prefix-valid first-error annotations and are translated into aligned natural-language processes for PRM training and evaluation. Experiments show that the synthesized data improve Best-of-8 reranking on logical reasoning benchmarks and show preliminary transfer to mathematical process evaluation.

Distilling large reasoning models is essential for making Long-CoT reasoning practical, as full-scale inference remains computationally prohibitive. Existing curation-based approaches select complete reasoning traces post-hoc, overlooking collaboration among heterogeneous teachers and lacking dynamic exploration, which leads to redundant sampling and missed complementary reasoning. We introduce CoRD, a collaborative multi-teacher decoding framework that performs step-wise reasoning synthesis guided by predictive perplexity-based scoring and beam search. This enables heterogeneous LRMs to jointly construct coherent reasoning trajectories while efficiently preserving diverse, high-potential hypotheses. Experiments show that CoRD produces higher-quality reasoning data and achieves near teacher-level student performance with fewer, structured supervision signals, without substantial efficiency overhead. CoRD further generalizes well to out-of-domain and open-ended settings. The dataset and model are available at \href{https://github.com/DISL-Lab/CoRD}{https://github.com/DISL-Lab/CoRD}.

Specification gaming is a critical failure mode of LLM agents. Despite this, there has been little systematic research into when it arises and what drives it. To address this, we build and open source a diverse suite of tasks where models can score highly by taking unintended actions. We find that all tested models exploit their specifications at non-negligible rates in most of our eight settings, including five non-coding settings. We see the highest rates of specification gaming in Grok 4 and the lowest rates in Claude models. We use our evaluation suite to study what drives specification gaming, and find that: 1. RL reasoning training substantially increases the rate at which models exploit their specifications, 2. Increasing RL reasoning budget has a weakly positive effect on exploit rate, and 3. Test-time mitigations reduce but do not eliminate the rate of specification gaming. Our results suggest that specification gaming is a fundamental challenge arising from RL reasoning training; we release our evaluation suite to support further work on this problem.

Recent diffusion large language models (dLLMs) have demonstrated both effectiveness and efficiency in reasoning via a block-based semi-autoregressive generation paradigm. Despite their progress, the fixed-size block generations remain a critical bottleneck for effective and coherent reasoning. 1. From a global perspective, different reasoning tasks would correspond to different optimal decoding block sizes, which makes a ``one-size-fits-all'' assumption ineffective. 2. Even within a single reasoning task, the rigid block partitioning would break the logical flow and reduce reasoning coherence. Through empirical observations, we reveal that for block-wise entropy, incorrect reasoning exhibits a fluctuating and unsteady trend between blocks, whereas the correctly generated tasks follow a consistent descending trend. Therefore, this paper proposes b1, a novel post-training framework for dLLMs that learns dynamic-size reasoning blocks via a Monotonic Entropy Descent objective with reinforcement learning to enhance reasoning coherence.b1 integrates seamlessly as a plug-and-play module with existing dLLM's post-training algorithms. Extensive experiments across various reasoning benchmarks showcase b1's consistent improvement over existing fixed-size block baselines. Our code has been released at https://github.com/YanJiangJerry/Block-R1.

Mathematical reasoning is a key benchmark for large language models. Reinforcement learning is a standard post-training mechanism for improving the reasoning capabilities of large language models, yet performance remains sensitive to the design of the reward function that drives policy optimization. This paper introduces a search-driven framework that treats the reward specification itself as an object of optimization. The setting of interest is one in which the base model is held fixed and the reward specification is the primary remaining design lever. Candidate reward functions are generated by a frontier language model, validated automatically, screened through 500-step Group Relative Policy Optimization (GRPO) training runs on a Llama-3.2-3B-Instruct base model with Low-Rank Adaptation (LoRA), and ranked by F1 on the GSM8K test set. Ranked summaries from prior rounds are then fed back into the next round of generation. Over five rounds, the search produces 50 candidate rewards. The mean F1 rises from 0.596 in Round 1 to 0.632 in Round 5, and the top individual reward reaches F1 = 0.787. Seven ensemble configurations of top-ranked rewards are evaluated. The best ensemble achieves F1 = 0.795 (95% bootstrap CI [0.756, 0.832]) and accuracy 0.660 [0.635, 0.686], a 0.19 absolute F1 gain over a base-rewards-only GRPO baseline (F1 = 0.609). Pairwise McNemar tests with Bonferroni correction show all five-or-more-reward configurations are statistically indistinguishable at α = 0.05/21. A three-seed re-training of the best ensemble yields F1 of 0.785. A randomly drawn 5-reward control collapses to F1 = 0.047, which shows that the ranked-feedback loop, not the additive signal of having more rewards, drives the gain.

We study how to improve a frozen pretrained language model with a small amount of adaptive extra computation. A simple approach is to add additional refinement steps on top of the backbone hidden states, but fixed extra refinement can be wasteful: a one-step refinement head may be too weak, while forcing a second full-sequence refinement step everywhere can increase compute without improving transfer. We introduce HALO, a hybrid adaptive latent-refinement method that combines a coarse refinement stage with selective second-stage latent refinement on a subset of tokens chosen by token scoring and monotonic token halting. On the main public benchmark comparison built from MMLU-Pro and GPQA-Diamond, HALO achieves the best overall average among the paper-facing methods, outperforming the frozen backbone, fixed-1, and fixed-2. Internal analysis further shows that HALO reaches nearly the same token-accuracy level as fixed-2 while using fewer average applied refine steps than fixed-1 and far fewer than fixed-2. These results suggest that the key advantage is not simply more refinement, but a better allocation of refinement: HALO achieves the strongest paper-facing result while also using less measured controller compute than either fixed baseline.

Static benchmarks for LLMs are increasingly compromised by contamination and overfitting especially on knowledge intensive reasoning tasks While recent dynamic benchmarks can alleviate staleness they often increase difficulty at the expense of answerability and controllability In this paper we propose StressEval a failure driven data synthesis framework that turns observed model failures into dynamic challenging and controllable test instances StressEval consists of three stages first it constructs a semi structured difficulty card that identifies the failed reasoning step and its root cause second it applies a dual perspective instance synthesis method that targets both knowledge gaps and reasoning breakdowns while preserving the underlying difficulty factors and third it applies a gating mechanism to retain only grounded unambiguous instances Seeding from multiple knowledge intensive reasoning datasets we employ StressEval to build Dynamic OneEval a focused suite of challenging dynamic benchmark Across several state of the art LLMs Dynamic OneEval yields substantially larger performance drops than the original benchmarks while retaining explicit difficulty factors enabling more actionable iteration

Multimodal large language models (MLLMs) have shown considerable potential in chart understanding and reasoning tasks. However, they still struggle with high information density (HID) charts characterized by multiple subplots, legends, and dense annotations due to three major challenges: (1) limited fine-grained perception results in the omission of critical visual cues; (2) redundant or noisy visual information undermines the performance of multimodal reasoning; (3) lack of adaptive deep reasoning relative to the amount of visual information. To tackle these challenges, we present a novel focus-driven fine-grained chart reasoning model, Chart-FR1, to improve perception, focusing efficiency, and adaptive deep reasoning on HID charts. Specifically, we propose Focus-CoT, a visual focusing chain-of-thought that enhances fine-grained perception by explicitly linking reasoning steps to key visual cues, such as local image regions and OCR signals. Building on this, we introduce Focus-GRPO, a focus-driven reinforcement learning algorithm with an information-efficiency reward that compresses redundant visual information for efficient focusing, and an adaptive KL penalty mechanism that enables flexible control over reasoning depth as more visual cues are discovered. Furthermore, to fill the gap in benchmarks for HID charts, we build HID-Chart, a challenging benchmark with an information-density metric designed to evaluate fine-grained chart reasoning capabilities. Extensive experiments on multiple chart benchmarks demonstrate that Chart-FR1 outperforms state-of-the-art MLLMs in chart understanding and reasoning. Code is available at https://github.com/phkhub/Chart-FR1.

Large Language Models (LLMs) have substantially advanced the field of Natural Language Processing (NLP), achieving state-of-the-art performance across a wide range of tasks. These improvements have been attributed, in part, to their emerging reasoning capabilities, which are enabled by large-scale training and increased model capacity. However, existing LLMs can generate erroneous responses when addressing complex queries that fall outside their training distribution, due to limited internal knowledge or the need for multi-step reasoning. To address these limitations, recent work has introduced large reasoning models (LRMs), which incorporate explicit internal reasoning processes to improve response accuracy. Additionally, state-of-the-art LRMs often comprise hundreds of billions of parameters and require several seconds per inference, even on advanced multi-GPU systems. These characteristics limit their practicality for deployment in conventional computing environments. Meanwhile, NLP research on multilingual LLMs continues to prioritize high-resource languages. However, these models exhibit limited performance in under-resourced languages, primarily due to insufficient language- and culture-specific training data. In this paper, we focus on Modern Greek, for which only a limited number of question answering (QA) datasets have been proposed, most of which are intended for model evaluation. To address this research gap in Greek QA, we make the following contributions: (i) CulturaQA, a high-quality LRM-generated and human-curated dataset, for Greek LLM training and evaluation; (ii) a memory-efficient LLM evaluation framework adaptable to diverse languages and QA tasks; (iii) Maistros 8B, a state-of-the-art open-weights Greek LLM developed via knowledge distillation and fine-tuning on CulturaQA; and (iv) a comprehensive evaluation of nine LLMs across nine human-curated Greek QA datasets.

Large reasoning models (LRMs) generate extended solutions, yet it remains unclear whether these traces reflect substantive internal computation or merely verbosity and overthinking. Although recent hidden-state analyses suggest that internal representations carry correctness-related signals, their coarse aggregations may obscure the token and layer structure underlying reasoning computation. We investigate hidden-state transitions across decoding steps and layers, and identify a distinct spatiotemporal pattern in LRMs: successful trajectories exhibit broad temporal dynamics with localized layer-wise concentration, while this structure is weaker in non-reasoning models and knowledge-heavy domains. We formalize this characteristic as Spatiotemporal Amplitude of Latent Transition (StALT), a training-free trajectory statistic that summarizes temporal changes between adjacent tokens weighted by within-token layer saliency. Across diverse models and benchmarks, StALT reliably separates correct from incorrect trajectories in reasoning-intensive regimes, providing a competitive label-free correctness signal alongside strong output-space and length-based baselines. Intervention analyses further show that this spatiotemporal amplitude responds systematically to manipulations that increase or reduce the demand for internal reasoning, supporting its association with latent reasoning dynamics in LRMs. These findings provide empirical evidence that LRMs exhibit measurable hidden-state dynamics and offer a practical probe for understanding internal computation beyond output-based evaluation.

Large Reasoning Models achieve strong performance on complex tasks but remain prone to hallucinations, particularly in long-form generation where errors compound across reasoning steps. Existing approaches to improving factuality, including abstention and factuality-driven optimization, follow a \emph{coupled exploration-commitment} paradigm, in which intermediate reasoning is unconditionally propagated to the final output, limiting fine-grained control over information selection and integration. In this paper, we propose an \textbf{Exploration-Commitment Decoupling} paradigm that disentangles knowledge exploration from final commitment, enabling models to explore with awareness while answering cautiously. We instantiate the paradigm with \textbf{Calibration-Aware Generation (CAG)}, a framework that equips models with end-to-end, calibration-aware generation capabilities, by augmenting intermediate reasoning with calibrated reliability estimates and prioritizing reliable content in final outputs. Across five long-form factuality benchmarks and multiple model families, CAG improves factuality by up to 13%, while reducing decoding time by up to 37%. Overall, our work highlights decoupling as a principled approach for more reliable long-form generation, offering directions for trustworthy and self-aware generative systems.

When copies of the same language model are prompted to debate, they produce diverse phrasings of one perspective rather than diverse perspectives. Multi-agent debate (MAD), and more broadly closed-system reasoning where agents iteratively transform each other's outputs, tends to preserve answer accuracy while degrading the reasoning behind those answers. We name the multi-agent case the Debate Trap and the broader phenomenon the Reasoning Trap, offering a programmatic theory of evidence-grounded reasoning failure.The framework has three parts: (i) SFS (Supported Faithfulness Score), a claim-level metric verifying decomposed atomic claims against provided evidence (decomposer-invariant rankings: Spearman rho=1.0); (ii) EGSR (Evidence-Grounded Socratic Reasoning), replacing adversarial argumentation with evidence-grounded inquiry; (iii) Theorem 1 (DPI Bound): under standard MAD, the chain E -> O^0 -> O^1 -> ... is Markov, and the Data Processing Inequality implies E[I(E;O^{t+1})] <= E[I(E;O^t)]. Three companion results -- open-system recovery (Theorem 2), EGSR accumulation (Lemma 2), and vote-aggregation floor (Proposition 1) -- partition multi-step LLM reasoning by its information-theoretic relationship to E. Across 16 conditions on SciFact (300 claims) and FEVER (1,000 claims), DebateCV (C13) preserves 88% of baseline accuracy while SFS drops 43%; majority-vote MAD (C15) reduces SFS to 1.7% of baseline (p < 10^{-6}, d = -0.96); EGSR recovers 98%. An R6 cohort study (Korean n=10x30 FEVER; English n=3x200 SciFact) finds inter-rater Fleiss kappa <= +0.018 with 0.8-1.4 Likert intra-rater shifts across language and domain -- the human agreement that faithfulness metrics have been calibrated against is not itself stable. We offer one falsifiable conjecture: any closed-system reasoning protocol preserving Theorem 1's Markov structure is, in expectation, subject to the same DPI bound.

Vision-Language Models (VLMs) typically rely on static initial frames for video reasoning, restricting their ability to incorporate essential dynamic information as the reasoning process evolves. Existing methods that augment Chain-of-Thought (CoT) with additional frame information often exhibit suboptimal CoT quality and lack the crucial ability to synthesize visual information for hypothetical or counterfactual scenarios. We introduce Act-to-See (Act2See), a novel framework that enables active visual perception by empowering VLMs to actively interleave video frames within text CoTs. Act2See is developed via Supervised Fine-Tuning (SFT) on a high-quality dataset of reasoning traces generated by a frontier VLM. These traces integrate active calls to either retrieve existing frames or generate new ones, and are rigorously verified against human-annotated CoTs to ensure quality. This approach cultivates an emergent capability: at inference time, the model actively determines when to search for or synthesize the necessary visual evidence. Act2See establishes new state-of-the-art results on challenging benchmarks, including VideoEspresso and ViTIB, and outperforms comparable or larger models on Video-MME, EgoNormia, and VCR-Bench, demonstrating an advancement in enabling VLMs with active visual perception for video reasoning.

Advances in inference methods have enabled language models to improve their predictions without additional training. These methods often prioritize raw performance over cost-effective compute usage. However, computational efficiency is key for real-world applications with resource constraints. We provide a systematic analysis of the inference scaling strategies self-consistency, self-refinement, multi-agent debate, and mixture-of-agents, to study their computational performance tradeoffs. We evaluate methods on two reasoning benchmarks (MMLU-Pro, BBH) and include extensive parameter configurations (e.g., scaling the number of parallel predictions, agents, and debate rounds) across different model sizes. Across 34 configurations and over 100 evaluations, we compute the Pareto-optimal front to select methods that achieve the best accuracy with the lowest computational budget. Notably, inference scaling improves accuracy by up to +7.1% points over chain-of-thought at the highest evaluated budgets (20x the CoT compute budget) on MMLU-Pro. With an equal computing budget, debate and mixture-of-agents outperform self-consistency by 1.3% and 2.7% points, respectively. While self-consistency saturates earlier, multi-agent gains persist, particularly on more complicated tasks. We identify a simple multi-agent design guideline: mixture-of-agents is most efficient when the number of parallel generations exceeds the number of sequential aggregations.

Multi-Hop Fact Verification requires complex reasoning across disparate evidence, posing significant challenges for Large Language Models , which may suffer from hallucinations and fractured logical chains. Existing methods, while improving transparency via Chain-of-Thought , often lack explicit modeling of the structural dependencies between evidence and claims. In this work, we introduce an SCM-inspired framework that grounds reasoning in explicit directed dependency graphs, treating verification as a constructive structural reasoning process rather than full causal inference with interventions or counterfactual semantics. We empirically identify an "inverted U-shaped" correlation between reasoning-chain length and accuracy, revealing that excessive structural complexity can degrade performance. To address this, we propose a rule-based reinforcement learning strategy using Group Relative Policy Optimization. This approach dynamically optimizes the trade-off between structural depth and conciseness. Extensive experiments on HoVer and EX-FEVER demonstrate that our SCM-GRPO framework outperforms strong baselines while producing more traceable reasoning structures for complex fact verification.

Predicting future clinical outcomes from electronic health records (EHR) remains challenging due to the complexity and heterogeneity of patient data. LLMs have shown strong potential for such predictive tasks, yet existing approaches mainly focus on enhancing medical knowledge through distillation or RAG while relying on the model's internal ability to interpret contextual information. In this work, we present ReMedi (Reasoner for Medical Clinical Prediction), a framework for improving clinical outcome prediction from EHR. ReMedi generates rationale-answer pairs using a challenging sample regeneration mechanism for complex clinical questions, which leverages ground-truth answers as hints to enhance reasoning for further fine-tuning and preference tuning. ReMedi integrates ground-truth outcome guidance into the preference data construction loop, regenerating rationale-answer variants. By tuning on these rationale-answer pairs, the model improves its predictive performance. Experiments on multiple EHR prediction tasks demonstrate substantial gains of up to 19.9 percent over state-of-the-art baselines in terms of F1 score, underscoring ReMedi's effectiveness in real-world clinical prediction.

There has been a growing interest in explaining entailments over description logic (DL) knowledge bases. The existing explanation formalisms focus on justifications to explain true axioms, and abductive reasoning to explain missing axioms in a knowledge base. However, these formalisms only point out the reasoning steps behind a (missing) entailment and lack a user-centered approach as they do not consider an inquirer's needs, level of understanding, or prior knowledge. We propose contrastive explanations, aiming at answering "why an axiom P (fact) is true instead of another axiom Q (foil)" over description logic knowledge bases. The motivation arises from the observation that when a user discovers that P has occurred, they are often surprised because they anticipated the occurrence of another similar event Q. Furthermore, individual explanations for "why P" and "why not Q" are unsatisfactory since a user expects to see the difference between P and Q. In this work, we first present formal foundations of contrasting questions and then define contrastive explanations within description logics. To this end, facts include ABox assertions of the form C(x) for a concept C and individual x. Possible foils for such facts are assertions C(y) (contrasting against an individual y), or D(x) (contrasting against a concept D). Additionally, we explore the properties of contrastive explanations in the DL EL and ALC. We also provide an implementation of our definition and an experimental evaluation on KBs of varying sizes.

Reasoning in large language models is predominantly evaluated through labeled benchmarks, conflating task performance with the quality of internal inference. Here we study reasoning as an intrinsic dynamical process by examining the evolution of internal representations during inference. We find that inference-time dynamics consistently self-organize into low-dimensional manifolds embedded within high-dimensional representation spaces. we find that such geometric compression, although pervasive, is not sufficient for stable or reliable reasoning. Instead, effective reasoning dynamics emerge within a constrained structural regime characterized by three conditions: adequate representational expressivity, spontaneous manifold compression, and preservation of non-degenerate information volume within the compressed subspace. Models outside this regime exhibit characteristic pathological inference dynamics. Based on these insights, we introduce a unified, label-free diagnostic computed solely from internal dynamics. These findings suggest that reasoning in LLMs is fundamentally governed by geometric and informational constraints, offering a complementary framework to benchmark-centric assessment.

Although reinforcement learning (RL) has significantly advanced reasoning capabilities in large multimodal language models (MLLMs), its efficacy remains limited for lightweight models essential for edge deployments. To address this issue, we leverage causal analysis and experiment to reveal the underlying phenomenon of perceptual bias, demonstrating that RL-based fine-tuning compels lightweight models to preferentially adopt perceptual shortcuts induced by data biases, rather than developing genuine reasoning abilities. Motivated by this insight, we propose VideoThinker, a causal-inspired framework that cultivates robust reasoning in lightweight models through a two-stage debiasing process. First, the Bias Aware Training stage forges a dedicated "bias model" to embody these shortcut behaviors. Then, the Causal Debiasing Policy Optimization (CDPO) algorithm fine-tunes the primary model, employing an innovative repulsive objective to actively push it away from the bias model's flawed logic while simultaneously pulling it toward correct, generalizable solutions. Our model, VideoThinker-R1, establishes a new state-of-the-art in video reasoning efficiency. For same-scale comparison, requiring no Supervised Fine-Tuning (SFT) and using only 1 of the training data for RL, it surpasses VideoRFT-3B with a 3.2% average gain on widely-used benchmarks and a 7% lead on VideoMME. For cross-scale comparison, it outperforms the larger Video-UTR-7B model on multiple benchmarks, including a 2.1% gain on MVBench and a 3.8% gain on TempCompass. Code is available at https://github.com/falonss703/VideoThinker.

Currently, process reward models (PRMs) have exhibited remarkable potential for test-time scaling. Since large language models (LLMs) regularly generate flawed intermediate reasoning steps when tackling a broad spectrum of reasoning and decision-making tasks, PRMs are required to possess capabilities for detecting process-level errors in real-world scenarios. However, existing benchmarks primarily focus on mathematical reasoning, thereby failing to comprehensively evaluate the error detection ability of PRMs across diverse reasoning scenarios. To mitigate this gap, we introduce GR-Ben, a process-level benchmark specifically designed for assessing PRM's performance across two primary reasoning domains (science and logic) and nine subdomains. We conduct extensive experiments on a diverse set of 22 models, encompassing both PRMs and LLMs, and derive two key findings: (1) In domains beyond mathematical reasoning, the error-detection ability of existing PRMs and LLMs is found to be markedly weaker by comparison.(2) In general, PRMs are less adept at identifying knowledge-based errors, whereas LLMs exhibit poorer performance in detecting computational errors. We hope GR-Ben can foster future researches on PRMs for general domains, thereby enhancing the reasoning capabilities of LLMs.

This position paper argues that LLMs should not yet be credited with decision explanation. This matters because recent work increasingly treats accurate behavioral prediction, plausible rationales, and outcome-conditioned reasoning traces as evidence that LLMs explain why people decide as they do, risking a premature redefinition of what counts as explanatory progress in human decision modeling. We first distinguish three claims with different evidential burdens: decision prediction, rationale generation, and decision explanation. We then argue that the evidence most commonly offered for LLM-based decision accounts directly supports the first two claims, and sometimes explanatory hypothesis generation, but does not distinguish decision explanation from prediction-supportive rationalization. Next, we propose a bridge standard for decision-explanation credit: stronger claims should specify explanatory targets, discriminate against weaker rationalizer alternatives, use target-appropriate process- or intervention-sensitive validation, and bound their scope. We then situate this standard against competing views and related literatures, clarifying why it preserves the value of LLMs as predictors, narrators, and hypothesis generators while resisting premature explanatory credit. We conclude with a principle of credit calibration: LLMs should be credited for the strongest claim their evidence warrants, and no stronger; if adopted, this principle can help turn LLMs from persuasive narrators of decisions into more reliable instruments for discovering, testing, and communicating explanations of human behavior.

The dominant noun-based modeling paradigm, grounded in probability theory and committed to pre-specified noun entities as primitive modeling units, is insufficient as a \emph{grammar of thought}: It leaves \emph{timing} outside the computational scope, precluding any adequate representation of the future as an open space of possibilities. This paper addresses three conceptual gaps absent from the existing literature: (1) possibility space -- a framework admitting multiple possible timelines for the same event; (2) timing computation -- the treatment of timing as a computable rather than observed dimension; and (3) causal factum -- the maximal causal efficacy recovered by reasoning backward from possible futures, rather than assumed in advance. Together, these definitions dissolve the confounding problem inherent to noun-based causal inference and provide the foundation for a spontaneously growing causal-reasoning world model. As proof of concept, we instantiate the framework and apply it to longitudinal EHR data from 3,276 breast cancer patients, demonstrating for the first time, to our knowledge, automatic trajectory discovery and counterfactual timing deduction (i.e., a What-If Machine) in a purely data-driven manner.

In this work, we introduce DUET (Dual-model Efficient Two-stage inference), a collaborative inference framework in which a capable model and a lightweight model work together to solve a task. Relying on a single large model to perform end-to-end reasoning and prediction often incurs substantial inference cost. In contrast, DUET decomposes inference into two stages: the capable model produces a reasoning signal, and the lightweight model interprets this signal to generate the final answer, allowing reasoning-intensive computation to be handled by the capable model while non-reasoning-intensive components are delegated to the lightweight model without sacrificing task performance. To achieve this objective, we propose a length-penalized joint training objective that encourages the capable model to transmit only the information that is sufficient for the lightweight model to solve the task. As a result, DUET maintains strong reasoning performance with substantially lower inference cost than end-to-end inference using a large model alone, saving up to 60% of the large model's output tokens on challenging reasoning benchmarks, including AIME and GPQA.

Large language models (LLMs) often achieve strong performance on reasoning benchmarks, but final-answer accuracy alone does not show whether they faithfully execute the procedure specified in a prompt. We introduce a controlled diagnostic benchmark for procedural execution, where models are given a step-wise arithmetic procedure and two numeric inputs, and must return the final computed value. Complexity is varied through procedure length and look-back dependencies over intermediate variables. Average first-answer accuracy drops from 63% on 5-step procedures to 20% on 95-step procedures. Generation-level analysis shows that failures often involve missing answers, premature answers, self-correction after an initial error and under-executed traces. These findings suggest that apparent reasoning ability can mask substantial weaknesses in faithful long-horizon procedural execution.

Reasoning language models often generate long chain-of-thought (CoT), which accumulates a massive KV cache during the decoding phase and incurs high decoding latency and limited throughput. To address these issues, KV cache compression has emerged as a promising technique for reducing memory overhead by selectively removing unimportant KV pairs while preserving useful ones for subsequent decoding. Nevertheless, we identify two key limitations in existing KV cache compression methods: 1) their threshold-triggered compression policy may provide limited throughput improvement or even reduce throughput, and may fully eliminate KV pairs from certain blocks of the sequence, potentially worsening information loss. 2) they typically retain either isolated KV pairs or fixed-size chunks with rigid boundaries, failing to preserve important flexible-sized chunks at arbitrary token positions. To overcome these limitations, we propose Kara, a sliding-window KV cache compression method that performs decoding-time compression by operating only on the recently generated context. Kara leverages bidirectional attention to score and select informative KV pairs in the window. To enable flexible preservation of important semantic information, we design a Token2Chunk module to expand a subset of selected KV pairs into chunks. Furthermore, we adapt Kara to PagedAttention and develop KvLLM, an inference framework built upon vLLM, which reduces KV cache memory usage and effectively improves output throughput. Extensive experiments demonstrate consistent performance improvements of proposed Kara and KvLLM.

Large language models (LLMs) are becoming increasingly capable mathematical collaborators, but static benchmarks are no longer sufficient for evaluating progress: they are often narrow in scope, quickly saturated, and rarely updated. This makes it hard to compare models reliably and track progress over time. Instead, we need evaluation platforms: continuously maintained systems that run, aggregate, and analyze evaluations across many benchmarks to give a comprehensive picture of model performance within a broad domain. In this work, we build on the original MathArena benchmark by substantially broadening its scope from final-answer olympiad problems to a continuously maintained evaluation platform for mathematical reasoning with LLMs. MathArena now covers a much wider range of tasks, including proof-based competitions, research-level arXiv problems, and formal proof generation in Lean. Additionally, we maintain a clear evaluation protocol for all models and regularly design new benchmarks as model capabilities improve to ensure that MathArena remains challenging. Notably, the strongest model, GPT-5.5, now reaches 98% on the 2026 USA Math Olympiad and 74% on research-level questions, showing that frontier models can now comfortably solve extremely challenging mathematical problems. This highlights the importance of continuously maintained evaluation platforms like MathArena to track the rapid progress of LLMs in mathematical reasoning.

The rapid spread of memes makes harmful content detection increasingly crucial, as effective identification can curb the circulation of misinformation. However, existing methods rely heavily on high-volume annotated data, which leads to substantial training costs and limited generalization. To address these challenges, we propose PrismAgent, a zero-shot, multi-agent, interpretable framework. PrismAgent conceptualizes this task as a criminal case investigation, employing four specialized agents responsible for the analysis, investigation, prosecution, and judgment stages within a structured collaborative workflow. In the first stage, the analyst agent paraphrases each meme under benevolent and malicious assumptions to probe its underlying intent. The investigator agent then retrieves supporting evidence from an unannotated dataset and constructs contextual interpretations for the meme and its variants. Next, the prosecutor agent performs three independent preliminary judgments by pairing the original meme with each of the three interpretations. Finally, the judge agent deliberates across all evidence to render a final verdict. Moreover, PrismAgent's explicit multi-stage reasoning chain makes the model inherently interpretable, as every intermediate step is explicitly explained rather than only producing a final detection result. Extensive experiments on three public datasets show that PrismAgent significantly outperforms existing zero-shot detection methods.

Long-horizon robotic manipulation requires plans that are both logically coherent and geometrically grounded. Existing Vision-Language-Action policies usually hide planning in latent states or expose only one modality: text-only chain-of-thought encodes causal order but misses spatial constraints, while visual prediction provides geometric cues but often remains local and semantically underconstrained. We introduce Interleaved Vision--Language Reasoning (IVLR), a policy framework built around \trace{}, an explicit intermediate representation that alternates textual subgoals with visual keyframes over the full task horizon. At test time, a single native multimodal transformer self-generates this global semantic-geometric trace from the initial observation and instruction, caches it, and conditions a closed-loop action decoder on the trace, original instruction, and current observation. Because standard robot datasets lack such traces, we construct pseudo-supervision by temporally segmenting demonstrations and captioning each stage with a vision-language model. Across simulated benchmarks for long-horizon manipulation and visual distribution shift, \method{} reaches 95.5% average success on LIBERO, including 92.4% on LIBERO-Long, and 59.4% overall success on SimplerEnv-WidowX. Ablations show that both modalities are necessary: without traces, LIBERO-Long success drops to 37.7%; text-only and vision-only traces reach 62.0% and 68.4%, while the full interleaved trace reaches 92.4%. Stress tests with execution perturbations and masked trace content show moderate degradation, suggesting that the trace can tolerate local corruption and moderate execution drift, but remains limited under stale or incorrect global plans.

Reinforcement Learning with Verifiable Rewards (RLVR) enhances reasoning of Large Language Models (LLMs) but usually exhibits limited generation diversity due to the over-incentivization of positive rewards. Although methods like Negative Sample Reinforcement (NSR) mitigate this issue by upweighting penalty from negative samples, they may suppress the semantic distributions shared between positive and negative responses. To boost reasoning ability without losing diversity, this paper proposes negative sample projection Residual Reinforcement Learning (ResRL) that decouples similar semantic distributions among positive and negative responses. We theoretically link Lazy Likelihood Displacement (LLD) to negative-positive head-gradient interference and derive a single-forward proxy that upper-bounds representation alignment to guide conservative advantage reweighting. ResRL then projects negative-token hidden representations onto an SVD-based low-rank positive subspace and uses projection residuals to modulate negative gradients, improving reasoning while preserving diversity and outperforming strong baselines on average across twelve benchmarks spanning Mathematics, Code, Agent Tasks, and Function Calling. Notably, ResRL surpasses NSR on mathematical reasoning by 9.4% in Avg@16 and 7.0% in Pass@128. Code is available at https://github.com/1229095296/ResRL.git.

Animal-welfare advocates produce a lot of writing, and increasingly that writing trains the language models that millions of people then ask about animal welfare. Using vocabulary-matched stance-contrast probes on a held-out animal-welfare benchmark, we measure how each of ten linguistic features changes Llama-3.2-1B's preference for pro-animal-welfare reasoning when used as fine-tuning data. Eight of the ten features produce statistically significant shifts. Seven move the model toward stronger pro-animal-welfare reasoning: assertive certainty, explicit moral vocabulary, emotion words, evaluative claims, narrative structure, depicted harm severity, and immediate temporal framing. Two move it the other way: hedged language and concrete sensory description both dilute the pro-animal-welfare stance. First-person perspective has no statistically significant effect. The practical recommendation for anyone writing animal-welfare text that may end up in LLM training corpora: assert a position rather than describe a scene neutrally. The features that shift the model are the ones that make the writer's position explicit; the features that dilute it hold animal-welfare content but withhold stance.

The inception of Large Language Models (LLMs) has catalyzed AI adoption in the finance sector, yet their reliability in complex, jurisdiction-specific tasks like Indian Chartered Accountancy (CA) remains limited. The models display difficulty in executing numerical tasks which require multiple steps while also needing advanced knowledge about legal regulations and the method of scaling their operations is not feasible in settings which have limited access to resources. We present CA-ThinkFlow as a parameter-efficient Retrieval-Augmented Generation (RAG) framework which operates with a 14B, 4-bit-quantized reasoning model, 14B-DeepSeek-R1, and a layout-aware Docling extraction system which maintains document structure during extraction. CA-ThinkFlow uses a basic RAG method which automatically adds retrieved information into the prompt, while it depends on the model's built-in Chain-of-Thought (CoT) functions to create context and produce correct answers. The system we developed system operates at performance levels which match large proprietary models when we tested it on the multi-level CA-Ben benchmark, achieving Scholastic Reliability Coefficient (SRC) results which equal 68.75% of GPT-4o and Claude 3.5 Sonnet. The framework shows high efficiency and strength in handling parameters, but essential reasoning abilities fail to process complex regulatory texts which exist in fields such as Taxation.

Current transformers discard their rich latent residual stream between positions, reconstructing latent reasoning context at each new position and leaving potential reasoning capacity untapped. The State Stream Transformer (SST) V2 enables parameter-efficient reasoning in continuous latent space through an FFN-driven nonlinear recurrence at each decoder layer, where latent states are streamed horizontally across the full sequence via a learned blend. This same mechanism supports continuous latent deliberation per position at inference time, dedicating additional FLOPs to exploring abstract reasoning before committing to a token. A two-pass parallel training procedure resolves the sequential dependency of the recurrence to allow compute-efficient training. Hidden state analysis shows the state stream facilitates reasoning through exploration of distinct semantic basins in continuous latent space, where transitions at content-dependent positions move the model into a substantially different Bayesian posterior, directly influencing the latent space at future positions. We also find, via a learned probe, that at the first generated token position, the latent state already predicts whether the eventual answer will survive or break under additional latent computation for every subsequent position. Co-trained into an existing 27B backbone using only a small dataset of GSM8K examples, the SST delivers a +15.15 point gain over a fine-tuning-matched baseline on out-of-distribution GPQA-Diamond and cuts that same baseline's remaining GSM8K errors by 46%, together showing that the reasoning improvement is attributable to the architectural mechanism rather than scale or training data. On GPQA-Diamond, the resulting 27B SST also achieves higher accuracy than several larger open-weight and proprietary systems, including open-weight models up to 25 times larger.

When a language model answers a table question, users have no way to verify which cells informed which reasoning steps. We introduce RSAT, a method that trains small language models (SLMs, 1-8B) to produce step-by-step reasoning with cell-level citations grounded in table evidence. Phase 1 (SFT) teaches a structured JSON output format from verified reasoning traces. Phase 2 (GRPO) optimizes a composite reward centered on NLI-based faithfulness, alongside citation validity and parsimony. Across six models from two families-Qwen 2.5 (1.5B/3B/7B) and Llama 3 (1B/3B/8B)-RSAT improves faithfulness 3.7$\times$ over SFT alone (0.224$\rightarrow$0.826), with near-perfect citation validity (0.992). Post-hoc attribution collapses below 13% format success, confirming that attribution must be integrated into reasoning, not retrofitted. Ablations show the faithfulness reward is essential: removing it drops faithfulness from 0.97 to 0.03.

Robotic foundation models require reasoning over complex visual scenes to execute adaptive actions in dynamic environments. While recent studies on latent-reasoning Vision-Language-Action (VLA) models have demonstrated the capability to capture fine-grained physical dynamics, they remain predominantly confined to static imitation learning, severely limiting their adaptability and generalization. In this paper, we present LaST-R1, a novel reinforcement learning (RL) post-training framework designed to effectively harness "latent reasoning-before-acting" policies. Specifically, we propose Latent-to-Action Policy Optimization (LAPO), a core RL algorithm that jointly optimizes the latent reasoning process and the action generation. By explicitly embedding latent Chain-of-Thought (CoT) reasoning directly within the RL optimization loop, LAPO stimulates profound physical world modeling, which in turn drives robust execution in interactive environments. Furthermore, an adaptive latent CoT mechanism is introduced, allowing the policy to dynamically modulate its reasoning horizon based on diverse environment states. Experiments show that LaST-R1 achieves a near-perfect 99.9% average success rate on the LIBERO benchmark with only one-shot supervised warm-up, significantly improving convergence speed and performance over prior state-of-the-art (SOTA) methods. In real-world deployments, LaST-R1 yields up to a 22.5% average improvement over SOTA supervised fine-tuning approach across four complex tasks, including both single-arm and dual-arm settings. Finally, LaST-R1 demonstrates strong generalization across simulated and real-world environments.

Recent advances in large language models (LLMs) have increasingly relied on reinforcement learning (RL) to improve their reasoning capabilities. Three types of approaches have been widely adopted: The first relies on a deep neural network to estimate the value function of the learning policy in order to reduce the variance of the policy gradient. However, estimating and maintaining such a value network incurs substantial computational and memory overhead. The second avoids training a value network by approximating the value function using sample averages. However, it samples a large number of reasoning traces per prompt for accurate value function approximation, making it computationally expensive. The third samples only a single reasoning trajectory per prompt, which reduces computational cost but suffers from poor sample efficiency. This paper focuses on a practical, resource-constrained setting in which only a small number of reasoning traces can be sampled per prompt, while low-variance gradient estimation remains essential for high-quality policy learning. To address this challenge, we bring classical nonparametric statistical methods, which are both computationally and statistically efficient, to LLM reasoning. We employ kernel smoothing as a concrete example for value function estimation and the subsequent policy optimization. Numerical and theoretical results demonstrate that our proposal achieves accurate value and gradient estimation, leading to improved policy optimization.