{"total":52,"rows":[{"id":"2409.12183","title":"To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning","created":"2024-09-18","cited_by_count":263,"area":"lr"},{"id":"2502.02542","title":"OverThink: Slowdown Attacks on Reasoning LLMs","created":"2025-02-04","cited_by_count":96,"area":"lr"},{"id":"2410.05695","title":"Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thought","created":"2024-10-08","cited_by_count":56,"area":"lr"},{"id":"2402.16048","title":"How Likely Do LLMs with CoT Mimic Human Reasoning?","created":"2024-02-25","cited_by_count":34,"area":"lr"},{"id":"2505.18237","title":"Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens","created":"2025-05-23","cited_by_count":34,"area":"lr"},{"id":"2502.16906","title":"AutoLogi: Automated Generation of Logic Puzzles for Evaluating Reasoning Abilities of Large Language Models","created":"2025-02-24","cited_by_count":31,"area":"lr"},{"id":"2411.12498","title":"Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus","created":"2024-11-19","cited_by_count":29,"area":"lr"},{"id":"2506.08295","title":"From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?","created":"2025-06-09","cited_by_count":23,"area":"lr"},{"id":"2501.14851","title":"JustLogic: A Comprehensive Benchmark for Evaluating Deductive Reasoning in Large Language Models","created":"2025-01-24","cited_by_count":22,"area":"lr"},{"id":"2506.17088","title":"Chain-of-Thought Prompting Obscures Hallucination Cues in Large Language Models: An Empirical Evaluation","created":"2025-06-20","cited_by_count":21,"area":"lr"},{"id":"2603.13260","title":"Explain in Your Own Words: Improving Reasoning via Token-Selective Dual Knowledge Distillation","created":"2026-02-25","cited_by_count":16,"area":"lr"},{"id":"2509.11656","title":"MALLM: Multi-Agent Large Language Models Framework","created":"2025-09-15","cited_by_count":15,"area":"lr"},{"id":"2502.20377","title":"PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation","created":"2025-02-27","cited_by_count":14,"area":"lr"},{"id":"2506.01341","title":"TurnBench-MS: A Benchmark for Evaluating Multi-Turn, Multi-Step Reasoning in Large Language Models","created":"2025-06-02","cited_by_count":13,"area":"lr"},{"id":"2506.12241","title":"Privacy Reasoning in Ambiguous Contexts","created":"2025-06-13","cited_by_count":11,"area":"lr"},{"id":"2406.12084","title":"When Reasoning Meets Information Aggregation: A Case Study with Sports Narratives","created":"2024-06-17","cited_by_count":7,"area":"lr"},{"id":"2502.14643","title":"Length-Controlled Margin-Based Preference Optimization without Reference Model","created":"2025-02-20","cited_by_count":6,"area":"lr"},{"id":"2505.16686","title":"SPaRC: A Spatial Pathfinding Reasoning Challenge","created":"2025-05-22","cited_by_count":5,"area":"lr"},{"id":"2604.08016","title":"Wiring the 'Why': A Unified Taxonomy and Survey of Abductive Reasoning in LLMs","created":"2026-04-09","cited_by_count":5,"area":"lr"},{"id":"2410.01772","title":"DeFine: Decision-Making with Analogical Reasoning over Factor Profiles","created":"2024-10-02","cited_by_count":4,"area":"lr"},{"id":"2501.05712","title":"Multi-Step Reasoning in Korean and the Emergent Mirage","created":"2025-01-10","cited_by_count":4,"area":"lr"},{"id":"2505.15712","title":"TurnaboutLLM: A Deductive Reasoning Benchmark from Detective Games","created":"2025-05-21","cited_by_count":4,"area":"lr"},{"id":"2506.06008","title":"Token Signature: Predicting Chain-of-Thought Gains with Token Decoding Feature in Large Language Models","created":"2025-06-06","cited_by_count":4,"area":"lr"},{"id":"2506.17251","title":"Training-free LLM Verification via Recycling Few-shot Examples","created":"2025-06-08","cited_by_count":4,"area":"lr"},{"id":"2502.17169","title":"Logic Haystacks: Probing LLMs Long-Context Logical Reasoning (Without Easily Identifiable Unrelated Padding)","created":"2025-02-24","cited_by_count":3,"area":"lr"},{"id":"2503.06218","title":"SCoRE: Benchmarking Long-Chain Reasoning in Commonsense Scenarios","created":"2025-03-08","cited_by_count":3,"area":"lr"},{"id":"2506.14927","title":"MDBench: A Synthetic Multi-Document Reasoning Benchmark Generated with Knowledge Guidance","created":"2025-06-17","cited_by_count":3,"area":"lr"},{"id":"2509.24239","title":"ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language Models","created":"2025-09-29","cited_by_count":3,"area":"lr"},{"id":"2604.04942","title":"TDA-RC: Task-Driven Alignment for Knowledge-Based Reasoning Chains in Large Language Models","created":"2026-03-13","cited_by_count":3,"area":"lr"},{"id":"2604.06389","title":"SELFDOUBT: Uncertainty Quantification for Reasoning LLMs via the Hedge-to-Verify Ratio","created":"2026-04-07","cited_by_count":3,"area":"lr"},{"id":"2509.01619","title":"Throttling Web Agents Using Reasoning Gates","created":"2025-09-01","cited_by_count":2,"area":"lr"},{"id":"2509.16866","title":"seqBench: A Tunable Benchmark to Quantify Sequential Reasoning Limits of LLMs","created":"2025-09-21","cited_by_count":2,"area":"lr"},{"id":"2510.18814","title":"A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning","created":"2025-10-21","cited_by_count":2,"area":"lr"},{"id":"2510.21007","title":"Can Confidence Estimates Decide When Chain-of-Thought Is Necessary for LLMs?","created":"2025-10-23","cited_by_count":2,"area":"lr"},{"id":"2602.00127","title":"ALIGN: Aligned Delegation with Performance Guarantees for Multi-Agent LLM Reasoning","created":"2026-01-28","cited_by_count":2,"area":"lr"},{"id":"2602.02103","title":"How Far Ahead Do LLMs Plan? Uncovering the Latent Horizon in Chain-of-Thought Reasoning","created":"2026-02-02","cited_by_count":2,"area":"lr"},{"id":"2602.08693","title":"Reasoning aligns language models to human cognition","created":"2026-02-09","cited_by_count":2,"area":"lr"},{"id":"2602.16154","title":"Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution","created":"2026-02-18","cited_by_count":2,"area":"lr"},{"id":"2605.22873","title":"When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions","created":"2026-05-20","cited_by_count":2,"area":"lr"},{"id":"2606.03969","title":"Quantifying Faithful Confidence Expression in Large Reasoning Models","created":"2026-06-02","cited_by_count":2,"area":"lr"},{"id":"2607.27783","title":"Reasoning Consensus: Structural Ensembling of LLM Reasoning via Weighted DAG Aggregation","created":"2026-07-30","cited_by_count":2,"area":"lr"},{"id":"2510.14200","title":"RLSR: Reinforcement Learning with Supervised Reward Outperforms SFT in Instruction Following","created":"2025-10-16","cited_by_count":1,"area":"lr"},{"id":"2510.23868","title":"GIFT: Group-Relative Implicit Fine-Tuning Integrates GRPO with DPO and UNA","created":"2025-10-27","cited_by_count":1,"area":"lr"},{"id":"2601.07794","title":"Kinship Data Benchmark for Multi-hop Reasoning","created":"2026-01-12","cited_by_count":1,"area":"lr"},{"id":"2606.29654","title":"Budgeted Act-or-Defer Multi-Agent LLM Deliberation with Local Reliability Bounds","created":"2026-06-28","cited_by_count":1,"area":"lr"},{"id":"2602.05946","title":"f-GRPO and Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment","created":"2026-02-05","cited_by_count":0,"area":"lr"},{"id":"2605.11625","title":"Nice Fold or Hero Call: Learning Budget-Efficient Thinking for Adaptive Reasoning","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2606.02994","title":"Inducing Reasoning Primitives from Agent Traces","created":"2026-06-02","cited_by_count":0,"area":"lr"},{"id":"2606.13020","title":"SciR: A Controllable Benchmark for Scientific Reasoning in LLMs","created":"2026-06-11","cited_by_count":0,"area":"lr"},{"id":"2608.05152","title":"Mean-Field Dynamics of Chain-of-Thought Reasoning in Large Language Models","created":"2026-05-20","cited_by_count":0,"area":"lr"},{"id":"2608.14791","title":"CEDAR-GRPO: Process-Aware Reinforcement Learning for General Abductive Reasoning in LLMs","created":"2026-08-14","cited_by_count":0,"area":"lr"},{"id":"2610.00940","title":"ReHoPER: Receding-Horizon Planning for Enhanced Reasoning","created":"2026-10-01","cited_by_count":0,"area":"lr"}],"next_cursor":null}