{"total":92,"rows":[{"id":"2509.20328","title":"Video models are zero-shot learners and reasoners","created":"2025-09-24","cited_by_count":220,"area":"lr"},{"id":"2503.21614","title":"A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond","created":"2025-03-27","cited_by_count":132,"area":"lr"},{"id":"2504.21370","title":"ShorterBetter: Guiding Reasoning Models to Find Optimal Inference Length for Efficient Reasoning","created":"2025-04-30","cited_by_count":72,"area":"lr"},{"id":"2505.21318","title":"Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations","created":"2025-05-27","cited_by_count":49,"area":"lr"},{"id":"2502.09061","title":"CRANE: Reasoning with constrained LLM generation","created":"2025-02-13","cited_by_count":38,"area":"lr"},{"id":"2507.02076","title":"Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs","created":"2025-07-02","cited_by_count":31,"area":"lr"},{"id":"2509.12235","title":"RL Fine-Tuning Heals OOD Forgetting in SFT","created":"2025-09-08","cited_by_count":31,"area":"lr"},{"id":"2503.07832","title":"RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Code","created":"2025-03-10","cited_by_count":30,"area":"lr"},{"id":"2505.16838","title":"R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search","created":"2025-05-22","cited_by_count":30,"area":"lr"},{"id":"2410.19599","title":"Take Caution in Using LLMs as Human Surrogates: Scylla Ex Machina","created":"2024-10-25","cited_by_count":29,"area":"lr"},{"id":"2511.16660","title":"Cognitive Foundations for Reasoning and Their Manifestation in LLMs","created":"2025-11-20","cited_by_count":26,"area":"lr"},{"id":"2502.02362","title":"Premise-Augmented Reasoning Chains Improve Error Identification in Math reasoning with LLMs","created":"2025-02-04","cited_by_count":22,"area":"lr"},{"id":"2412.15118","title":"Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation","created":"2024-12-19","cited_by_count":21,"area":"lr"},{"id":"2510.01833","title":"Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning","created":"2025-10-02","cited_by_count":19,"area":"lr"},{"id":"2511.20100","title":"QiMeng-Kernel: Macro-Thinking Micro-Coding Paradigm for LLM-Based High-Performance GPU Kernel Generation","created":"2025-11-25","cited_by_count":19,"area":"lr"},{"id":"2511.09092","title":"OR-R1: Automating Modeling and Solving of Operations Research Optimization Problem via Test-Time Reinforcement Learning","created":"2025-11-12","cited_by_count":17,"area":"lr"},{"id":"2508.03012","title":"Tool-integrated Reinforcement Learning for Repo Deep Search","created":"2025-08-05","cited_by_count":15,"area":"lr"},{"id":"2510.09388","title":"Don't Tell the Answer, Truly Guide the Reasoning During RL Rollouts","created":"2025-10-10","cited_by_count":14,"area":"lr"},{"id":"2510.00938","title":"Large Reasoning Models Learn Better Alignment from Flawed Thinking","created":"2025-10-01","cited_by_count":13,"area":"lr"},{"id":"2505.20223","title":"Chain-of-Thought for Autonomous Driving: A Comprehensive Survey and Future Prospects","created":"2025-05-26","cited_by_count":12,"area":"lr"},{"id":"2508.10118","title":"From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation","created":"2025-08-13","cited_by_count":12,"area":"lr"},{"id":"2509.01822","title":"When LLM Meets Time Series: Can LLMs Perform Multi-Step Time Series Reasoning and Inference","created":"2025-09-01","cited_by_count":12,"area":"lr"},{"id":"2506.11027","title":"From Reasoning to Code: GRPO Optimization for Underrepresented Languages","created":"2025-05-20","cited_by_count":11,"area":"lr"},{"id":"2604.02547","title":"Beyond Resolution Rates: Behavioral Drivers of Coding Agent Success and Failure","created":"2026-04-02","cited_by_count":11,"area":"lr"},{"id":"2504.02181","title":"A Survey of Scaling in Large Language Model Reasoning","created":"2025-04-02","cited_by_count":10,"area":"lr"},{"id":"2505.17447","title":"LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization","created":"2025-05-23","cited_by_count":10,"area":"lr"},{"id":"2509.23392","title":"Your Models Have Thought Enough: Training Large Reasoning Models to Stop Overthinking","created":"2025-09-27","cited_by_count":10,"area":"lr"},{"id":"2511.01633","title":"Scaling Graph Chain-of-Thought Reasoning: A Multi-Agent Framework with Efficient LLM Serving","created":"2025-11-03","cited_by_count":10,"area":"lr"},{"id":"2512.24574","title":"Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time","created":"2025-12-31","cited_by_count":10,"area":"lr"},{"id":"2508.05710","title":"Klear-CodeTest: Scalable Test Case Generation for Code Reinforcement Learning","created":"2025-08-07","cited_by_count":9,"area":"lr"},{"id":"2505.20072","title":"Incentivizing Strong Reasoning from Weak Supervision","created":"2025-05-26","cited_by_count":8,"area":"lr"},{"id":"2506.06211","title":"PuzzleWorld: A Benchmark for Multimodal, Open-Ended Reasoning in Puzzlehunts","created":"2025-06-06","cited_by_count":8,"area":"lr"},{"id":"2601.22069","title":"VTC-R1: Vision-Text Compression for Efficient Long-Context Reasoning","created":"2026-01-29","cited_by_count":8,"area":"lr"},{"id":"2410.11900","title":"FLARE: Faithful Logic-Aided Reasoning and Exploration","created":"2024-10-14","cited_by_count":7,"area":"lr"},{"id":"2505.19501","title":"Toward Scientific Reasoning in LLMs: Training from Expert Discussions via Reinforcement Learning","created":"2025-05-26","cited_by_count":7,"area":"lr"},{"id":"2601.15495","title":"Tracking the Limits of Knowledge Propagation: How LLMs Fail at Multi-Step Reasoning with Conflicting Knowledge","created":"2026-01-21","cited_by_count":7,"area":"lr"},{"id":"2607.26760","title":"Metis: Memory Foundation Model","created":"2026-07-29","cited_by_count":7,"area":"lr"},{"id":"2505.03418","title":"Knowledge Augmented Complex Problem Solving with Large Language Models: A Survey","created":"2025-05-06","cited_by_count":6,"area":"lr"},{"id":"2508.20737","title":"Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocol","created":"2025-08-28","cited_by_count":6,"area":"lr"},{"id":"2511.00640","title":"DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching","created":"2025-11-01","cited_by_count":6,"area":"lr"},{"id":"2603.11226","title":"ExecVerify: White-Box RL with Verifiable Stepwise Rewards for Code Execution Reasoning","created":"2026-03-11","cited_by_count":6,"area":"lr"},{"id":"2603.16475","title":"Breaking the Chain: A Causal Analysis of LLM Faithfulness to Intermediate Structures","created":"2026-03-17","cited_by_count":6,"area":"lr"},{"id":"2410.13510","title":"GeoCoder: Solving Geometry Problems by Generating Modular Code through Vision-Language Models","created":"2024-10-17","cited_by_count":5,"area":"lr"},{"id":"2511.13223","title":"TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs","created":"2025-11-17","cited_by_count":5,"area":"lr"},{"id":"2512.23988","title":"Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning Process","created":"2025-12-30","cited_by_count":5,"area":"lr"},{"id":"2504.09100","title":"A Short Survey on Small Reasoning Models: Training, Inference, Applications and Research Directions","created":"2025-04-12","cited_by_count":4,"area":"lr"},{"id":"2506.06971","title":"Chain-of-Code Collapse: Reasoning Failures in LLMs via Adversarial Prompting in Code Generation","created":"2025-06-08","cited_by_count":4,"area":"lr"},{"id":"2506.13932","title":"Code Reasoning for Software Engineering Tasks: A Survey and A Call to Action","created":"2025-06-16","cited_by_count":4,"area":"lr"},{"id":"2602.12056","title":"LawThinker: A Deep Research Legal Agent in Dynamic Environments","created":"2026-02-12","cited_by_count":4,"area":"lr"},{"id":"2604.02819","title":"Student-in-the-Loop Chain-of-Thought Distillation via Generation-Time Selection","created":"2026-04-03","cited_by_count":4,"area":"lr"},{"id":"2606.14142","title":"Implicit Reasoning for Large Language Model-based Generative Recommendation","created":"2026-06-12","cited_by_count":4,"area":"lr"},{"id":"2410.19245","title":"MaCTG: Multi-Agent Collaborative Thought Graph for Automatic Programming","created":"2024-10-25","cited_by_count":3,"area":"lr"},{"id":"2505.23881","title":"Using Reasoning Models to Generate Search Heuristics that Solve Open Instances of Combinatorial Design Problems","created":"2025-05-29","cited_by_count":3,"area":"lr"},{"id":"2510.04532","title":"More Than Meets the Eye? Uncovering the Reasoning-Planning Disconnect in Training Vision-Language Driving Models","created":"2025-10-06","cited_by_count":3,"area":"lr"},{"id":"2601.22249","title":"FunPRM: Function-as-Step Process Reward Model with Meta Reward Correction for Code Generation","created":"2026-01-29","cited_by_count":3,"area":"lr"},{"id":"2602.23864","title":"RUMAD: Reinforcement-Unifying Multi-Agent Debate","created":"2026-02-27","cited_by_count":3,"area":"lr"},{"id":"2508.20729","title":"Re4: Scientific Computing Agent with Rewriting, Resolution, Review and Revision","created":"2025-08-28","cited_by_count":2,"area":"lr"},{"id":"2510.00078","title":"Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A Survey","created":"2025-09-30","cited_by_count":2,"area":"lr"},{"id":"2510.12643","title":"Reasoning Pattern Matters: Learning to Reason without Human Rationales","created":"2025-10-14","cited_by_count":2,"area":"lr"},{"id":"2511.00521","title":"Reasoning Planning for Language Models","created":"2025-11-01","cited_by_count":2,"area":"lr"},{"id":"2511.05874","title":"An Empirical Study of Reasoning Steps in Thinking Code LLMs","created":"2025-11-08","cited_by_count":2,"area":"lr"},{"id":"2512.09679","title":"Understanding Chain-of-Thought Effectiveness in Code Generation: An Empirical and Information-Theoretic Analysis","created":"2025-12-10","cited_by_count":2,"area":"lr"},{"id":"2601.18987","title":"LLMs versus the Halting Problem: Characterizing Program Termination Reasoning","created":"2026-01-26","cited_by_count":2,"area":"lr"},{"id":"2605.16385","title":"Hilbert-Geo: Solving Solid Geometric Problems by Neural-Symbolic Reasoning","created":"2026-05-11","cited_by_count":2,"area":"lr"},{"id":"2605.29277","title":"Code-QA-Bench: Separating Code Reasoning from Documentation Memorization in Repository-Level QA","created":"2026-05-28","cited_by_count":2,"area":"lr"},{"id":"2507.19749","title":"Can LLMs Solve ASP Problems? Insights from a Benchmarking Study (Extended Version)","created":"2025-07-26","cited_by_count":1,"area":"lr"},{"id":"2508.09537","title":"From Context to Intent: Reasoning-Guided Function-Level Code Completion","created":"2025-08-13","cited_by_count":1,"area":"lr"},{"id":"2509.24957","title":"Intra-request branch orchestration for efficient LLM reasoning","created":"2025-09-29","cited_by_count":1,"area":"lr"},{"id":"2601.07180","title":"Structured Reasoning for Large Language Models","created":"2026-01-12","cited_by_count":1,"area":"lr"},{"id":"2603.23844","title":"Language Models as Higher-Order Planning Formalizers","created":"2026-03-25","cited_by_count":1,"area":"lr"},{"id":"2605.19418","title":"Conflict-Resilient Multi-Agent Reasoning via Signed Graph Modeling","created":"2026-05-19","cited_by_count":1,"area":"lr"},{"id":"2605.24140","title":"HyperGuide: Hyperbolic Guidance for Efficient Multi-Step Reasoning in Large Language Models","created":"2026-05-22","cited_by_count":1,"area":"lr"},{"id":"2605.31073","title":"ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2503.14838","title":"Think Like Human Developers: Harnessing Community Knowledge for Structured Code Reasoning","created":"2025-03-19","cited_by_count":0,"area":"lr"},{"id":"2506.17630","title":"Answer-Centric or Reasoning-Driven? Uncovering the Latent Memory Anchor in LLMs","created":"2025-06-21","cited_by_count":0,"area":"lr"},{"id":"2507.04034","title":"Lyria: A Genetic Algorithm-Driven Neuro-Symbolic Reasoning Framework for LLMs","created":"2025-07-05","cited_by_count":0,"area":"lr"},{"id":"2507.08037","title":"CRISP: Complex Reasoning with Interpretable Step-based Plans","created":"2025-07-09","cited_by_count":0,"area":"lr"},{"id":"2507.20509","title":"LLMs-guided adaptive compensator: Bringing Adaptivity to Automatic Control Systems with Large Language Models","created":"2025-07-28","cited_by_count":0,"area":"lr"},{"id":"2509.11132","title":"Rethinking Technology Stack Selection with AI Coding Proficiency","created":"2025-09-14","cited_by_count":0,"area":"lr"},{"id":"2509.20105","title":"PEPS: Quantum-Inspired Reinforcement Learning for Coherent Reasoning Traces in LLMs","created":"2025-09-24","cited_by_count":0,"area":"lr"},{"id":"2510.17598","title":"Reasoning Distillation and Structural Alignment for Improved Code Generation","created":"2025-10-20","cited_by_count":0,"area":"lr"},{"id":"2601.21469","title":"Adaptive Confidence Gating in Multi-Agent Collaboration for Efficient and Optimized Code Generation","created":"2026-01-29","cited_by_count":0,"area":"lr"},{"id":"2602.04919","title":"Gradually Compacting Large Language Models for Reasoning Like a Boiling Frog","created":"2026-02-04","cited_by_count":0,"area":"lr"},{"id":"2602.10518","title":"MapVerse: A Benchmark for Geospatial Question Answering on Diverse Real-World Maps","created":"2026-02-11","cited_by_count":0,"area":"lr"},{"id":"2603.18334","title":"Can LLMs Reason Like Automated Theorem Provers for Rust Verification? VCoT-Bench: Evaluating via Verification Chain of Thought","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2603.27694","title":"Can Large Language Models Simulate Human Cognition Beyond Behavioral Imitation?","created":"2026-03-29","cited_by_count":0,"area":"lr"},{"id":"2604.02709","title":"Evaluating the Formal Reasoning Capabilities of Large Language Models through Chomsky Hierarchy","created":"2026-04-03","cited_by_count":0,"area":"lr"},{"id":"2604.12881","title":"Evaluating LLMs Code Reasoning Under Real-World Context","created":"2026-04-14","cited_by_count":0,"area":"lr"},{"id":"2606.01182","title":"CA-BED: Conversation-Aware Bayesian Experimental Design","created":"2026-05-31","cited_by_count":0,"area":"lr"},{"id":"2606.21974","title":"Fine-Tuning Large Language Models for Quantum Reasoning","created":"2026-06-20","cited_by_count":0,"area":"lr"},{"id":"2609.27763","title":"Alignment of LRMs via Counter-Aligned Few-Shot Conversation Exposure","created":"2026-08-16","cited_by_count":0,"area":"lr"},{"id":"2609.36254","title":"Towards Mitigating Deceptive Safety Alignment in Large Reasoning Models","created":"2026-09-28","cited_by_count":0,"area":"lr"}],"next_cursor":null}