LLM Reasoning

LLM: Large Language Model

Ask about this topic

Overview

This field asks how language models can carry out multi-step inference across mathematics, coding, logic, science, and real-world tasks, and how to tell robust reasoning from pattern matching. Common approaches include chain-of-thought prompting, self-consistency and tree search at inference time, tool use and symbolic verification, and post-training with supervised traces, reinforcement learning from verifiable rewards, or process feedback. Researchers are also exploring latent and recurrent computation to reduce reliance on long written traces, alongside benchmarks that test compositionality, robustness, and long-horizon execution. A central tension is that more computation can improve accuracy but raise cost, while plausible explanations and correct final answers do not by themselves establish faithful, reliable reasoning.

Latest papers

CardsList

931 papers105 papers in the last four weeks, up 27% on the four weeks before. 0.6% of all new papers.

Oct 10, 2025

Deductive Logic in Language Models: Horizontal vs Vertical Reasoning

Recent language models exhibit significant logical reasoning abilities, yet the mechanisms supporting deductive inference remain poorly understood. This paper studies small transformer-based language models trained from scratch on multi-step deductive tasks, focusing on the distinction between horizontal reasoning, where intermediate steps are generated autoregressively, and vertical reasoning, where inference unfolds implicitly across layers before the first output token is produced. We analyze two synthetic tasks: logical consequence over chains of symbolic implications and root-to-leaf navigation in binary trees. Mechanistic interpretability reveals that Chain-of-Thought supervision enables models to learn rule-based inference rather than statistical shortcuts. In the horizontal setting, a shallow attention-only model develops interpretable circuits for rule completion, rule chaining, and final decision making, largely implemented through induction-head-like mechanisms. We further introduce a truncated pseudoinverse method to decode the information carried by queries, keys, and values. For vertical reasoning, Chain-of-Thought appears to act less as explicit step-by-step guidance and more as a form of curriculum learning, helping the model acquire increasingly complex reasoning patterns. Without Chain-of-Thought, models tend to memorize or exploit dataset biases. These results provide a low-level account of how transformers can implement deductive reasoning and suggest how Chain-of-Thought may serve different functions in horizontal and vertical reasoning.

Davide Maltoni, Matteo Ferrara

Department of Computer Science and Engineering, University of Bologna, Italy

Transformer InterpretabilityCoT ReasoningImplicit Reasoning in Language ModelsLLM Reasoning
AskPDF
Oct 9, 2025

Group Contrastive Policy Optimization: Learning Beyond the Self-Exploration Limit with Golden Answers

Reinforcement learning with verifiable rewards (RLVR) has become a powerful paradigm for improving the reasoning abilities of large language models, yet group-based methods lose their learning signal when every sampled response receives zero reward. We propose Group Contrastive Policy Optimization (GCPO), a hybrid objective that preserves standard on-policy optimization for informative rollout groups and activates a proximal contrastive objective only when exploration completely fails. The auxiliary objective pairs an offline golden reasoning trajectory with the current policy's failed responses, thereby providing a reliable positive reference and prompt-specific hard negatives without treating the golden trajectory as an on-policy rollout. Its old-policy token probabilities are evaluated through teacher forcing and used solely to constrain the update, rather than as an importance-sampling correction for the teacher distribution. A first-order analysis shows that the resulting update increases a length-normalized likelihood margin between reliable reasoning and observed failures. Experiments across two model scales and 10 core mathematical reasoning benchmarks demonstrate that GCPO improves training efficiency and final reasoning performance over competitive supervised and RLVR baselines.

Hao Wu, Wei Liu, Shizhe Xiang +3

RL for Language Model ReasoningLLM ReasoningReinforcement Learning with Verifiable RewardsContrastive RLGroup Relative Policy Optimization
AskPDF
Oct 9, 2025

oMeBench: Towards Robust Benchmarking of LLMs in Organic Mechanism Elucidation and Reasoning

Organic reaction mechanisms describe the step-wise elementary processes by which reactants transform into intermediates and products, and are fundamental to understanding chemical reactivity and guiding molecular and reaction de-sign. While large language models (LLMs) have shown promise on chemical tasks such as synthesis design, it remains unclear to what extent this reflects genuine chemical reasoning capabilities: the ability to generate chemically valid intermediates, maintain consistency across reaction steps, and follow logically coherent multi-step pathways. To investigate this, we introduce oMeBench, the first large-scale, expert-curated benchmark for organic mechanism reasoning, comprising over 10,000 annotated mechanistic steps with reaction type labels, intermediate structures, and difficulty ratings. To enable fine-grained evaluation, we further propose oMeS, a dynamic scoring framework that jointly assesses step-level logical consistency and chemical structural similarity. Systematic evaluation of state-of-the-art LLMs reveals that while current models exhibit promising chemical intuition, they struggle to produce correct and consistent reasoning across multi-step mechanisms. Notably, combining prompting strategies with fine-tuning enables smaller-scale models to achieve performance comparable to closed-source frontier models. We hope oMeBench will serve as a rigorous foundation for advancing AI systems toward genuine chemical reasoning.

Ruiling Xu, Yifan Zhang

University of Illinois Urbana-Champaign

LLM EvaluationBenchmark DesignLLM Reasoning
AskPDF
Oct 3, 2025

Sample, Align, Synthesize: Graph-Based Response Synthesis with ConGrs

Language models can be sampled multiple times to access the distribution underlying their responses, but existing methods cannot efficiently synthesize rich epistemic signals across different long-form responses. We introduce Consensus Graphs (ConGrs), a flexible DAG-based data structure that represents shared information, as well as semantic variation in a set of sampled LM responses to the same prompt. We construct ConGrs using a light-weight lexical sequence alignment algorithm from bioinformatics, supplemented by the targeted usage of a secondary LM judge. Further, we design task-dependent decoding methods to synthesize a single, final response from our ConGr data structure. Our experiments show that synthesizing responses from ConGrs improves factual precision on two biography generation tasks by up to 31% over an average response and reduces reliance on LM judges by more than 80% compared to other methods. We also use ConGrs for three refusal-based tasks requiring abstention on unanswerable queries and find that abstention rate is increased by up to 56%. We apply our approach to the MATH and AIME reasoning tasks and find an improvement over self-verification and majority vote baselines by up to 6 points of accuracy. We show that ConGrs provide a flexible method for capturing variation in LM responses and using the epistemic signals provided by response variation to synthesize more effective responses.

Sayan Ghosh, Shahzaib Saqib Warraich, Dhruv Tarsadiya +2

Thomas Lord Department of Computer Science, University of Southern California

Text GenerationSelf-Consistency in Language ModelsLLM ReasoningFactual Knowledge in Language Models
AskPDF
Oct 3, 2025

Attention-Aligned Reasoning for Large Language Models

Large Language Models (LLMs) tend to generate a long reasoning chain when solving complex tasks. However, as the reasoning chain extends, critical intermediate steps and the original prompt will be buried in the context, receiving insufficient attention and leading to errors. In this work, we present ATAR, a novel reasoning method that leverages the inherent reasoning structure to steer LLM attention. Our experiments show that ATAR outperforms SOTA methods across six benchmarks, achieving up to 15.39% absolute improvement. Furthermore, with ATAR, "non-reasoning" models achieve comparable or even better performance compared to reasoning models of the same size in most benchmarks. Finally, our ablation studies show that the attention alignment component contributes significantly, and that these improvements are persist under different attentionsteering backends.

Hongxiang Zhang, Yuan Tian, Tianyi Zhang

Purdue University

LLM ReasoningStructured Reasoning in Language ModelsLong-Context Reasoning in Language Models
AskPDF
Oct 2, 2025

How Well Does Mathematical Reasoning Transfer Across Languages in English-Centric LLMs?

Recent advances in Reinforcement Post-Training (RPT) have substantially improved the mathematical reasoning capabilities of large language models (LLMs), but it remains unclear how well such gains transfer across languages. In this work, we study cross-lingual mathematical reasoning transfer in English-centric LLMs under controlled multilingual evaluation. We first evaluate a range of English-centric reasoning models on multilingual mathematical reasoning benchmarks and find that transfer is highly variable across initial model choice, target language, and training paradigm. Through controlled comparative experiments, we further find that stronger English-centric initialization does not necessarily lead to stronger relative transfer efficiency, even when it yields higher multilingual reasoning accuracy. Finally, we show that the largest improvement comes from moving beyond English-only supervision: adding a single parallel language yields a substantial gain, while further gains from additional languages are smaller but consistent. Overall, our results highlight the need to evaluate multilingual mathematical reasoning directly, using both absolute performance and relative transfer-efficiency metrics.

Wen Yang, Junhong Wu, Chong Li +2

School of Artificial Intelligence, University of Chinese Academy of Sciences · Institute of Automation, Chinese Academy of Sciences · Wuhan AI Research

Cross-Lingual Reasoning in Language ModelsCross-Lingual TransferLLM ReasoningMultilingual Language Model Evaluation
AskPDF
Sep 28, 2025

Explore-Execute Chain: Towards an Efficient Structured Reasoning Paradigm

Many LLMs plan before they act, yet planning and execution are often still entangled in one long generation trace, enforced only through prompts, or split across separate components. We argue that these two stages call for different computation: planning benefits from diversity and breadth, whereas execution demands precision and faithful adherence to a chosen strategy. Treating them as a single undifferentiated chain wastes tokens on routine derivation and makes it costly to explore alternative strategies at test time. We present the Explore-Execute Chain (E\textsuperscript{2}C), which keeps both stages in one model but separates them structurally: a stochastic Exploration phase drafts a concise high-level plan, and a deterministic Execution phase carries it out. Causal SFT and RL train this split so that exploration stays informative and execution remains plan-faithful. Once plans are short yet decisive, extra inference compute can be directed to exploration rather than to repeatedly decoding full solutions. On AIME'2024 at K=32K{=}32, E\textsuperscript{2}C-ReAct Loop reaches 53.3% accuracy with only 12.4k tokens, outperforming Tree-of-Thoughts (N=32N{=}32: 50.0%, 71.3k). The same structure also supports lightweight domain adaptation: Exploration-Focused SFT (EF-SFT) updates only the planning phase, uses 3.5% of the tokens required by standard SFT, and improves medical benchmark accuracy by up to 14.5%.

Kaisen Yang, Tinghe Zhang, Rushi Shah +4

1Qizhi Institute · 2Dept. of Computer Science, Tsinghua University · College of AI, Tsinghua University +4

LLM ReasoningStructured ReasoningLLM Inference EfficiencyLLM PlanningTest-Time ScalingEfficient Language Model Reasoning+2
AskPDF
Sep 25, 2025

Predicting LLM Reasoning Performance with Small Proxy Model

Given the prohibitive cost of pre-training large language models, it is essential to leverage smaller proxy models to optimize datasets before scaling up. However, this approach becomes challenging for reasoning capabilities, which exhibit emergent behavior that only appear reliably at larger model sizes, often exceeding 7B parameters. To address this, we introduce rBridge, showing that small proxies (≤\leq1B) can effectively predict large-model reasoning by aligning more closely with (1) the pre-training objective and (2) the target task. rBridge achieves this by weighting negative log-likelihood with task alignment, using reasoning traces from frontier models as gold labels. In our experiments, rBridge (i) reduces dataset ranking costs by over 100x relative to the best baseline, (ii) achieves the strongest correlation across six reasoning benchmarks at 1B to 32B scale, and (iii) zero-shot transfers predictive relationships across pre-training datasets at 1B to 7B scale. These findings indicate that rBridge offers a practical path for exploring reasoning-oriented pre-training at lower cost.

Woosung Koh, Juyoung Suk, Sungjun Han +2

Trillion Labs · KAIST AI · ▽Trillion Labs, ♠KAIST AI

Language Model PretrainingLLM EvaluationTraining Data SelectionLanguage Model ScalingLLM Reasoning
AskPDF
Sep 1, 2025

Vis-CoT: A Human-in-the-Loop Framework for Interactive Visualization and Intervention in LLM Chain-of-Thought Reasoning

Large language models (LLMs) show strong reasoning via chain-of-thought (CoT) prompting, but the process is opaque, which makes verification, debugging, and control difficult in high-stakes settings. We present Vis-CoT, a human-in-the-loop framework that converts linear CoT text into an interactive reasoning graph. Users can visualize the logical flow, identify flawed steps, and intervene by pruning incorrect paths and grafting new, user-defined premises. This shifts interaction from passive observation to active collaboration, steering models toward more accurate and trustworthy conclusions. Across GSM8K and StrategyQA, Vis-CoT improves final-answer accuracy by up to 24 percentage points over non-interactive baselines. A user study also shows large gains in perceived usability and trust. Vis-CoT points to a practical path for more reliable, understandable, and collaborative reasoning by combining LLMs with targeted human oversight.

Kaviraj Pather, Elena Hadjigeorgiou, Arben Krasniqi +4

Department of Computer Science & Engineering University of Mauritius R´eduit 80837, Mauritius · Department of Electrical & Computer Engineering Cyprus University of Technology 3036 Limassol, Cyprus · Faculty of Electrical & Computer Engineering University of Prishtina ”Hasan Prishtina” 10000 Prishtina, Kosovo +4

LLM InterpretabilityHuman-in-the-Loop AIVisual CoTLLM Reasoning
AskPDF
Aug 29, 2025

PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains

Best-of-n sampling improves the accuracy of large language models (LLMs) and large reasoning models (LRMs) by generating multiple candidate solutions and selecting the one with the highest reward. The key challenge for reasoning tasks is designing a scoring function that can identify correct reasoning chains without access to ground-truth answers. We propose Probabilistic Confidence Selection And Ranking (PiCSAR): a simple, training-free method that scores each candidate generation using the joint log-likelihood of the reasoning and final answer. The joint log-likelihood of the reasoning and final answer naturally decomposes into reasoning confidence and answer confidence. PiCSAR achieves substantial gains across diverse benchmarks (+10.18 on MATH500, +9.81 on AIME2025), outperforming baselines with at least 2x fewer samples in 16 out of 20 comparisons. Our analysis reveals that correct reasoning chains exhibit significantly higher reasoning and answer confidence, justifying the effectiveness of PiCSAR.

Joshua Ong Jun Leang, Zheng Zhao, Aryo Pradipta Gema +7

Imperial College London · University of Edinburgh · UCL

Confidence Estimation in Language ModelsBest-of-N SamplingLLM RerankingLLM Uncertainty EstimationAlgorithmic ReasoningLLM Reasoning
AskPDF
Aug 17, 2025

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review

Large Language Models (LLMs) have demonstrated remarkable progress in reasoning across diverse domains. However, effective reasoning in real-world tasks requires adapting the reasoning strategy to the demands of the problem, ranging from fast, intuitive responses to deliberate, step-by-step reasoning and tool-augmented thinking. Drawing inspiration from cognitive psychology, we propose a novel taxonomy of LLM reasoning strategies along two knowledge boundaries: a fast/slow boundary separating intuitive from deliberative processes, and an internal/external boundary distinguishing reasoning grounded in the model's parameters from reasoning augmented by external tools. We systematically survey recent work on adaptive reasoning in LLMs and categorize methods based on key decision factors. We conclude by highlighting open challenges and future directions toward more adaptive, efficient, and reliable LLMs.

Xinda Jia, Jinpeng Li, Zezhong Wang +6

School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China · Huawei Technologies Co., Ltd., Beijing 100084, China · Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong 999077, China +3

Adaptive Reasoning in Language ModelsLLM Tool UseLLM ReasoningLarge Reasoning Models
AskPDF
Aug 13, 2025

Beyond Scaling Law: A Data-Efficient Distillation Framework for Reasoning

Large language models (LLMs) demonstrate remarkable reasoning capabilities in tasks such as algorithmic coding and mathematical problem-solving. Recent methods have improved reasoning through expanded corpus and multistage training combining reinforcement learning and supervised fine-tuning. Although some methods suggest that small but targeted dataset can incentivize reasoning via only distillation, a reasoning scaling laws is still taking shape, increasing computational costs. To address this, we propose a data-efficient distillation framework (DED) that optimizes the Pareto frontier of reasoning distillation. Inspired by the on-policy learning and diverse roll-out strategies of reinforcement learning, the key idea of our approach is threefold: (1) We identify that benchmark scores alone do not determine an effective teacher model. Through comprehensive comparisons of leading reasoning LLMs, we develop a method to select an optimal teacher model. (2) While scaling distillation can enhance reasoning, it often degrades out-of-domain performance. A carefully curated, smaller corpus achieves a balanced trade-off between in-domain and out-of-domain capabilities. (3) Diverse reasoning trajectories encourage the student model to develop robust reasoning skills. We validate our method through evaluations on mathematical reasoning (AIME 2024/2025, MATH-500) and code generation (LiveCodeBench), achieving state-of-the-art results with only 0.8k carefully curated examples, bypassing the need for extensive scaling. Our systematic analysis demonstrates that DED outperforms existing methods by considering factors beyond superficial hardness, token length, or teacher model capability. This work offers a practical and efficient pathway to advanced reasoning while preserving general capabilities.

Xiaojun Wu, Xiaoguang Jiang, Huiyang Li +11

1Zhongxing Telecom Equipment(ZTE), China · 2China Mobile Communications Group Co Ltd

CoT DistillationLanguage Model DistillationAlgorithmic ReasoningLLM ReasoningData-Efficient Learning
AskPDF
Aug 7, 2025

FedCoT: Communication-Efficient Federated Reasoning Enhancement for Large Language Models

Enhancing LLM reasoning in federated settings is nontrivial due to stringent computational, communication, and privacy constraints, especially in healthcare, where clinically consequential decisions require not only accuracy but also interpretable, auditable rationales to meet safety, accountability, and regulatory requirements. Conventional federated fine-tuning largely imitates final answers rather than cultivating step-by-step reasoning, often relying on privacy-sensitive centralized distillation and still incurring substantial communication overhead. We address this gap with \ours{}, a federated reasoning framework that combines lightweight chain-of-thought resampling with a compact discriminator for selection, and client-aware LoRA stacking with weighted classifier aggregation to accommodate heterogeneity while reducing aggregation noise and communication; clients generate candidate chains and supervision locally, and only lightweight modules are aggregated on the server. Experiments on medical reasoning benchmarks show consistent gains under tight resource budgets while keeping data local and respecting privacy, offering an interpretable and resource-efficient solution. Our code is made publicly available at https://github.com/DIaacKr/FedCoT

Chuan Li, Qianyi Zhao, Fengran Mo +1

East China Normal University, China · University of Montreal, Canada

Communication-Efficient Distributed TrainingMedical LLMsLLM ReasoningFederated Learning
AskPDF
Aug 6, 2025

From "Aha Moments" to Controllable Thinking: Toward Meta-Cognitive Reasoning in Large Reasoning Models via Decoupled Reasoning and Control

Large Reasoning Models (LRMs) can exhibit step-by-step reasoning, reflection, and backtracking, but these behaviors are often unregulated, leading to overthinking. As a result, LRMs continue generating redundant reasoning even after reaching high-confidence conclusions. This increases inference cost and latency, limiting practical deployment. The root cause is the absence of an intrinsic mechanism to monitor the reasoning state and decide when to continue, backtrack, or stop. We propose MERA, a meta-cognitive reasoning framework that decouples reasoning from control to enable independent optimization of control strategies. MERA constructs high-quality reasoning-control supervision data via a takeover-based pipeline, and transforms long-horizon traces into structured reasoning-control alternating sequences for training. The model is trained with supervised fine-tuning to internalize the structured separation, and further optimized with Control-Segment Policy Optimization (CSPO), which combines segment-wise GRPO with control masking to focus learning on control segments. Experiments across reasoning benchmarks show that MERA improves both efficiency and accuracy.

Rui Ha, Rui Pu, Chaozhuo Li +2

Beijing University of Posts and Telecommunications, China · 2Chongqing University of Posts and Telecommunications, China

RL for Language Model ReasoningLLM Inference AccelerationLLM ReasoningLarge Reasoning Models
AskPDF
Jul 20, 2025

Knowing When to Critique: Task-Adaptive Metacognitive Regulation for Reliable LLM Reasoning

Large language models (LLMs) reason fluently but do not regulate their reasoning: they apply uniform scrutiny to every input, which leaves them vulnerable to adversarial and counterfactual prompts, while indiscriminate critique over-corrects answers that were already sound. We propose MetaCrit, a multi-agent framework grounded in Nelson and Narens' metacognitive regulation theory that calibrates how much critique each task receives. MetaCrit separates regulation into four agents: an object-level generator, a monitoring agent that assesses response validity, a control agent that critiques logical soundness, and a meta-level synthesizer that reconciles their signals into a regulated response. Adaptivity here is input-conditioned intervention strength within a fixed pipeline: all four agents run on every input and what varies is the direction and magnitude of the correction they produce, not which stages execute. Across reasoning, safety, and bias benchmarks, MetaCrit improves truthfulness and logical soundness and reaches zero toxicity on BOLD and HONEST without a reasoning trade-off, whereas the same critique applied indiscriminately degrades performance. The cost is four calls per query, about one sixth of the cost of a dedicated reasoning model of similar accuracy. A writing study shows that MetaCrit is preferred for critical-thinking support, and its agents transfer to existing frameworks without architectural change. Code is available at https://github.com/Paparare/EduThink4AI.

Xinmeng Hou, Ziting Chang, Zhouquan Lu +5

Nanyang Technological University · Unicorn Verse · Shanghai Jiao Tong University +3

LLM Self-CorrectionMulti-Agent LLMsMetacognition in Language ModelsLLM Reasoning
AskPDF
Jun 25, 2025

ππ-CoT: Prolog-Initialized Chain-of-Thought Prompting for Multi-Hop Question-Answering

Chain-of-Thought (CoT) prompting significantly enhances large language models' (LLMs) problem-solving capabilities, but still struggles with complex multi-hop questions, often falling into circular reasoning patterns or deviating from the logical path entirely. This limitation is particularly acute in retrieval-augmented generation (RAG) settings, where obtaining the right context is critical. We introduce Prolog-Initialized Chain-of-Thought (ππ-CoT), a novel prompting strategy that combines logic programming's structural rigor with language models' flexibility. ππ-CoT reformulates multi-hop questions into Prolog queries decomposed as single-hop sub-queries. These are resolved sequentially, producing intermediate artifacts, with which we initialize the subsequent CoT reasoning procedure. Extensive experiments demonstrate that ππ-CoT matches or outperforms standard RAG and in-context CoT on multi-hop question-answering benchmarks, with the largest gains on questions for which retrieval surfaces the necessary evidence.

Chao Wan, Albert Gong, Mihir Mishra +3

Cornell University.

Multi-Hop QALLM PromptingLLM ReasoningCoT ReasoningRetrieval-Augmented Generation
AskPDF
Jun 23, 2025

Adaptive Activation Steering for Efficient LLM Reasoning via Closed-Loop PID Control

Reasoning LLMs trained with long chain-of-thought often overthink: they spend tokens on redundant reflection and transitions that inflate cost without improving accuracy. Static activation steering (e.g.\ SEAL) suppresses such content with a fixed vector, but applies the same strength regardless of how redundant the current chunk actually is. We describe PID-steering, a training-free, decoding-time method that modulates the steering strength with a PID controller driven by a lightweight chunk-level redundancy classifier. On a subset of GSM8K with DeepSeek-R1-Distill-Qwen-1.5B, the method improves accuracy from 85.7% to 89.6% (+3.9 pp) while cutting average output length from 1026 to 790 tokens (−-23%). We report it as a small-scale proof of concept rather than a benchmark result.

Aryasomayajula Ram Bharadwaj

Independent Researcher

Language Model SteeringEfficient Language Model InferenceActivation SteeringPID ControlLLM Reasoning
AskPDF
Jun 16, 2025

Code Reasoning for Software Engineering Tasks: A Survey and A Call to Action

The rise of large language models (LLMs) has led to dramatic improvements across a wide range of natural language tasks. Their performance on certain tasks can be further enhanced by incorporating test-time reasoning techniques. These inference-time advances have been adopted into the code domain, enabling complex software engineering (SWE) tasks such as code generation, test generation and issue resolution. However, the impact of different reasoning techniques on code-centric SWE tasks has not been systematically explored. In this work, we survey code reasoning techniques that underpin these capabilities, with a focus on test-time compute and inference-time reasoning paradigms. We examine a variety of code-specific reasoning methods and progressively build up to SWE agents, which combine planning, tool use, and multi-step interaction. We also compare the impact of different techniques on coding tasks, highlighting their relative importance and outlining open challenges and future research directions. Across commonly used models and benchmarks, we find that approaches exploiting code-specific signals (e.g., structure and execution feedback) are frequently associated with improved performance, motivating a dedicated study of code reasoning beyond natural-language reasoning.

Saurabh Pujar, Ira Ceka, Irene Manotas +3

IBM · Columbia University

Software Engineering AgentsExecution-Guided Code GenerationAgentic Code GenerationLLM Reasoning
AskPDF
Jun 16, 2025

BOW: Training Language Models to Reason Over Plausible Next Words

Next-word prediction (NWP) trains language models against a single observed continuation, even though many contexts admit multiple plausible next words. Recent RL-based next-word reasoning methods make this tension explicit: they reward a model for producing a rationale that supports one context-conditioned continuation, which can turn a pre-existing preference into a confident, self-justifying trajectory. We introduce BOW, an RL framework that instead trains models to produce self-contained, neutral, and comprehensive descriptions of the plausible next-word space. The policy generates a next-word reasoning trajectory from the full context, but a frozen scorer computes the core reward from that trajectory alone, without separately receiving the context. BOW-Reg adds a lightweight breadth regularizer to this core reward to discourage premature collapse. On two model backbones, BOW remains competitive with the original models and often outperforms trained baselines across ten general reasoning benchmarks. On benchmarks testing ambiguous references and word meanings, BOW-Reg achieves the highest SharedRef correctness and the lowest HoWN-Simple single-sense collapse on both backbones. Human evaluation further shows that BOW-Reg produces broader next-word reasoning trajectories, while direct next-word-prediction evaluation shows that these trajectories remain predictive.

Ming Shen, Zhikun Xu, Jacob Dineen +2

Arizona State University

RL for Language Model ReasoningNext-Token PredictionLanguage Model Post-TrainingText GenerationLLM Reasoning
AskPDF
May 29, 2025

SocialMaze: A Benchmark for Evaluating and Enhancing Social Reasoning in Large Language Models in Complex Social Environments

Large language models (LLMs) are increasingly deployed in socially grounded applications, where success requires interpreting context, inferring others' mental states, and reasoning about unreliable information. Yet existing benchmarks rarely evaluate these demands jointly in complex, evolving settings. We introduce SocialMaze, a benchmark that organizes six tasks across social deduction games, daily-life interactions, and digital community platforms along three descriptive design axes: deep reasoning, dynamic interaction, and information uncertainty. These axes characterize intended sources of task difficulty rather than latent, factor-analytic dimensions of model capability. Automated checks and human validation support data quality. Evaluations of twelve proprietary and open-weight LLMs show substantial variation in the use of evolving interaction histories; stronger chain-of-thought reasoners perform better on tasks requiring deeper inference, while uncertainty consistently degrades performance. Reasoning workflows help weaker short-chain-of-thought backbones but saturate on stronger reasoners. Finally, targeted fine-tuning on curated reasoning traces substantially improves structured social-reasoning tasks, whereas transfer to language-aggregation tasks remains statistically inconclusive. The project homepage is available at https://xzx34.github.io/socialmaze/.

Zixiang Xu, Yanbo Wang, Yue Huang +13

Mohamed bin Zayed University of Artificial Intelligence · University of Southern California · University of Notre Dame +3

LLM EvaluationAI Agent BenchmarksSocial ReasoningLLM Reasoning
AskPDF
May 29, 2025

PBEBench: A Multi-Step Programming by Examples Reasoning Benchmark inspired by Historical Linguistics

Although many benchmarks evaluate the reasoning abilities of Large Language Models (LLMs) within domains such as mathematics, coding, or data wrangling, few abstract away from domain specifics to examine reasoning as a capability in and of itself. We contribute a novel type of benchmark evaluating the inductive reasoning capabilities of LLMs that is inspired by the forward reconstruction task from historical linguistics but is formulated in an extremely simple, general way (in the form of Programming by Examples). The task involves generating a cascade of simple string rewrite programs to transform a given list of input strings into a list of desired output strings. We present a fully automated pipeline that programmatically generates problems of this type with controllable difficulty, enabling scalable evaluation of reasoning models while avoiding contamination. Using this approach, we construct two benchmarks: PBEBench-Lite, which efficiently stratifies models of varying capabilities, and PBEBench, which requires models to induce programs similar in complexity to those constructed by historical linguists. Our experiments reveal a substantial performance gap between models that leverage test-time compute or LCoT (long chain-of-thought) reasoning and those that do not. Moreover, although recent models show promise, the solve rate for both of them drops below 5% for hard instances of the PBEBench dataset (ground truth cascade lengths of 20 and 30, respectively), falling well short of realistic historical linguistics requirements even with computationally expensive, popular scaling techniques from the PBE and reasoning literature. Additionally, we also study the effectiveness of different scaling strategies and the impact of various hyperparameters on the difficulty of the generated data using gpt-oss-120b, the best-performing open-source model.

Atharva Naik, Prakam, Yash Mathur +6

Carnegie Mellon University · Independent Researcher · Ohio State University

Program SynthesisInductive InferenceLLM EvaluationLogical ReasoningSynthetic Benchmark GenerationLLM Reasoning+1
AskPDF
May 28, 2025

Learning Composable Chains-of-Thought

A common approach for teaching large language models (LLMs) to reason is to train on chain-of-thought (CoT) traces of in-distribution reasoning problems, but such annotated data is costly to obtain for every problem of interest. We want reasoning models to generalize beyond their training distribution, and ideally to generalize compositionally: combine atomic reasoning skills to solve harder, unseen reasoning tasks. We take a step towards compositional generalization of reasoning skills when addressing a target compositional task that has no labeled CoT data. We find that simply training models on CoT data of atomic tasks leads to limited generalization, but minimally modifying CoT formats of constituent atomic tasks to be composable can lead to improvements. We can train "atomic CoT" models on the atomic tasks with Composable CoT data and combine them with multitask learning or model merging for better zero-shot performance on the target compositional task. Such a combined model can be further bootstrapped on a small amount of compositional data using rejection sampling fine-tuning (RFT). Results on string operations and natural language skill compositions show that training LLMs on Composable CoT outperforms multitask learning and continued fine-tuning baselines within a given training data budget.

Fangcong Yin, Zeyu Leo Liu, Liu Leqi +2

The University of Texas at Austin · Princeton University

LLM Fine-TuningCoT ReasoningLLM TrainingCompositional GeneralizationLLM Reasoning
AskPDF
May 22, 2025

Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning

Large Language Models (LLMs) have shown impressive performance on complex tasks through Chain-of-Thought (CoT) reasoning. However, conventional CoT relies on explicitly verbalized intermediate steps, which constrains its broader applicability, particularly in abstract reasoning tasks beyond language. To address this, there has been growing research interest in latent CoT reasoning, where the reasoning process is embedded within latent spaces. By decoupling reasoning from explicit language generation, latent CoT offers the promise of richer cognitive representations and facilitates more flexible, faster inference. This paper aims to present a comprehensive overview of this emerging paradigm and establish a systematic taxonomy. We analyze recent advances in methods, categorizing them from token-wise horizontal approaches to layer-wise vertical strategies. We then provide in-depth discussions of these methods, highlighting their design principles, applications, and remaining challenges. We hope that our survey provides a structured foundation for advancing this promising direction in LLM reasoning. The relevant papers will be regularly updated at https://github.com/EIT-NLP/Awesome-Latent-CoT.

Xinghao Chen, Anhao Zhao, Heming Xia +7

Department of Computing, The Hong Kong Polytechnic University · Ningbo Digital Twin Institute, Eastern Institute of Technology, Ningbo, China

CoT ReasoningLLM ReasoningLatent CoT Reasoning
AskPDF
May 21, 2025

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning

Large reasoning models (LRMs) have achieved remarkable success on complex tasks, yet their tendency to "overthink" leads to inefficiencies. Although "save-thinking" prompts are intended to mitigate this issue, we find that LRMs still frequently enter the "Still-thinking" mode instead of the expected "No-thinking" mode, especially on difficult queries. To analyze this behavioral divergence, we examine LRMs from three perspectives: confidence at the thinking-termination boundary, divergence in internal attention distributions, and attention allocation across prompt segments. We find that high perplexity is associated with later Still-thinking behavior, and that Still-thinking cases allocate more attention to the original question. Based on these observations, we propose an attention intervention method to regulate this behavior. While this intervention suppresses explicit thinking, it also causes a drop in accuracy, suggesting that the suppressed reasoning behavior is often useful for correctness. Our work provides confidence- and attention-level evidence for this behavior, highlighting the trade-off between instruction following, inference efficiency, and reasoning correctness.

Rongzhi Zhu, Yi Liu, Jiancheng Wang +6

State Key Laboratory for Novel Software Technology, Nanjing University, China · China Unicom Software Research Institute, China · National Institute of Healthcare Data Science, Nanjing University, China +1

Overthinking in Language ModelsLLM InterpretabilityEfficient Language Model ReasoningCausal Interventions in Language ModelsLLM ReasoningLarge Reasoning Models
AskPDF
May 13, 2025

Synergizing Large Language Models and Theory for Human-like Causal Reasoning

Performing causal reasoning akin to humans is fundamental to achieving strong artificial intelligence. However, existing studies on causal reasoning and large language models (LLMs) often underestimate the role of human causal cognition. Human causal reasoning is far more than recognizing causes and effects. Humans often factor in many other considerations when establishing a causal link between two events, such as norm violations, intentionality, morality, counterfactual scenarios, etc. To simulate such reasoning, it is intuitive to identify cause-effect pairs using token causality formalisms while modeling the factors that influence human causal judgment using findings from cognitive science experiments. To support the evaluation and modeling of human-like causal reasoning in LLMs, we introduce HCR-Bench, a challenging benchmark with 1,093 instances and detailed human causal reasoning step annotations, and HCR-Reasoner, an approach that systematically integrates theories of token causality and cognitive science into LLMs for human-like causal reasoning. Results suggest that HCR-Reasoner consistently improves LLMs' causal alignment with humans, and that theory-guided reasoning is highly effective.

Yanxi Zhang, Xin Cong, Zhong Zhang +3

Center for Data Science, AAIS, Peking University · Wangxuan Institute of Computer Technology, Peking University · Tsinghua University +1

Causal Reasoning in Language ModelsCausal ReasoningLLM Reasoning
AskPDF
Mar 31, 2025

Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models

Recent advancements in Large Language Models (LLMs) have significantly enhanced their ability to perform complex reasoning tasks, transitioning from fast and intuitive thinking (System 1) to slow and deep reasoning (System 2). While System 2 reasoning improves task accuracy, it often incurs substantial computational costs due to its slow thinking nature and inefficient or unnecessary reasoning behaviors. In contrast, System 1 reasoning is computationally efficient but leads to suboptimal performance. Consequently, it is critical to balance the trade-off between performance (benefits) and computational costs (budgets), giving rise to the concept of reasoning economy. In this survey, we provide a comprehensive analysis of reasoning economy in both the post-training and test-time inference stages of LLMs, encompassing i) the cause of reasoning inefficiency, ii) behavior analysis of different reasoning patterns, and iii) potential solutions to achieve reasoning economy. By offering actionable insights and highlighting open challenges, we aim to shed light on strategies for improving the reasoning economy of LLMs, thereby serving as a valuable resource for advancing research in this evolving area. We also provide a public repository to continually track developments in this fast-evolving field.

Rui Wang, Hongru Wang, Boyang Xue +9

University of Edinburgh, Edinburgh, UK · University of Macau, Macau SAR, China · University of Illinois Urbana-Champaign, USA

LLM Inference EfficiencyCost-Aware InferenceLLM Reasoning
AskPDF
Feb 13, 2025

Thinking beyond the anthropomorphic paradigm benefits LLM research

Anthropomorphism, or the attribution of human traits to technology, is an automatic and unconscious response that occurs even in those with advanced technical expertise. In this position paper, we analyze hundreds of thousands of research articles to present empirical evidence of the prevalence and growth of anthropomorphic terminology in research on large language models (LLMs). We argue for challenging the deeper assumptions reflected in this terminology -- which, though often useful, may inadvertently constrain LLM development -- and broadening beyond them to open new pathways for understanding and improving LLMs. Specifically, we identify and examine five anthropomorphic assumptions that shape research across the LLM development lifecycle. For each assumption (e.g., that LLMs must use natural language for reasoning, or that they should be evaluated on benchmarks originally meant for humans), we demonstrate empirical, non-anthropomorphic alternatives that remain under-explored yet offer promising directions for LLM research and development.

Lujain Ibrahim, Myra Cheng

University of Oxford · Stanford University

Anthropomorphism in AILLM Reasoning
AskPDF
Jan 16, 2025

Foundations of Large Language Models

This is a book about large language models. As indicated by the title, it primarily focuses on foundational concepts rather than comprehensive coverage of all cutting-edge technologies. The book is structured into six main chapters, each exploring a key area: pre-training, generative models, prompting, alignment, inference, and reasoning. It is intended for college students, professionals, and practitioners in natural language processing and related fields, and can serve as a reference for anyone interested in large language models.

Tong Xiao, Jingbo Zhu

NLP Lab, Northeastern University & NiuTrans Research

Language Model PretrainingLLM AlignmentLLM InferenceLLM PromptingLLM Reasoning
AskPDF
Oct 31, 2024

RL-STaR: Theoretical Analysis of Reinforcement Learning Frameworks for Self-Taught Reasoner

The reasoning abilities of large language models (LLMs) have improved with chain-of-thought (CoT) prompting, allowing models to solve complex tasks stepwise. However, training CoT capabilities requires detailed reasoning data, which is often scarce. The self-taught reasoner (STaR) framework addresses this by using reinforcement learning to automatically generate reasoning steps, reducing reliance on human-labeled data. Although STaR and its variants have demonstrated empirical success, a theoretical foundation explaining these improvements is lacking. This work provides a theoretical framework for understanding the effectiveness of reinforcement learning on CoT reasoning and STaR. Our contributions are: (1) criteria for the quality of pre-trained models necessary to initiate effective reasoning improvement; (2) an analysis of policy improvement, showing why LLM reasoning improves iteratively with STaR; (3) conditions for convergence to an optimal reasoning policy; and (4) an examination of STaR's robustness, explaining how it can improve reasoning even when incorporating occasional incorrect steps. We also run RL-STaR on GPT-2, Qwen2.5-0.5B and Phi-3-mini, and the measured return curves follow the ones the analysis predicts. This framework bridges empirical findings with theoretical insights, advancing reinforcement learning approaches for reasoning in LLMs.

Fu-Chieh Chang, Yu-Ting Lee, Hui-Ying Shih +2

MediaTek Research, Taipei, Taiwan · Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan · Department of Mathematical Sciences, National Chengchi University, Taipei, Taiwan +2

Reinforcement LearningRL for Language Model ReasoningLanguage Model Self-ImprovementLLM Reasoning
AskPDF
Sep 9, 2024

IFAR: Multi-Perspective and Multi-Level Causal Discovery with LLMs

Large language models (LLMs) have developed rapidly, and their reasoning capabilities have become a hot research topic. However, there is still limited exploration of abductive reasoning. The multi-perspective and multi-level of causes is one of the core challenges of abductive reasoning, which cannot be solved well by existing methods. We construct a specialized dataset named DeepAbduction, which is designed for tracing the causes of pollution and disease, addressing the lack of datasets in this field. We propose Inverse-Forward Abductive Reasoning (IFAR) framework for LLMs multi-perspective and multi-level abductive reasoning. IFAR is zero-shot and combines generalized backward reasoning with relation-by-relation forward verification. Experimental results show that IFAR achieves an improvement of approximately 40% in the F1 score compared to other methods under mainstream LLMs, while maintaining a balance between recall and precision. Furthermore, IFAR enhances the performance of non-reasoning LLMs to surpass LLMs which have been trained for reasoning, and remains effective when applied to the latter. Code will be released after the acceptance of our work.

Jinwei He, Feng Lu

Beihang University, Beijing, China

Abductive ReasoningCausal Structure LearningLLM Reasoning
AskPDF