Chain-Of-Thought Reasoning

In pointwise document reranking, Chain-of-Thought models typically underperform direct scoring models. While existing diagnostics attribute this to inferior classification, score polarization, or calibration breakdown, whether targeted training can bridge this gap remains unclear. Our empirical study first confirms that this gap is stable across scales up to 32B parameters, ruling out model and data capacity confounders. We then apply stress tests utilizing reinforcement learning, fine-grained supervision, and architectural decoupling to explicitly repair these deviations. Although these interventions improve classification accuracy and absolute scores, the relative ranking gap persists. These findings suggest that, within the pointwise scoring paradigm, routing continuous relevance semantics through discrete text constrains ranking signal resolution, revealing a bottleneck that is stable and difficult to overcome under current standard methods, rather than an easily resolvable training bias.

As pretraining scaling laws approach saturation, Test-Time Scaling (TTS) has emerged as an important direction for improving reasoning by allocating inference-time compute to a fixed model prior. Viewed at a high level, TTS reframes inference as search over a space of partial reasoning states. While Chain-of-Thought (CoT) exposes intermediate steps, common instantiations rely on single-trajectory decoding, limiting recovery from early errors and exploration. This survey systematizes recent progress in tree-search-based reasoning, viewing inference as instance-specific optimization rather than decoding. We trace the evolution from uninformed search to Monte Carlo Tree Search (MCTS), highlighting how sampling-based control supports principled exploration-exploitation trade-offs. To unify a fragmented literature, we introduce a Unified Design Space spanning search topology, evaluation signals, and control dynamics, and advocate a standardized compute-reporting abstraction to make compute-accuracy trade-offs explicit and comparable.

Generating multiple diverse and high-quality solutions is valuable for many applications, such as code-test generation and drug discovery. However, Large Language Models (LLMs) tend to converge on a single high-confidence solution during inference, limiting exploration of alternative valid solution paths. Existing test-time methods promote diversity through tree-like search and prune semantically similar branches using response-level semantic embeddings. However, we find that such embeddings are easily confounded by linguistic and stylistic similarities, making it difficult to distinguish genuinely distinct solution paths. To address this, we introduce Answer Probing, which probes the potential answer an LLM would reach from an intermediate reasoning path. We demonstrate that the hidden states of probed answers more effectively differentiate distinct solution paths than semantic embeddings, and the perplexity of probed answers serves as a practical proxy for reasoning correctness. Based on these findings, we propose Answer Probing-Guided Tree Search (APTS), which guides the tree search by the probed answers' hidden state similarity and perplexity. Experiments on three reasoning tasks across two LLMs show that APTS consistently enhances solution diversity, demonstrating its effectiveness and robustness.

Neurosymbolic reasoning has shown promising success in addressing complex reasoning tasks by combining large language models (LLMs) and symbolic solvers. While this approach shows promise, a fundamental challenge remains: improving the accuracy of translations from natural language to logical formulas. Current methods predominantly rely on prompt engineering, which is difficult to scale across different domains and input formats. Drawing inspiration from the success of fine-tuning in other model adaptation and alignment applications, we propose a fine-tuning-based Stratified Consistency Distillation approach: (1) We generate K logical translations per input using a frontier LLM and cluster them by semantic equivalence (2) Based on the entropy level, we apply majority voting (low entropy), LLM-as-a-Judge (medium entropy), or unification/abstention (high entropy), and (3) fine-tune a smaller model using the selected pseudo-labels. Our experiments show significant and consistent improvements in both Pass@K and our novel Equivalent Logical Similarity metrics, demonstrating the potential of advancing logical translation through consistency distillation.

Logical reasoning with large language models (LLMs) is a critical capability, as it reflects a system's ability to correctly deduce hypotheses from a given context using faithful deductive processes. However, LLM reasoning has often been shown to be sensitive to small surface-level variations in problem formulation, raising questions about whether models truly follow the underlying logical structure. Studying this behavior is challenging because the symbolic components of logical problems, such as operators and predicates, are difficult to systematically manipulate in natural language. We introduce a tool-driven framework for generating controlled, label-preserving edits to logical reasoning problems. Our method operates on symbolic representations of first-order logic and constraint satisfaction problem tasks, enabling targeted modifications to logical operators and other structural components before translating them back into natural language. Using this framework, we evaluate various LLMs under cumulative and individual operator edits and analyze their behavior in response to these changes. Our quantitative and qualitative analyses show that LLM reasoning behavior under controlled operator edits is inconsistent, regardless of model size or family: models sometimes adapt correctly to structural changes but often fail to track their logical consequences. The results from this automated stress test enable an evaluation of language models across different dimensions and help measure the reliability of their reasoning.

This paper addresses the problem of translating natural-language routing rules written by business administrators into executable workflow graphs for enterprise contact centers. Each target is a directed acyclic graph (DAG) of conditional actions with parallel branches, hit-first fallback chains, and per-branch Boolean predicates, encoded in the JSON dialect of a commercial routing platform. We show that neuro-symbolic decomposition enables lower-cost, non-reasoning large language models to generate complex workflow DAGs at production-relevant quality without expensive extended-reasoning models. Our central diagnostic is an emission-density bottleneck: on a 635-rule benchmark of manufactured synthetic data, models select the correct graph nodes with high accuracy but increasingly misconfigure attributes and Boolean grouping as the number of interdependent nodes emitted in one pass grows. We therefore move combinatorial graph construction from the model into a deterministic compiler driven by a compact intermediate representation, with a learned registry-selection front end that focuses generation on relevant vocabulary. Across four models, the full system reaches approximately 89% LLM-judge validity, approximately 90% exact-match condition accuracy, and 99-100% valid JSON while using roughly half the per-rule prompt tokens of a monolithic prompt. On GPT-5.3-chat, the method improves judge validity by 24 percentage points and achieves statistical equivalence to a reasoning model's out-of-the-box quality, although an approximately 8-point frontier gap remains. We also present a deployment path and transferable lessons for structured-generation applications.

Korean introduces an additional typographical perturbation level not captured by ordinary character-level edit models: because syllable blocks are internally composed of sub-character units called jamo, keyboard-level errors can occur within a syllable, either producing a valid but semantically altered character or exposing raw jamo on the surface. Both outcomes disrupt sub-word tokenization and are not reliably corrected by existing grammatical error correction pipelines, leaving LLMs directly exposed to corrupted inputs. To quantify this vulnerability, we apply five jamo-level perturbation types to the KMMLU benchmark and evaluate four language models, finding that accuracy declines monotonically with perturbation intensity and that parameter scaling does not confer robustness against intra-syllabic noise. We further show that typo-corrupted inputs induce a distinct shift in internal representations that is not reducible to ordinary answer incorrectness, and that a simple linear probe trained on these representations detects unseen perturbation types with high AUROC. Motivated by this signal, we propose Typo-Aware Chain-of-Thought (TACoT), which routes inputs to chain-of-thought inference only when the probe detects a likely typo, recovering a substantial portion of the CoT accuracy gain at a fraction of the inference cost.

Large Language Models (LLMs) are increasingly used to annotate structured product data in e-commerce, but early deployment often begins as a cold-start problem: only limited pre-launch labels are available, the value of expensive reasoning is unknown, and human review is needed before the system can be trusted at scale. This challenge is especially common in rule-based annotation workflows, where each item must satisfy multiple business rules and both model errors and ambiguous rule boundaries affect final decisions. We introduce the Differential Reasoning Router (DRR), a cost-aware framework for cold-start LLM annotation that jointly optimizes model selection and human escalation. Rather than treating a reasoning model as a default fallback, DRR estimates separate success probabilities for a direct model and a reasoning model at both the sample and business-rule levels, enabling adaptive routing: easy cases are handled directly, reasoning is reserved for cases where it is expected to improve the decision, and likely double-failure or rule-disagreement cases are escalated to human annotators. The resulting labels provide targeted ground truth for prompt engineering, supervised fine-tuning, calibration, and rule refinement, enabling a gradual shift from human-heavy cold-start annotation toward high-confidence automated routing. In a production e-commerce workflow, DRR reaches accuracy parity with the strongest confidence-based router while achieving more than 60% reasoning-token cost savings.

Large Language Models (LLMs) trained on extensive scientific research are increasingly integrated as assistants for scientific discovery. However, most research papers omit the fine-grained cognitive process of examining constraints, failed alternatives, and iterative decisions required to achieve the desired goal. Such cognitive processes are vital for real-world scientists working toward specific goals under constraints. In this paper, we show that LLMs, when trained to produce such cognitive traces, perform better as scientific discovery assistants than when trained solely on scientific literature. We propose COGTRL, a trajectory-level reinforcement learning framework that trains LLMs to emulate cognitively grounded reasoning by jointly optimizing cognitive traces and the scientific steps produced in an interleaved manner. Across two 3B-parameter models and two scientific domains (AI and Materials Science), COGTRL improves method quality by an average of 7.85 points over comparable 3B model baselines and achieves competitive performance relative to 70B parameter models. Moreover, analysis by domain experts shows a preference for methods generated by COGTRL over the baselines.

Large language models (LLMs) achieve strong reasoning performance, which depends critically on inference-time decisions. Yet these decisions are commonly handled by static, one-size-fits-all policies, limiting adaptation to diverse tasks and reasoning stages. Recent adaptive methods partially address this limitation, but they primarily adapt either decoding stochasticity (how the model explores) or reasoning compute (how long the model reasons) in isolation, leaving their interaction within a single reasoning trajectory unmodeled. To address this challenge, we shift toward a within-trajectory joint control view, and instantiate it in AutoCRAT, a decoder-side controller for frozen backbones. Using only signals available during decoding, AutoCRAT jointly adjusts sampling stochasticity and reasoning budget during generation. AutoCRAT operates over a discrete action space and updates control decisions only at semantic boundaries, improving stability while remaining responsive to the evolving reasoning process. Comprehensive evaluation across 6 benchmarks demonstrates that AutoCRAT (I) uses 13.8-52.7% fewer inference tokens on average than recommended static configurations, (II) surpasses recommended static and adaptive baselines by 1.5-4.5% in relative accuracy, and (III) enjoys strong cross-backbone transferability.

Large language models often answer complex reasoning questions without revealing intermediate steps, raising whether they reason latently or complete patterns. We propose the Hidden CoT Detection Score (HCDS), a comparative behavioral and mechanistic signal measuring whether neutral-prompt behavior aligns more closely with explicit CoT or explicit no- CoT. Here, hidden CoT operationally denotes this neutral-prompt CoT-like alignment; HCDS does not directly observe or prove an unexposed reasoning trace. On GSM8K, HCDS is significantly positive for both Qwen3-4B variants (Thinking $+1.87$, $p = 1.2 \times 10^{-7}$; Instruct $+1.41$, $p = 1.9 \times 10^{-4}$), replicates across a different inference stack and quantization within $0.08$ ($+1.80$ and $+1.45$), and is not significantly positive in seven of eight length-adjusted calibration-control cells. The unadjusted score produces large positive scores on single-step arithmetic and numeric factual lookup. The variants also respond differently to no-CoT instructions: Instruct complies from the prompt alone, whereas Thinking continues reasoning and requires intervention. These findings show stronger, less prompt-conditional CoT-like behavior in the reasoning-tuned model, consistent with but not proof of latent reasoning. HCDS thus investigates latent reasoning without relying on models' self-reported traces.

Large language models (LLMs) often produce fluent but weakly grounded conclusions when reasoning over non-interactive, long-form narratives. A central failure mode is that unsupported intermediate hypotheses can enter the reasoning trajectory and contaminate subsequent inference, especially when evidence is scattered across distant parts of the story. To address this problem, we propose EVAR, an evidence-validated hypothesis admission framework for budget-aware narrative reasoning. EVAR first compiles the narrative into an immutable evidence store of source-linked atomic claims and assigns an instance-specific inference budget from unresolved gaps and uncertainty signals. During refinement, EVAR directly proposes candidate hypotheses for unresolved gaps, constructs hypothesis-conditioned validation challenges, and verifies each candidate against the locked store before admission: supported hypotheses enter the answer-supporting state, unverifiable ones are quarantined, and contradictory ones are discarded. A sufficiency-based stopping mechanism further avoids unnecessary refinement. Experiments on NarraCrime and multiple public reasoning benchmarks show that EVAR improves both task performance and evidence faithfulness while maintaining controllable inference cost.

Speculative decoding accelerates autoregressive language model inference by having a lightweight draft model propose multiple candidate tokens, which are then verified in parallel by a larger target model. However, after the first rejection, standard prefix-based verification discards the remaining draft suffix, so the computation spent generating and verifying those positions does not contribute to decoding progress. Focusing on DFlash, we show that rejected positions in a rejected suffix may still align with the target continuation, indicating that the draft model can retain useful semantic and structural information despite local token-level errors. Motivated by this observation and inspired by conditional diffusion, we introduce~\textbf{ReTrace}, a rejected-trajectory conditioning method that conditions each draft block on the rejected suffix from the previous round rather than generating it from fresh mask placeholders alone. ReTrace retains the hidden representations of the rejected suffixes, aligns them with the next draft block, refines them using target-aware correction signals from the same verification pass, and admits them into the drafter's input embeddings through gated residual fusion. Because rejected tokens are never committed and target-side verification remains unchanged, ReTrace preserves the lossless property of speculative decoding without requiring an additional model forward pass. Experiments with Qwen3 models across mathematical reasoning, code generation, and open-ended dialogue demonstrate that ReTrace consistently improves average acceptance length and end-to-end decoding speed over its DFlash backbone. By introducing cross-round conditioning without modifying within-round proposal generation, ReTrace is largely orthogonal to existing drafting improvements and might be combined with them for further gains.

Recent advances in large reasoning models (LRMs) have shown strong performance on complex problems through long chain-of-thought (Long CoT) reasoning. However, distilling such trajectories into smaller student models remains challenging: direct Long CoT supervision often provides limited gains and can be less effective than concise Short CoT rationales. In this work, we investigate this phenomenon from a gradient-centric perspective. Our analysis shows that Long CoT induces larger gradient magnitudes and more concentrated update directions than Short CoT, with this effect becoming more pronounced as student model capacity increases. These findings suggest that effective Long CoT distillation requires balancing the reasoning information density of reasoning trajectories with their distributional alignment to the student model. Motivated by this insight, we propose \textbf{M}odel \textbf{I}nterporlation \textbf{Distillation} (\textbf{MI-Distillation}), a framework that constructs a continuous Instruct-Reasoning data spectrum through model interpolation. To select suitable trajectories from this spectrum, we further introduce \textbf{Seq}uential \textbf{L}earnable \textbf{S}urprisal \textbf{S}core (\textbf{SeqLSS}), which favors reasoning paths that are both informative and learnable for the student. Extensive experiments on reasoning benchmarks show that MI-Distillation consistently improves small model CoT distillation over strong Long CoT baselines.

Chain-of-thought (CoT) monitoring assumes that reasoning traces faithfully record the information that shapes a model's answer. Existing faithfulness tests often place explicit bias cues in the user message, while agents may encounter preferences through tool returns or raw artifacts. We introduce FACE-Eval (Faithful Attribution of Cue Effects Evaluation), a 5,100-sample evaluation that varies cue location (user message or tool return) and explicitness (direct summary or raw artifact). We measure verbalized commitment among cue-following answers and unverbalized adoption among all cued samples. We evaluate 15 open-weight models from eight families, with total parameters ranging from 4B to 1.60T. Every model has lower verbalized commitment for tool-return than user-message cues and for implicit than explicit cues. Unverbalized adoption is higher for tool-return cues on all 15 models and for implicit cues in 28 of 30 model-channel comparisons. A source-attribution prompt narrows the channel gap on seven models, sometimes by increasing user-channel unverbalized adoption, while telling models that their reasoning will be monitored does not reliably close the gap. We also use two transcript monitors (GPT-5.6-Luna and GPT-4o-mini) to detect preference adoption in the largest model of each family. Across 32 model-channel-explicitness cells, higher unverbalized adoption is associated with lower detection ability for both monitors (Pearson r=-0.54 and r=-0.78, respectively). These results suggest that CoT monitoring may be less reliable when preference information arrives through tools or must be inferred from raw artifacts, within the single-call, prefilled-tool setting tested here.

Reinforcement learning-based knowledge distillation has the potential to transfer complex reasoning from teacher to student models, yet it currently faces a critical dilemma: researchers must choose between sparse outcome-based rewards, which provide insufficient logical guidance, or expensive neural Process Reward Models (PRMs) for dense signals. We resolve this by introducing SPEAR (Symbolic Process Evaluation and Alignment Reward), a training-free and plug-and-play process reward method for sequence-level on-policy distillation. SPEAR projects natural-language reasoning traces into domain-adaptive symbolic milestones, providing an efficient proxy for process-level reasoning alignment. By utilizing the longest common subsequence (LCS) to align student explorations with teacher milestones, SPEAR provides a dense, order-aware reward signal that enforces logical consistency without the need for an external neural verifier. Our experiments across math, science, and commonsense reasoning tasks demonstrate that SPEAR effectively bridges the reasoning gap between student and teacher models via sequence-level distillation with efficient dense process rewards. Our code and data are available at: https://github.com/zhuochunli/SPEAR.

Large Language Models (LLMs) increasingly act as autonomous agents executing complex, long-running procedural skills. Existing agent runtimes maintain execution by continually appending observations, actions, and intermediate reasoning traces to an ever-growing conversation history, causing latency degradation and context-poisoning failures over long horizons. We present SKILL. state, a runtime architecture that replaces append-only conversational history with an explicit, mutable execution state. At each execution step, the model receives only the immutable skill specification, the current structured execution state, and the latest observation. Intermediate reasoning is discarded immediately after producing a validated state update, preventing prompt growth with execution history. Across diverse datasets, models, and execution environments, SKILL. state improves task accuracy while substantially reducing cumulative token consumption. Our results demonstrate that explicit execution state is an effective and architecture-agnostic abstraction for scalable long-horizon agent skills.

Continuous self-improvement requires an ever-expanding pool of self-generated, diverse, adaptive goals. For language agents, existing training environment pools (hand-curated, statically synthesized, or frozen-verifier) keep the goal distribution fixed as the learner scales. We introduce SPADE (Self-Play in Adaptive Synthetic Executable Environments), a self-play RL framework in which a single LLM plays two roles: an Environment Designer that writes complete, long-horizon training environments as executable code with an OpenAI Gym-style reset()/step() interface, and a Reasoning Agent that learns to act in them. Each is a stateful, multi-turn environment (state transitions, reward functions, and verification code), so one interface spans reasoning problems and multi-step agentic tool use. The Reasoning Agent's regret is estimated using the gap between its reward with and without privileged hints; in optimizing this regret signal the Environment Designer learns to target environments at the edge of the agent's capabilities while keeping them feasible. Through extensive experimentation, we find several components critical to success: grounding the Environment Designer on documents sampled from a large pretraining corpus, and giving it an accumulated environment memory. Scaling to 30B-parameter models, SPADE improves over the strongest fixed-environment baseline by +5.3 on average across eight held-out math, science, code, and reasoning benchmarks, and lifts the tool-use setting by +5.7 on BFCL-v4 multi-turn and +13.9 on ACEBench-Agent; on the games setting, the margin over the strongest baseline grows with model scale. By making environment design itself a learnable component, SPADE takes a concrete step toward open-ended self-improvement.

A benchmark should deliver more than a scalar score: what makes an evaluation trustworthy is the reasoning that justifies the score. This is especially critical for world models, where judging a rollout requires understanding whether physics, causality, and world state evolve correctly. Humans spot such violations naturally, yet no existing benchmark automates this capability: metrics are computed brute-force, leaving no reasoning chain that can be examined or verified. We introduce HarnessEval-W, an agentified evaluation pipeline that brings the harness paradigm from the LLM ecosystem to world model benchmarking. Rather than applying a fixed rubric, HarnessEval-W interprets the context of each evaluation case, decomposes the evaluation question into measurable subproblems, and spawns specialized sub-agents, each equipped with tailored context and diagnostic tools to reason over its own subproblem. The parent agent then validates the gathered evidence and summarizes it into the final verdict. This hierarchical workflow turns every evaluation into a transparent evidence tree whose complete reasoning chain justifies the result. We apply HarnessEval-W to 18 representative world models over 330 evaluation cases. Its judgments closely align with human preferences while providing verifiable, fine-grained diagnoses of every generated rollout. We open-source the full pipeline as a live benchmark and invite the broad community to contribute to grow new skills and evaluation cases as world models evolve.

World Models (WM) are increasingly seen as a foundation for intelligent agents that can predict, plan, and act beyond their training distribution. In this paper, we study WMs from a causal perspective across multiple levels of abstraction, ranging from perceptual observations to building a conceptual representation of the structure governing the environment dynamics. We argue that useful WMs must go beyond generative capabilities alone: they should also capture entity properties, entity-to-entity interactions, and entity-to-environment interactions that determine and explain the dynamics of a system. We provide a formal definition of Causal WMs (CWMs) grounded in the tasks they are intended to support, connecting world modelling with existing work in causal representation learning, object-centric learning, causal discovery, structural causal models, and model-based decision-making. Finally, we relate CWMs to the literature on identifiability, clarifying when the components of a WM can be recovered from data and up to which equivalence. With this, we ground WMs in representations and structures that support causal reasoning and informed decision-making.

Embodied intelligent virtual agents are expected to operate as persistent, adaptive, and context-aware entities within complex virtual and Metaverse worlds. However, implementing cognitively capable agents in such environments is conceptually and technologically challenging. Among a range of blueprints and development approaches, the Cognitive Embodied Agent Architecture (CEAA) has been developed as an implementation-oriented framework for architecting components of perception, memory, reasoning, planning, and embodied action. Considering the recent advances in edge computing and generative AI language models, this paper explores the use of Small Language Models (SLMs) to support edge-based operation of selected CEAA components, focusing on "Think" and "Memory" as processes central to cognitive orchestration and persistence of virtual agents in interactive virtual worlds. An edge-based virtual agent gateway system was developed and evaluated on an NVIDIA Jetson Orin NX using Qwen2.5 models of different sizes, exploring the system's capability to process service requests and handle memory-driven conversations. A series of simulation experiments evaluated routing accuracy, memory-read performance, and latency, demonstrating an SLM-driven prototype agent system that partially implements selected CEAA processes to support the development of embodied agents whose cognitive "brain" can operate efficiently and contextually for interactive experiences in immersive virtual worlds.

We study a large language model (LLM) service in which a provider chooses a per-token price and a default reasoning-token allocation, while a user may accept the default, customize the allocation, or exit. Larger allocations can improve accuracy but increase token cost and latency. We model this interaction as a Stackelberg game and derive the user's unique optimal customized allocation in closed form. For any price, the acceptable defaults form either an empty set or a compact interval. We characterize the provider's optimal default through a three-regime rule, reduce equilibrium computation to a one-dimensional price optimization, and prove the existence of the equilibrium. We further show that defaults affect the implemented reasoning allocation only when users value the convenience of avoiding customization; otherwise, every service-providing outcome implements the user's optimal customized allocation. Experiments with two compact open-weight reasoning models on five mathematics and science benchmarks support the accuracy-token model and show how model and task characteristics determine equilibrium prices, defaults, and reasoning allocations.

Training Multimodal Large Language Models for audio-visual social understanding is a crucial step toward embodied social intelligence. Chain-of-thought (CoT) reasoning has become the dominant approach, with HumanOmniV2 and its IntentBench benchmark as a prominent reference point. In this context, we report three findings. First, IntentBench is highly noisy: $\sim$7% of questions are broken and $\sim$23% are trivially answerable without the video input. We remove the affected questions and release Intentbench-Prime. Second, current reasoning approaches are expensive and surprisingly ineffective. A simple Vanilla SFT baseline matches or outperforms existing reasoning methods across three benchmarks at a fraction of the cost, establishing it as an essential baseline for evaluating novel fine-tuning techniques. Third, our analysis reveals that substantial priors can be learned solely from the text modality and that using a textual caption instead of the video yields performance on par with Vanilla SFT. These surprising findings reveal the limitations of current MLLMs when it comes to social understanding. IntentBench-Prime, Vanilla SFT model, and code are publicly available.

The evaluation of LLM reasoning is moving from final-answer accuracy to process-level assessment, yet existing methods still fail to capture how models plan reasoning paths and allocate reasoning resources--that is, how they organize search. Prior process-level methods focus on the coherence and redundancy of chain-of-thought (CoT), and most benchmark tasks have a single objective solvable by static capabilities such as derivation and tool use, leaving search organization unmeasured. We introduce TsuGO, a process-level reasoning benchmark for evaluating Search Efficiency in LLM reasoning through Go life-and-death problems. These problems provide closed and verifiable solution spaces with an inherent adversarial structure, making candidate generation, response checking, branch comparison, and backtracking necessary parts of reasoning rather than incidental trace patterns. By constraining the solution space, TsuGO disentangles domain knowledge from search organization, parses CoT into a structured search tree, and reports Search Efficiency together with Token Efficiency and other diagnostic metrics and visualizations. Experiments show that current LLMs remain far from stable tsumego solving: stronger models succeed by finding the correct candidate earlier and sustaining effort on productive branches, but most models still behave much closer to unguided search algorithms than to neural-guided KataGo. Longer CoT or higher Token Efficiency does not necessarily imply better search. Our results identify search organization and reasoning-resource allocation as missing dimensions in LLM reasoning evaluation.

Text-to-image generation has reached photorealistic quality, yet state-of-the-art systems remain unreliable at producing scientific diagrams, whose value depends not on appearance but on physical faithfulness: correct force directions, valid coordinate systems, consistent thermodynamic states, and equations matching the depicted scenario. Trained on web imagery with physically shallow captions, generic models produce diagrams that look plausible but are physically wrong, harmful in education and scientific communication. We present Princigram, a physics-faithful scientific-diagram generator, and its data pipeline. Our central advance is Structured Physical Chain-of-Thought (SP-CoT): a per-subdiscipline schema that decomposes a physics diagram into an explicit multi-step reasoning chain across six subdisciplines, from scene identification through force or process analysis to governing laws and synthesis. Unlike free-form chain-of-thought, SP-CoT follows a fixed schema with strict fidelity rules that separate visually grounded facts from physically inferred reasoning and type all mathematics symbolically; it serves both as dense training supervision and, at inference, as a structured "thinking" prompt. With it we curate and structurally annotate 4.3 million physics images, of which 115,037 carry expert-level annotation, and adapt a unified multimodal backbone. We further introduce VeriphyT2IBench, whose questions are derived from each held-out diagram's own structured annotation: each diagram becomes an item-specific bank of binary questions about its objects, forces, and states, so a judge model's score decomposes into named physical facts rather than one holistic number. On the physics subset of GenExam and on VeriphyT2IBench, Princigram shows that explicit physics-structured supervision improves the physical faithfulness of generated scientific diagrams.

Long-horizon LLM agents must preserve information from past interactions to support future tasks. Existing memory systems typically rely on eager consolidation, invoking LLMs after each interaction to extract, summarize, or update memories. This design makes memory construction increasingly costly as conversations grow. Coarse summarization can reduce construction cost but risks discarding fine-grained contextual evidence, whereas larger retrieval contexts or multi-hop LLM reasoning shift the overhead to query time. We present LycheeMemory V2, an efficient long-term memory framework that replaces turn-level consolidation with semantic segment-level consolidation. Instead of consolidating every interaction, LycheeMemory batches multiple exchanges into segments and encodes each finalized segment into context-independent typed memory records. Segment-level batching lowers LLM encoding frequency, while semantic boundary detection helps preserve coherent event-level and temporal evidence compared with fixed-window batching. The resulting records are organized with lightweight structured indexes for query-planned evidence retrieval. Experiments using GPT-4.1-Mini show that LycheeMemory achieves state-of-the-art performance, reaching 89.22% on LoCoMo and 92.20% on LongMemEval-S. Compared with A-Mem, it reduces construction tokens by 86.0% on LoCoMo and 75.9% on LongMemEval-S without increasing query-time token usage. More broadly, our results suggest that the accuracy--cost trade-off of long-term agent memory depends not only on what information is retained, but also on the granularity at which it is consolidated.

Strategic reasoning in Large Language Models (LLMs) within long-horizon environments is often limited by inconsistent subgoals. In these settings, finite attention resources prevent the model from maintaining strategic coherence over thousands of steps. This limitation leads to strategic drift, where localized decisions fail to sustain a coherent trajectory across reasoning. To address this, we introduce EpicStar, a framework that enables agents to learn memory as policy to tackle long-horizon reasoning. Specifically, the agent maintains a bank of successful past episodes as a heuristic alongside a working memory to track short-term environmental changes. During inference, a dynamic gating mechanism determines whether to execute a retrieved action directly or to perform new reasoning through a contextual fusion of the retrieved episodes and current working memory. Utilizing StarCraft II as the testbed, we evaluated EpicStar against diverse opponent styles. It significantly outperforms baseline methods, achieving higher win rates while consuming an order of magnitude fewer tokens, and it maintains this advantage consistently across difficulty levels and opponent strategies. Our findings provide compelling evidence that structured cross-episode memory is essential for enabling LLM agents to perform robust, long-term strategic execution in dynamic, autonomous settings.

Improving reasoning LLMs requires the ability to judge the quality of long reasoning traces for effective reasoning data curation, strong training signals during reinforcement learning, and an in-depth understanding of reasoning behaviors during model performance evaluation. Additionally, surfacing reasoning mistakes that the model makes would enable improving the model's performance at runtime through providing feedback. Due to the difficulty of this complex task on long reasoning traces, single-model judges (even frontier models) do not do well at identifying reasoning defects. Additionally, leveraging frontier models during online training of reasoning LLMs is generally prohibited due to guardrails in terms of use. In this work, we introduce Reasoning Jury, a system that replaces the single judge with a jury of LLMs and a moderated consensus mechanism, to improve the fidelity of judgments for identifying reasoning defects. In reasoning jury, defects of a reasoning trace and their severity are surfaced through a deliberation where a moderator conducts a discussion amongst the jury where the jurors critique each other's judgments and get to modify their initial votes. The moderator derives a consensus through deliberation amongst jurors or consolidation of judgements. We show that Reasoning Jury with a jury of open-weight models (e.g., gpt-oss-120b) is able to significantly outperform frontier models (opus-4.6, sonnet-4.6, and gemini-3.1-pro) at correctly identifying reasoning defects. Besides accuracy performance improvements, the aggregated cost of the jury (initial verdicts, deliberations, consolidation, etc.) is a fraction (8 to 15%) of the cost of running frontier models in LLM-as-a-judge setup. We also show how these judgements can be leveraged to understand failure modes of reasoning LLMs on benchmarks, which allows much deeper understanding of a model's performance.

Agents deployed in enterprise settings must reason across structured APIs and document collections, yet existing benchmarks evaluate these capabilities in isolation. We introduce VAKRA (e\textbf{V}aluating \textbf{A}PI and \textbf{K}nowledge \textbf{R}etrieval \textbf{A}gents), a benchmark of over $8{,}000$ executable APIs across $62$ domains with tasks spanning three settings of increasing difficulty: diverse API interaction styles, multi-hop reasoning over structured APIs, and multi-source reasoning with natural-language tool-use policy constraints. Correctness is verified by re-executing predicted tool calls against live APIs, accommodating multiple valid paths. Using a fixed ReAct harness to isolate model capabilities from agent architecture, we evaluate frontier and open-weight models and find that even the best model achieves only 70.4% on single-hop endpoint-style tasks and drops to 50--51% on compositional APIs; performance degrades by over 50% as reasoning depth increases, and policy-constrained questions expose severe failures (as low as 2.4% on unanswerable queries). Trace analysis shows failures concentrate at language-mediated reasoning - entity disambiguation, cross-source grounding, rather than tool invocation mechanics. Code is available https://github.com/IBM/VAKRA. Dataset is available https://huggingface.co/datasets/ibm-research/VAKRA

Existing Vision-Language Models (VLMs) exhibits a critical bottleneck in robust spatial reasoning. Recent reinforcement learning (RL) methods aim to close this gap with verifiable outcomes, yet they suffer from poor credit assignment across intermediate reasoning steps. Concurrently, structured reasoning approaches overlook the critical depth perception necessary for comprehensive 3D understanding. To address these challenges, we propose SCOUT (Structured Chain-Of-Thought Utilizing Process-Supervised RL Training). Specifically, we design a structured Chain-of-Thought (CoT) framework that explicitly models 3D environmental perception to ensure robust spatial understanding and reasoning. Furthermore, we introduce a novel RL algorithm featuring multi-objective process rewards and a tailored advantage estimation method, facilitating fine-grained credit assignment across distinct segments of the reasoning trajectory. To support our framework, we develop SCOUT-24k, a structured spatial reasoning CoT dataset synthesized through a customized pipeline. Extensive evaluations demonstrate that SCOUT-3B improves upon baseline models by 16.85% and 6.3% on general spatial benchmarks and complex spatial reasoning tasks respectively. Notably, our larger SCOUT-7B even outperforms GPT-4o by a margin of 4.28%. Moreover, despite being trained exclusively on single image, SCOUT-7B exhibits robust out-of-domain generalization to multi-image and video scenarios. These empirical results render SCOUT as a critical step towards next generation of spatially-aware VLMs.

Standard evaluation of large language models assumes stable model rankings across inference conditions. We challenge this assumption by varying the token generation budget, i.e., the maximum tokens a model may produce, across seven levels (64--4,096), evaluating four models on three reasoning benchmarks (56,476 inferences). We report four findings: (i) 3--19% of items exhibit non-monotone behavior (accuracy decreasing with more budget), even after controlling for truncation, and this phenomenon is model-specific (cross-model overlap: 6--14%). (ii) Model rankings reverse across budgets on all benchmarks ($p {<} 0.01$, McNemar). (iii) Oracle analysis reveals model complementarity up to $+27.8$pp, most pronounced at constrained budgets. (iv) A budget-aware router captures 14.1% of the oracle gap cross-domain; budget features help within-domain ($+1.6$ to $+5.7$pp) but are domain-specific and hurt transfer ($-1.2$pp). These results argue for budget-conditioned evaluation protocols.

As LLM-based agents with user-instructed goals are becoming widely deployed, they increasingly encounter each other in strategic interactions, and face challenges of finding mutually beneficial outcomes. Prior literature has argued that cooperation problems such as the Prisoner's Dilemma are resolvable in settings where agents know they follow very similar decision making patterns, as for example in monocultural AI ecosystems. Following that line of work, this paper introduces the first framework for evaluating LLM decision making when agents are provided with graded similarity signals. Among our findings, we establish that different LLM models vary drastically in how they navigate similarity signals, with some modern models showing consistent behavior across cooperation problems, payoff structures, and prompt framing. Perhaps surprisingly, our experiments also show that the dataset based on which the similarity signal is computed has small to no impact on induced cooperation, and that LLM models systematically self-identify as highly similar when asked to evaluate another model's chain-of-thought reasoning by themselves. Finally, we develop an LLM-behavioral-game-theoretic model that captures some of their reasoning rationale, and show that it can support cooperative outcomes in equilibrium under sufficiently high similarity scores.

Chain of Thought (CoT) lifts the expressive ceiling of bounded-depth Transformers, with characterizations tying the number of CoT steps to circuit complexity classes. What remains largely missing are concrete instantiations with explicit, depth-bounded constructions, and the traversal procedures such characterizations presuppose. We close this gap for branching complexity. We give CoT realizations of depth-first search (DFS) and of Dijkstra algorithm, the latter subsuming breadth-first search, by unique hard-attention decoders of at most two layers, and use them as a shared computational substrate: reusing the DFS decoder yields the Strahler number of an $n$-vertex tree in $2n-1$ steps with four layers, and reusing the Dijkstra decoder yields its width in $n-1$ steps with three. Since computing the Strahler number of a binary tree given as a term is \textsf{NC\textsuperscript{1}}-complete, and our constructions handle arbitrary $n$-ary trees without layer normalization or positional encodings, this is a non-trivial witness for the linear-step regime of the CoT hierarchy. Exploiting the classical bijection between ordered trees and Dyck paths, itself realized by our DFS construction, which emits the path as it traverses, we give independent constructions for both measures on the path representation.

While existing benchmarks have made substantial progress in evaluating LLMs across STEM domains, financial reasoning over structured data remains comparatively less explored. We introduce V-FiLLM, a framework that generates financial reasoning benchmarks from executable computation trees grounded in real tables, yielding items whose answers are correct by construction. Trees are evaluated symbolically to obtain ground truth and rendered into natural-language questions, removing any model from the labeling loop, so items can be generated at arbitrary scale without annotation cost and without inheriting a generator's error rate. V-FiLLM exposes four independently controllable axes of difficulty including computation depth, expression breadth, financial concept complexity, and context size. By evaluating on open-source models, we find that accuracy falls up to 51% as reasoning depth increases, and up to 47% points under adversarial numerical perturbations, highlighting remaining challenges in robust financial reasoning over tables. We further show that lightweight LoRA fine-tuning on verified chain-of-thought traces improves accuracy from 81.1% to 85.6% on held-out problems and outperforms the base model by 5% points on FinQA (Chen et al., 2022a), s), suggesting that targeted, low-cost adaptation is a promising direction for compositional reasoning in financial QA.

Vision-Language-Action (VLA) models can connect scene understanding, semantic reasoning, and trajectory generation for autonomous driving. However, verbose natural-language Chain-of-Thought (CoT) is poorly suited to real-time control because it is open-ended, costly to decode, and difficult to optimize as an action-facing representation. We propose XCoT-VLA, which replaces descriptive rationales with compact executable CoT tokens learned from automatically constructed Reason-Action supervision. Logged trajectories provide action evidence, while scene context supplies causal semantics. The predicted XCoT sequence remains in context and conditions fixed trajectory queries through shared multimodal self-attention. Deterministic token-function routing applies the Reason FFN to XCoT tokens and the Control FFN to trajectory queries for flow-matching trajectory generation. We further introduce XCoT Policy Optimization (XCPO) as an optional refinement extension in the same executable token space. XCoT-VLA reduces longitudinal ADE from 1.645 to 1.323 on a general-distribution set and lateral FDE from 1.616 to 0.648 in lane-change scenarios. By representing driving-oriented reasoning with only 2-6 executable XCoT tokens, our method substantially reduces autoregressive reasoning overhead and remains within the real-time planning budget. These results demonstrate that driving-oriented reasoning can be compact, executable, and directly connected to trajectory generation.

Scientific papers contain fine-grained records of problem solving: authors mention technical obstacles and methods that were used to address them, often along with reasoning on why those methods were chosen. We introduce MUSE (Mining Underlying Scientific Explanations), a full-text, multi-domain resource of scientific Problem-Solution-Rationale (P-S-R) triplets. We curate 579 expert-annotated full-text paragraphs, with a rich annotation schema covering salient problem, solution, and rationale spans, solves and rationale_of links and conceptual coreference. A modular extraction pipeline scales this annotation to build a high-quality knowledge base of 37K source-grounded P-S-R triplets. We evaluate the extraction components and include a preliminary experiment training a rationale-supervised LLM for scientific problem solving. Interestingly, we find that rationale supervision improves performance on complex, multi-constraint problems but can harm performance on simpler ones.

We present the REAP system for the AKBC Shared Task 2026 on constructing knowledge bases from language models in a closed-book setting, subject to a budget of at most 32B parameters and no model fine-tuning. Our system combines structured chain-of-thought reasoning, relation-specific query strategies, and a reasoning-based empty-set gate to elicit parametric knowledge, followed by direct extraction into valid JSON arrays. On the test set, the system, built on the Mistral-Small-24B-Instruct-2501 model, achieves a macro-F1 score of 0.62, with particularly strong results on countryLandBordersCountry (F1 = 0.95), companyTradesAtStockExchange (F1 = 0.73), and hasArea (F1 = 0.77). Our code is publicly available at https://github.com/yammdd/AKBC-Shared-Task-2026.

Large Reasoning Models (LRMs) improve performance by allocating additional inference-time compute to generate extended chain-of-thought reasoning. However, recent studies reveal that sequential test-time scaling often yields diminishing or even negative returns, as longer traces exhibit increased uncertainty, error compounding, and drift from the original problem. We propose ThinkRetrieve, a test-time scaling framework that augments the reasoning traces of LRMs with dynamically retrieved solved examples at each reasoning step. Given an external corpus of problems paired with step-by-step solutions, ThinkRetrieve retrieves relevant exemplars at each intermediate step and injects them directly into the thinking trace, providing the model with guidance on how to reason rather than merely what facts are relevant. Experiments across five reasoning models (1.5B--8B parameters) on GSM-8K, MATH-500, AIME 2025, and SciQ demonstrate that ThinkRetrieve consistently improves accuracy over standard test-time scaling, with relative gains of up to $60\%$ on AIME 2025.

Autoformalisation (AF) systems map natural language reasoning steps into formal statements in a proof assistant such as Lean. We consider how to assess the faithfulness of these systems. Existing approaches require expensive human-annotated ground truth, or rely on LLM judges or embedding models, which come with limited guarantees of accuracy. In addition, these methods typically only consider inputs that are known to be correct, and therefore do not assess whether the AF translates incorrect inputs faithfully. To address these limitations, we propose a new benchmark for AF faithfulness that is cheap to apply, sound under weak assumptions, and assesses both positive and negative examples. Our method is based on automatically generating perturbed reasoning steps that are designed to be invalid, and then measuring validity preservation on unperturbed steps and invalidity preservation on perturbed steps. We apply our method to eight AF systems across four mathematical datasets, and observe pervasive sycophancy: many AFs "silently correct" invalid inputs into provable statements. The most validity-preserving fine-tuned AFs are also the most sycophantic, suggesting a tension between validity and invalidity preservation in current AF systems.

Effective research ideation requires moving beyond a static understanding of prior work to trace how research problems and solutions evolve across the literature. Existing methods either treat papers as unstructured context or model scholarly evolution as isolated citation chains, overlooking interactions among research trajectories. We propose Tree-of-Ideas (ToI), a two-stage framework. EvoTrace reconstructs branching scholarly trajectories from citations, tracking evolving methods, resolved problems, and gaps. EvoAgent then reasons across trajectories to identify convergent problems and complementary solutions, generating grounded research ideas. Across six AI research topics, ToI achieves the highest score among automatic methods (6.27 vs. 5.36 for the strongest baseline on a 10-point scale), with strong Novelty (6.36) and Groundedness (7.00). Also, its score approaches that of human-paper references (6.29), demonstrating the value of cross-path evolutionary reasoning.

We present TAR (Traffic Anomaly Reasoning) and TAR-Bench datasets, resources for training and evaluating video-language models beyond anomaly detection. TAR contains 44,040 chain-of-thought training annotations across 10 tasks for 3,670 CCTV videos ($\sim$26 hours) from eight public datasets. Its evaluation component, TAR-Bench, contains 960 human-curated test annotations for 80 held-out clips trimmed from 17 public YouTube videos. TAR's training annotations are produced with MAVEN, which consolidates multi-scale video evidence into structured event descriptions before generating question-answer pairs and reasoning traces. On TAR-Bench, eleven vision-language models reveal that strong question-answering accuracy does not reliably predict temporal or scene reasoning ability. Multi-task fine-tuning on TAR yields consistent gains, with the full 10-task model improving aggregate score by 21.4 points over its zero-shot baseline. TAR and TAR-Bench provide the official training and in-domain evaluation data for AI City Challenge 2026 Track 3. The dataset is available at https://huggingface.co/datasets/nvidia/PhysicalAI-Traffic-Anomaly-Reasoning

Due to the diversity of real-world time series, no single forecasting model consistently dominates across all samples. Ensemble learning addresses this by combining complementary model strengths, yet existing methods rely on fixed rules or black-box models based solely on numerical inputs, failing to leverage LLM reasoning for interpretable weighting decisions. We propose REATS, which leverages LLM reasoning capabilities as an intelligent ensemble router that jointly processes textual temporal pattern descriptions and numerical features to produce interpretable, sample-adaptive ensemble weights through chain-of-thought reasoning. To enable effective LLM-based ensembling, we study its key design choices and propose: (i) a structured input pipeline that transforms raw time series into hybrid textual--numerical representations with fixed token cost, enabling rule-based chain-of-thought construction without API dependency, augmented with retrieved similar-sample priors; (ii) a diverse multi-row weight supervision scheme coupled with a token-efficient percentage-table format that reduces numerical complexity and mitigates LLM hallucinations; and (iii) a two-stage fine-tuning framework combining SFT with GRPO, where a reciprocal reward mapping transforms the continuous unbounded MSE gap into bounded signals with amplified near-oracle sensitivity, addressing the uniform sensitivity and outlier-dominated advantage compression inherent in naive reward designs for regression-based GRPO. Experiments on eight benchmarks demonstrate that REATS outperforms competitive ensemble baselines while providing natural language explanations and demonstrating strong transfer learning and out-of-domain generalization to unseen candidate models.

We introduce BDH-CQ, a reasoning model that combines in-context learning with recurrent latent reasoning. Inputs presented at inference time continuously update the model's recurrent memory; the model then solves a query through iterative computation in a high-dimensional latent space, without verbalizing its intermediate reasoning. We evaluate the model on the public ARC-AGI-1 evaluation set and use controlled ARC-like interventions to study what it learns from demonstrations, how consistently it applies an inferred transformation, and which concepts remain difficult. A 150M-parameter configuration reaches 29.5% pass@2 at a computed inference cost of $0.0007 per task. This operating point breaks through the previously reported ARC-AGI-1 cost-accuracy Pareto frontier, establishing a new state of the art in benchmark cost efficiency.

Leading large language model providers now conceal their models' step-by-step reasoning, or chain-of-thought, to protect intellectual property and limit information leakage. Rather than storing these traces server-side, providers return them to the client as blocks of encrypted text, which the client passes back with each subsequent request. Building on prior research, we identify an architectural vulnerability: these encrypted blocks are fully compatible and interchangeable across different sessions, users, and models within a provider's ecosystem. We exploit this compatibility to develop a scalable decryption jailbreak. By injecting an encrypted reasoning trace from a given model into a weaker, and less safeguarded model from the same provider, we force it to decode and output the trace verbatim in plaintext, without ever jailbreaking the more capable model directly. This vulnerability enables four distinct attack vectors. First, it circumvents anti-distillation mechanisms, allowing adversaries to extract a proprietary model's reasoning, as we demonstrate across Anthropic, OpenAI, and Google. Second, it allows for large-scale private data extraction. Developers frequently share session logs publicly, unaware of contents of the encrypted blocks. By decoding 315,320 reasoning blocks scraped from public repositories, we recovered 367 Personally Identifiable Information (PII) artifacts and 182 credentials. Third, it inadvertently reveals hazardous information hidden within the reasoning process, even in cases where the model's final, visible output safely rejects a malicious request. Fourth, attackers can leverage this flaw to execute invisible prompt injections, embedding malicious payloads entirely within encrypted blocks to poison public agentic rollouts. Following responsible disclosure, we propose concrete cryptographic and system-level mitigations to secure client-side reasoning.

Advances in advanced artificial intelligence tools have sparked research in robot autonomy, but the development of such systems has largely focused on execution rather than verifying the feasibility actions planning models propose. Like general-purpose LLMs, robotics planning models carry risks: biased toward user-specified goals, they may suggest actions misaligned with scientific ethics, they may be unsafe due to an inability to "remember" prior safety risks, or they may be vulnerable to adversarial attacks on the autonomy ecosystem. We propose a LLM-driven verification layer between planning and execution to evaluate action permissibility. Our LLM-as-a-Judge ensemble combines chain-of-thought reasoning across models and synthesizes those expert judge outputs, mirroring a combination of a mixture of experts and self-consistency approach. This layer serves as middleware, gating plans from the server's planning module before they reach the MCP server and therefore the robot's low-level controls: plans are approved, rejected for reformulation, or escalated for human review. With this system, we achieve near 85% precision across accept/escalate/reject categories 97% containment of adversarial attacks, with negligible errors between accepting and rejecting tasks, and errors mostly manifesting at the escalate boundary.

Electrical circuit analysis requires more than recognizing components in an image. A solver must ground symbols and labels, recover latent topology, select a physical model, formulate coupled equations, propagate intermediate quantities, and preserve units, signs, directions, and phase conventions. We introduce \benchmark, a benchmark of 1,000 authentic textbook problems for evaluating this complete long-horizon visual-to-symbolic reasoning process. Each problem pairs one or more circuit diagrams with a self-contained question, a typed or semantically specified answer, and a reference worked solution. An evidence-first construction pipeline aligns questions, figures, and solutions, while a reasoning-oriented taxonomy organizes problems by circuit type and dependency depth. Evaluation combines conservative typed scoring with identity-blinded multi-model semantic consensus, retaining every problem in the denominator. Across three commercial chatbot systems and six open-source multimodal large language models, the highest-scoring system reaches 84.8% accuracy. However, performance consistently deteriorates on long-horizon problems, and qualitative analysis exposes persistent failures in topology-to-target binding, physical conventions, and late-stage output propagation. \benchmark{} provides a focused testbed for measuring whether multimodal models can transform technical visual evidence into sustained, physically valid symbolic reasoning. Code are available at GitHub - CircuitReason/CircuitReason1K.

Reinforcement learning (RL) has become a central post-training paradigm for eliciting reasoning capabilities in large language models, yet uniform task sampling allocates compute without regard to differences in how tasks respond to optimization. Existing task-valuation methods mostly rely on snapshot-based signals such as current pass rate or reward, which estimate how solvable a task is under the current policy. However, tasks with similar current solvability can still differ substantially in how positively they respond to further training. We study this residual axis as task learnability: a regime-conditional measure of expected positive response to continued training under a fixed RL post-training regime. By analyzing per-task reward trajectories, we find that learnability is reproducible across independently sampled training contexts and predictive of downstream utility. To make this signal practical before training begins, we propose TrajVal, a lightweight probe-based estimator that approximates per-task learnability from a short probe run and two endpoint evaluations. TrajVal can be used either as a standalone static prior for task sampling or as a multiplicative prior for existing online schedulers. Experiments on mathematical and logical reasoning benchmarks across multiple model scales show that TrajVal improves data efficiency over uniform sampling and provides complementary gains when combined with online scheduling methods.

LLM agents are increasingly deployed in multi-agent social settings where they must cooperate, negotiate, and adapt to other agents. Measuring and improving these social skills is hard because, unlike math or logic, social interaction offers no objective ground truth: evaluations fall back on LLM judges, which are costly, subjective, and noisy, and models get no reliable signal to learn from. To address both, we first introduce Social Gym, an environment of 21 multi-agent social games (e.g., Werewolves, Resistance, Spyfall) whose rule-decided outcomes make agent performance verifiable and objective, with an Elo tournament that produces a cross-game leaderboard. Benchmarking experiments show that while GPT-5-mini tops the leaderboard, no model excels at all games uniformly or in all game roles, pointing to limitations of social reasoning. Motivated by this, we additionally propose SPaRTan (Self-Play and Reflect-Transfer), a training-free self-improvement loop: a model plays a game, reflects on its trajectories and their outcomes to produce a transferable playbook, and applies that playbook in subsequent games. Our results show that SPaRTan playbooks help GPT-5-mini agents level their performance on weaker roles, but largely do not improve Qwen3-32B's performance. Together, Social Gym and SPaRTan offer a reproducible, verifiable foundation for measuring and improving LLM social reasoning without weight updates.

Continual self-evolution requires LLM agents to transform environmental interactions into reliable and reusable experience. Existing methods typically refine individual trajectories or abstract shared knowledge from related trajectories, but their experience representations are often disconnected from the underlying reasoning process. This limits feedback attribution, cross-task transfer, and update and retrieval efficiency, particularly in complex reasoning tasks with outcome-level feedback. To overcome this limitation, we propose \textbf{T}ree-\textbf{o}f-\textbf{E}xperience (ToE), a structured experience-management framework that aligns experience organization with the hierarchical reasoning process of LLM agents. Specifically, ToE organizes the experience into a shared tree of analytical perspectives and reasoning paths, whose reliability is calibrated through environmental outcomes to support systematic updating, transfer, and efficient retrieval. The experimental results on \textsc{Game of 24} and \textsc{FinEvolveBench} show that ToE substantially improves both problem-solving performance and efficiency. On \textsc{Game of 24}, ToE achieves a 31.4% relative improvement in accuracy over the experience-free ToT baseline. On \textsc{FinEvolveBench}, ToE improves tsIC by an average of 41.24% over the experience-free pipeline across 12 evaluation settings, whereas conventional experience-management methods often underperform experience-free baselines.

Recommendation systems thrive on personalization, where ''correctness'' is rarely a binary truth but a matter of subjective human preference. As Large Language Models (LLMs) are deployed as autonomous verifiers of safety and quality guidelines, they face a distinctive challenge: context-aware preference alignment. Recent gains in Reinforcement Learning with Verifiable Rewards (RLVR) are indexed mostly on objective, mathematical tasks. Through a large-scale study spanning both proprietary and open-source models on four real-world verification tasks from a production recommender platform, we ask whether explicit reasoning generalizes to subjective, human-centric industry rubrics. We expose a fundamental vulnerability: rigid, math-centric reasoning traces actively degrade verification, and applying standard RLVR triggers a phenomenon we term reasoning collapse, in which the policy abandons deliberation in favor of rapid heuristic guessing. We introduce a conditional length-penalized post-training algorithm that intertwines verification accuracy with bounded reasoning length, halting collapse and recovering performance. Finally, we show that a reasoning trace's efficacy is tightly coupled with its socio-linguistic framing: across 1500 synthesized personas, verification accuracy swings by nearly 0.38 macro-F1 depending solely on the adopted reasoning persona---evidence that much subjective-verification error is really reasoning-style mismatch. This observation motivates a mid-training architecture that routes reasoning through contextually aligned personas. This work offers both a scalable algorithmic patch and a long-term architectural blueprint for aligning reasoning models with real-world subjective constraints.

Large language models (LLMs) increasingly serve as data-driven reasoners, yet their chains-of-thought (CoT) can be unfaithful even when final answers are correct. Most existing verification'' signals are not diagnostic: answer matching observes only the outcome, LLM-as-judge provides subjective and non-verifiable critiques, and scalar rewards (e.g., PRMs/RMs) offer little insight into where a multi-step derivation fails.We propose \textbf{SymDiag}, a neuro-symbolic framework that \textbf{reframes reasoning verification as structured failure diagnosis}. SymDiag translates natural-language CoT into symbolic constraints and performs step-level satisfiability/entailment checks to (i) localize failing steps and (ii) produce verifiable diagnostic evidence, including counterexamples, inconsistency witnesses, and missing-premise indicators. A central challenge is that apparent logic violations'' can be caused either by genuine reasoning defects or by neural-to-symbolic translation noise. SymDiag therefore incorporates a Self-Auditor that disentangles TranslationError from ReasoningError via dual symbolic encodings consistency checks, enabling robust diagnosis under partial observability. Across diverse mathematical, logical, scientific, and general reasoning benchmarks, SymDiag improves detection of unfaithful reasoning and provides substantially more effective feedback for multi-round reasoning repair than outcome-only verification and LLM-based judging, offering a principled foundation for trustworthy and scalable reasoning diagnosis.

We independently reproduce two recent methods for making large language model (LLM) reasoning more reliable, and stress-test them across domains and models (RPC across four new task domains with Qwen3-8B, LCF across four 7-8B models). The first, RPC, aggregates token probabilities and self-consistency at inference; the second, LCF, trains projectors that split hidden states into "content" and "logic" and edits the logic part toward a valid region. Validating such reliability claims matters because the original evaluations are run by each method's own authors and were never independently reproduced or stress-tested across models and domains, and LCF shipped no public code. We re-run RPC's published-path aggregation and re-implement LCF's projector, contrastive, and intervention pipeline, then extend both to text-to-SQL, legal extraction, fallacy identification, and precedent grading, and probe LCF's representation directly. RPC reproduces the original grid exactly on the authors' released reasoning paths; on four new domains its edge over self-consistency is never significant (ties or small mixed differences, paired p >= 0.28), and on BIRD, the one domain where we vary the budget, the edge grows with K as predicted but its largest gap (+2.5 accuracy at K=32, p=0.16) reverses to -0.25 when we enlarge the sample to n=200. LCF's logic-validity direction is real but weak (0.82 separability at the single best sub-layer versus 0.95 for a semantic-attribute control); its one positive effect (Qwen3 $Δ$Prob) is not significant (p=0.56), while it significantly reduces $Δ$Prob on two of the other three models.

Harmful chat dialogues are ever-shifting through type-shifting and lexical evasion, yet we find they share invariant principles, i.e., an Ordered Reasoning Chain (ORC) of recurring topics, harm language indicators, severity hierarchies, and type characteristics, which can help us capture the key information in the frequently changing lexical expressions. We propose BRACE, which encodes the ORC as four differentiable stages (Topic -> Indicator -> Severity -> Type) with intermediate supervision, serving as a structured regularizer blended with direct heads, and supported by prototype-based feature augmentation and feature path disentanglement. The evaluation results show that, across 4 domains and 5 harm categories, BRACE achieves harm-type macro F1 of 0.934 (RoBERTa-wwm-ext, 3-seed mean), with decoder backbones (Qwen3-1.7B LoRA) reaching 0.949. Ablation studies show that all components contribute to BRACE, and the structural decomposition of ORC enables BRACE to distinguish harmful types with semantic ambiguity. Disclaimer: This paper may contain content that is disturbing to some readers.

Multilingual reasoning models are commonly evaluated by whether they arrive at the correct answer, but not by whether they preserve the intended language while reasoning and responding. This omission conceals important multilingual behaviors that emerge as tasks become harder. In this paper, we study task difficulty, task accuracy, thinking-language consistency (TC), and answer-language consistency (AC) across reasoning models using PolyMath benchmark in eight languages and four difficulty levels. We uncover four findings: (1) language consistency exhibits four difficulty-dependent behaviors: output-language consistency remains aligned with input, remains misaligned, degrades gradually, or collapses abruptly. (2) We identify the language consistency breakdown effect, where increasing difficulty can cause a sudden drop in output-language consistency, especially in less strongly represented and non-Latin-script languages. (3) Due to this breakdown effect, accuracy can be preserved or even improved at a harder difficulty level as the model shifts to its internal dominant language. (4) Quantization can improve or degrade output-language consistency independently of its effect on accuracy, with GPTQ and AWQ often outperforming AutoRound under tolerance-based voting with ε = 1.0. These results show that multilingual capability cannot be characterized by accuracy alone; reliable evaluation should jointly consider task accuracy, language consistency, and task difficulty for multilingual benchmarks.

On-policy self-distillation (OPSD) improves the reasoning abilities of LLMs by internalizing privileged context into model parameters through self-distillation. Two recent research lines promote vanilla OPSD by choosing which tokens to learn from and by controlling how much privileged information the teacher receives, respectively. However, we show that each line optimizes one variable while holding the other fixed, which leads to a suboptimal solution. We argue that the two variables are coupled through the student's learning capacity: the privileged information sets the per-token divergence the teacher prescribes, while token weighting selects which of these the student must absorb. We formalize the two lines of work into a unified optimization framework, which maximizes the aggregate teacher--student divergence, subject to a budget on the aggregate learning difficulty the student can absorb. Under this modelling, we propose Unified On-Policy Self-Distillation (USD), a lightweight online algorithm to solve the Lagrangian. USD reveals that a single dual variable governs both decisions: at one price for learning difficulty, it simultaneously sets the token-selection threshold and the direction of privileged-information adjustment, keeping supervision matched to the student's evolving capacity. Through extensive experiments, USD consistently demonstrates superior performance over OPSD and token- and PI-side baselines across various model scales on various reasoning benchmarks. Code is available at https://github.com/lauvlalala/USD.

While Large Language Models (LLMs) employing Chain-of-Thought (CoT) exhibit superior reasoning capabilities, the neural mechanisms distinguishing this explicit Thinking mode from direct answer generation (NoThinking mode) remain poorly understood. To deconstruct this cognitive process, we apply Top-K Sparse Autoencoders (SAEs) to the intermediate representations of DeepSeek-R1-Distill-Qwen-7B and examine the model's divergent behaviors across math-solving tasks of three distinct difficulty levels. Observationally, we identify a clear distinction in how the model functions under two reasoning modes: Thinking mode relies on sparse and high-intensity feature activations driving verbal deduction independent of problem complexity, whereas NoThinking mode exhibits an adaptive and diffuse pattern prioritizing symbolic manipulation. Causally, suppressing the three most active sparse features by Total Activation Volume reveals three principles: (i) reasoning and syntactic structure are tightly coupled, as interventions consistently degrade \LaTeX{} and boxed-solution formatting; (ii) Thinking responds to disruption with compensatory over-generation marked by increased metacognitive cues and repetitive, low-information continuations; and (iii) coherent CoT behavior depends on a fragile coordination among specialized features, yielding distinct failure modes under perturbation but a consistently impaired output structure.

Test-time compute scaling is a primary driver of performance in large reasoning models (LRMs), but extreme inefficiency bounds current approaches, shifting the critical question from \emph{how much} compute to spend, to \emph{where} to allocate it. We formalize test-time reasoning as a constrained compute allocation problem over partial trajectories. Under a fixed hardware budget, existing paradigms fail to actively allocate the compute to the most promising partial progress: traditional parallel sampling treats traces independently and induces severe memory bottlenecks, while subtractive pruning starves hardware and fails to actively and sufficiently shift the output distribution. To overcome this dichotomy, we introduce Gambit, an inference algorithm that executes \emph{thought-level beam search}. By periodically pruning unpromising trajectories and immediately branching from high-quality prefixes, Gambit dynamically concentrates compute onto the most promising reasoning traces via a light-weight scorer probing hidden states while maintaining continuous high hardware utilization. Extensive evaluations across multiple models and benchmarks demonstrate that Gambit strictly dominates existing baselines. Under identical hardware constraints, our method yields up to a +6.7% absolute accuracy gain on HMMT-24 and +3.3% on AIME-25 over pruning baselines, delivers $>2\times$ higher throughput on trace completion, and reduces total token consumption by up to 68.5% relative to standard parallel sampling.

Reasoning language models increasingly use test-time compute to improve performance, but existing evaluations typically study this compute one question at a time. Yet when multiple problems share an end-to-end cost or latency constraint, models must decide how to divide limited inference compute among them. We introduce an exam-style evaluation framework for studying this setting, in which a model must distribute one shared token budget across questions with different difficulty and point values to maximize its total score. Across several open and frontier reasoning models, we find that models fail to allocate a shared budget strategically across questions of varying difficulties and values. Models behave largely as greedy sequential solvers: they prioritize questions by presentation order, front-load effort on early questions, and remain insensitive to value, with these tendencies becoming more pronounced as the number of questions grows. Explicit planning prompts spread compute more evenly but do not produce value- or difficulty-aware prioritization. The same behavioral pattern extends from mathematical to code reasoning. These findings establish global budget allocation as a distinct capability that is not captured by conventional per-question evaluation and remains a challenge for current reasoning models.

Ultra-long egocentric video understanding requires reasoning over temporally sparse evidence distributed across hours or days, challenging current multimodal models with limited context and the grounding of key video segments. While Chain-of-Tool-Thought (CoTT) agent systems enable iterative retrieval and inspection, they suffer from error propagation due to rigid zoom-in strategies that lack recovery mechanisms. In this work, we address these challenges through SCOUT (Self-Checking Chain-Of-Tool-thought), a recovery-aware agentic framework introducing an adaptive policy that evaluates intermediate tool observations and dynamically trades off exploitation (zoom-in) and exploration (region switching), enabling robust multi-hop reasoning over extremely long horizons. However, training such multi-turn tool-using agents remains challenging, as existing RL methods rely on sparse outcome-level rewards and lack supervision over extended decision trajectories, resulting in suboptimal credit assignment for long-horizon reasoning. To address this, we develop UPS-GRPO, an uncertainty-prioritized policy optimization method that concentrates exploration on high-uncertainty post-tool states while preserving sample efficiency. We further introduce a turn-level advantage decomposition that integrates outcome rewards with tool-grounded temporal alignment rewards for improved credit assignment. Experiments show that SCOUT achieves state-of-the-art results on ultra-long egocentric benchmarks, while remaining competitive on shorter-horizon long-video settings.

Large reasoning models (LRMs) are prone to hallucination, which undermines their reliability and poses challenges for safe deployment. Hallucinations in LRMs arise from two distinct failure sources: reasoning hallucination, where flawed inference steps propagate to an incorrect conclusion, and knowledge hallucination, where the model lacks the requisite factual knowledge to answer the query. To address reasoning hallucination, we propose REIN, an alignment framework that trains LRMs to produce a structured reasoning sequence, \texttt{<think>} $$\rightarrow \texttt{<reflection>} $$\rightarrow $\texttt{<answer>}$, enabling explicit self-reflection before committing to a final answer. To address knowledge hallucination, REIN introduces a reward mechanism that encourages explicit abstention (e.g., "I don't know") when none of the sampled reasoning chains yields a correct answer, allowing the model to refrain from unsupported predictions. Extensive evaluations on mathematical and commonsense reasoning benchmarks show that REIN consistently improves selective accuracy, reduces incorrect-but-self-endorsed responses, and maintains high coverage compared with competitive baselines. Notably, REIN achieves these gains within a single forward pass, without requiring process supervision, inference-time controllers, external search, or multi-round critiques. Experiments on multiple backbones show that REIN reduces the hallucination proxy by $58\sim72\%$ relative to the base models while maintaining $86\sim91\%$ average coverage, and improves selective accuracy on attempted questions by $6.6\sim14.2\%$.