{"total":199,"rows":[{"id":"2601.05242","title":"GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization","created":"2026-01-08","cited_by_count":193,"area":"lr"},{"id":"2512.13607","title":"Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models","created":"2025-12-15","cited_by_count":48,"area":"lr"},{"id":"2602.04879","title":"Rethinking the Trust Region in LLM Reinforcement Learning","created":"2026-02-04","cited_by_count":37,"area":"lr"},{"id":"2602.18998","title":"Benchmark Test-Time Scaling of General LLM Agents","created":"2026-02-22","cited_by_count":26,"area":"lr"},{"id":"2601.11100","title":"ReCreate: Reasoning and Creating Domain Agents Driven by Experience","created":"2026-01-16","cited_by_count":24,"area":"lr"},{"id":"2604.11753","title":"Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks","created":"2026-04-13","cited_by_count":18,"area":"lr"},{"id":"2605.18421","title":"EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective","created":"2026-05-18","cited_by_count":17,"area":"lr"},{"id":"2602.07900","title":"Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agents","created":"2026-02-08","cited_by_count":14,"area":"lr"},{"id":"2601.03715","title":"R$^3$L: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification","created":"2026-01-07","cited_by_count":12,"area":"lr"},{"id":"2602.03279","title":"Agentic Proposing: Enhancing Large Language Model Reasoning via Compositional Skill Synthesis","created":"2026-02-03","cited_by_count":12,"area":"lr"},{"id":"2606.00765","title":"FALAT: Tracing Failures in LLM Agent Trajectories via Dependency-Guided Search","created":"2026-05-30","cited_by_count":12,"area":"lr"},{"id":"2606.07157","title":"Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models","created":"2026-06-05","cited_by_count":12,"area":"lr"},{"id":"2602.22603","title":"SideQuest: Model-Driven KV Cache Management for Long-Horizon Agentic Reasoning","created":"2026-02-26","cited_by_count":11,"area":"lr"},{"id":"2602.19362","title":"LLMs Can Learn to Reason Via Off-Policy RL","created":"2026-02-22","cited_by_count":10,"area":"lr"},{"id":"2605.24468","title":"SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent","created":"2026-05-23","cited_by_count":10,"area":"lr"},{"id":"2601.21684","title":"Do Not Waste Your Rollouts: Recycling Search Experience for Efficient Test-Time Scaling","created":"2026-01-29","cited_by_count":9,"area":"lr"},{"id":"2602.02188","title":"Reasoning in a Combinatorial and Constrained World: Benchmarking LLMs on Natural-Language Combinatorial Optimization","created":"2026-02-02","cited_by_count":9,"area":"lr"},{"id":"2602.02301","title":"Advancing General-Purpose Reasoning Models with Modular Gradient Surgery","created":"2026-02-02","cited_by_count":9,"area":"lr"},{"id":"2602.16793","title":"Escaping the Cognitive Well: Efficient Competition Math with Off-the-Shelf Models","created":"2026-02-18","cited_by_count":9,"area":"lr"},{"id":"2606.03854","title":"CLI-Anything: Towards Agent-Native Computer Use","created":"2026-06-02","cited_by_count":9,"area":"lr"},{"id":"2606.28436","title":"Dockerless: Environment-Free Program Verifier for Coding Agents","created":"2026-06-26","cited_by_count":9,"area":"lr"},{"id":"2601.03822","title":"ROI-Reasoning: Rational Optimization for Inference via Pre-Computation Meta-Cognition","created":"2026-01-07","cited_by_count":8,"area":"lr"},{"id":"2602.14367","title":"InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problem","created":"2026-02-16","cited_by_count":8,"area":"lr"},{"id":"2606.23181","title":"DART: Draft-Agreement Routing for Training-Free Adaptive Thinking Budgets in Hybrid Reasoning Models","created":"2026-06-22","cited_by_count":8,"area":"lr"},{"id":"2601.18204","title":"MemWeaver: Weaving Hybrid Memories for Traceable Long-Horizon Agentic Reasoning","created":"2026-01-26","cited_by_count":7,"area":"lr"},{"id":"2604.24432","title":"Kwai Summary Attention Technical Report","created":"2026-04-27","cited_by_count":7,"area":"lr"},{"id":"2607.22002","title":"Learning as Reasoning Unfolds: Progressive Rollout Allocation for Efficient Reinforcement Learning","created":"2026-07-24","cited_by_count":7,"area":"lr"},{"id":"2601.13761","title":"DARC: Decoupled Asymmetric Reasoning Curriculum for LLM Evolution","created":"2026-01-20","cited_by_count":6,"area":"lr"},{"id":"2601.16486","title":"Timely Machine: Awareness of Time Makes Test-Time Scaling Agentic","created":"2026-01-23","cited_by_count":6,"area":"lr"},{"id":"2602.03249","title":"Accordion-Thinking: Self-Regulated Step Summaries for Efficient and Readable LLM Reasoning","created":"2026-02-03","cited_by_count":6,"area":"lr"},{"id":"2603.25419","title":"TAPO: Translation Augmented Policy Optimization for Multilingual Mathematical Reasoning","created":"2026-03-26","cited_by_count":6,"area":"lr"},{"id":"2604.11209","title":"Exploring Knowledge Conflicts for Faithful LLM Reasoning: Benchmark and Method","created":"2026-04-13","cited_by_count":6,"area":"lr"},{"id":"2604.11778","title":"General365: Benchmarking General Reasoning in Large Language Models Across Diverse and Challenging Tasks","created":"2026-04-13","cited_by_count":6,"area":"lr"},{"id":"2604.14140","title":"LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning","created":"2026-04-15","cited_by_count":6,"area":"lr"},{"id":"2605.11633","title":"Can LLM Agents Respond to Disasters? Benchmarking Heterogeneous Geospatial Reasoning in Emergency Operations","created":"2026-05-12","cited_by_count":6,"area":"lr"},{"id":"2601.21484","title":"ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment","created":"2026-01-29","cited_by_count":5,"area":"lr"},{"id":"2602.00642","title":"LegalOne: A Family of Foundation Models for Reliable Legal Reasoning","created":"2026-01-31","cited_by_count":5,"area":"lr"},{"id":"2602.03554","title":"When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs","created":"2026-02-03","cited_by_count":5,"area":"lr"},{"id":"2602.04417","title":"EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL","created":"2026-02-04","cited_by_count":5,"area":"lr"},{"id":"2602.07773","title":"SRR-Judge: Step-Level Rating and Refinement for Enhancing Search-Integrated Reasoning in Search Agents","created":"2026-02-08","cited_by_count":5,"area":"lr"},{"id":"2602.08498","title":"Characterizing, Evaluating, and Optimizing Complex Reasoning","created":"2026-02-09","cited_by_count":5,"area":"lr"},{"id":"2602.22273","title":"FIRE: A Comprehensive Benchmark for Financial Intelligence and Reasoning Evaluation","created":"2026-02-25","cited_by_count":5,"area":"lr"},{"id":"2603.04597","title":"Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning","created":"2026-03-04","cited_by_count":5,"area":"lr"},{"id":"2603.06274","title":"Stem: Rethinking Causal Information Flow in Sparse Attention","created":"2026-03-06","cited_by_count":5,"area":"lr"},{"id":"2604.24198","title":"Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis","created":"2026-04-27","cited_by_count":5,"area":"lr"},{"id":"2606.09821","title":"Rethinking the Divergence Regularization in LLM RL","created":"2026-06-08","cited_by_count":5,"area":"lr"},{"id":"2607.22925","title":"Not All LLM Reasoning is Visible in the Chain-of-Thought","created":"2026-07-24","cited_by_count":5,"area":"lr"},{"id":"2601.22323","title":"Models Under SCOPE: Scalable and Controllable Routing via Pre-hoc Reasoning","created":"2026-01-29","cited_by_count":4,"area":"lr"},{"id":"2602.04496","title":"ReThinker: Scientific Reasoning by Rethinking with Guided Reflection and Confidence Control","created":"2026-02-04","cited_by_count":4,"area":"lr"},{"id":"2602.08214","title":"RECUR: Resource Exhaustion Attack via Recursive-Entropy Guided Counterfactual Utilization and Reflection","created":"2026-02-09","cited_by_count":4,"area":"lr"},{"id":"2603.08000","title":"SmartThinker: Progressive Chain-of-Thought Length Calibration for Efficient Large Language Model Reasoning","created":"2026-03-09","cited_by_count":4,"area":"lr"},{"id":"2604.01702","title":"On the Role of Reasoning Patterns in the Generalization Discrepancy of Long Chain-of-Thought Supervised Fine-Tuning","created":"2026-04-02","cited_by_count":4,"area":"lr"},{"id":"2604.03144","title":"InCoder-32B-Thinking: Industrial Code World Model for Thinking","created":"2026-04-03","cited_by_count":4,"area":"lr"},{"id":"2605.05365","title":"ZAYA1-8B Technical Report","created":"2026-05-06","cited_by_count":4,"area":"lr"},{"id":"2605.15726","title":"Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR","created":"2026-05-15","cited_by_count":4,"area":"lr"},{"id":"2606.14317","title":"CausalMotion: Structured Physical Reasoning as Keyframe and Trajectory Guidance for Training-Free Video Generation","created":"2026-06-12","cited_by_count":4,"area":"lr"},{"id":"2512.14917","title":"Evaluating Code Reasoning Abilities of Large Language Models Under Real-World Settings","created":"2025-12-16","cited_by_count":3,"area":"lr"},{"id":"2601.17755","title":"HyperGraphPro: Progress-Aware Reinforcement Learning for Structure-Guided Hypergraph RAG","created":"2026-01-25","cited_by_count":3,"area":"lr"},{"id":"2602.03061","title":"Evaluating LLMs When They Do Not Know the Answer: Statistical Evaluation of Mathematical Reasoning via Comparative Signals","created":"2026-02-03","cited_by_count":3,"area":"lr"},{"id":"2602.21228","title":"ImpRIF: Stronger Implicit Reasoning Leads to Better Complex Instruction Following","created":"2026-02-04","cited_by_count":3,"area":"lr"},{"id":"2603.07078","title":"CoTJudger: A Graph-Driven Framework for Automatic Evaluation of Chain-of-Thought Efficiency and Redundancy in LRMs","created":"2026-03-07","cited_by_count":3,"area":"lr"},{"id":"2603.08659","title":"CODA: Difficulty-Aware Compute Allocation for Adaptive Reasoning","created":"2026-03-09","cited_by_count":3,"area":"lr"},{"id":"2603.15542","title":"InterveneBench: Benchmarking LLMs for Intervention Reasoning and Causal Study Design in Real Social Systems","created":"2026-03-16","cited_by_count":3,"area":"lr"},{"id":"2603.21526","title":"VIGIL: Part-Grounded Structured Reasoning for Generalizable Deepfake Detection","created":"2026-03-23","cited_by_count":3,"area":"lr"},{"id":"2604.01161","title":"Reasoning Shift: How Context Silently Shortens LLM Reasoning","created":"2026-04-01","cited_by_count":3,"area":"lr"},{"id":"2605.04077","title":"Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO","created":"2026-04-14","cited_by_count":3,"area":"lr"},{"id":"2606.03705","title":"Code-on-Graph: Iterative Programmatic Reasoning via Large Language Models on Knowledge Graphs","created":"2026-06-02","cited_by_count":3,"area":"lr"},{"id":"2606.16118","title":"Know Your Limits : On the Faithfulness of LLMs as Solvers and Autoformalizers in Legal Reasoning","created":"2026-06-15","cited_by_count":3,"area":"lr"},{"id":"2607.19339","title":"OmniReasoner: Thinking with Long Audio-Video via Native Tool Use","created":"2026-07-21","cited_by_count":3,"area":"lr"},{"id":"2512.11470","title":"Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning","created":"2025-12-12","cited_by_count":2,"area":"lr"},{"id":"2601.03969","title":"Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models","created":"2026-01-07","cited_by_count":2,"area":"lr"},{"id":"2601.08267","title":"Med-CoReasoner: Reducing Language Disparities in Medical Reasoning via Language-Informed Co-Reasoning","created":"2026-01-13","cited_by_count":2,"area":"lr"},{"id":"2601.21937","title":"Retrieval-Infused Reasoning Sandbox: A Benchmark for Decoupling Retrieval and Reasoning Capabilities","created":"2026-01-29","cited_by_count":2,"area":"lr"},{"id":"2602.19517","title":"Classroom Final Exam: An Instructor-Tested Reasoning Benchmark","created":"2026-02-23","cited_by_count":2,"area":"lr"},{"id":"2603.02615","title":"Think, But Don't Overthink: Reproducing Recursive Language Models","created":"2026-03-03","cited_by_count":2,"area":"lr"},{"id":"2603.17368","title":"Towards Safer Large Reasoning Models by Promoting Safety Decision-Making before Chain-of-Thought Generation","created":"2026-03-18","cited_by_count":2,"area":"lr"},{"id":"2603.25253","title":"MolQuest: A Benchmark for Agentic Evaluation of Abductive Reasoning in Chemical Structure Elucidation","created":"2026-03-26","cited_by_count":2,"area":"lr"},{"id":"2604.08983","title":"AssemLM: A Spatial Reasoning Multimodal Large Language Model for Robotic Assembly","created":"2026-04-10","cited_by_count":2,"area":"lr"},{"id":"2604.18002","title":"Neural Garbage Collection: Learning to Forget while Learning to Reason","created":"2026-04-20","cited_by_count":2,"area":"lr"},{"id":"2604.25399","title":"CoRE: A Fine-Grained Code Reasoning Benchmark Beyond Output Prediction","created":"2026-04-28","cited_by_count":2,"area":"lr"},{"id":"2604.28076","title":"TopBench: A Benchmark for Implicit Predictive Reasoning in Tabular Question Answering","created":"2026-04-30","cited_by_count":2,"area":"lr"},{"id":"2605.06326","title":"Teaching Thinking Models to Reason with Tools: A Full-Pipeline Recipe for Tool-Integrated Reasoning","created":"2026-05-07","cited_by_count":2,"area":"lr"},{"id":"2605.07134","title":"Region4Web: Rethinking Observation Space Granularity for Web Agents","created":"2026-05-08","cited_by_count":2,"area":"lr"},{"id":"2606.01925","title":"QoEReasoner: An Agentic Reasoning Framework for Automated and Explainable QoE Diagnosis in RANs","created":"2026-06-01","cited_by_count":2,"area":"lr"},{"id":"2606.16140","title":"VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models","created":"2026-06-15","cited_by_count":2,"area":"lr"},{"id":"2606.22938","title":"Provable Benefits of RLVR over SFT for Reasoning Models: Learning to Backtrack Efficiently","created":"2026-06-22","cited_by_count":2,"area":"lr"},{"id":"2606.30420","title":"Experience Augmented Policy Optimization for LLM Reasoning","created":"2026-06-29","cited_by_count":2,"area":"lr"},{"id":"2607.27703","title":"SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them","created":"2026-07-30","cited_by_count":2,"area":"lr"},{"id":"2608.01292","title":"CrossLex: A Source-Grounded Benchmark for Cross-Jurisdictional Legal Reasoning in Large Language Models","created":"2026-08-02","cited_by_count":2,"area":"lr"},{"id":"2608.03573","title":"SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs","created":"2026-08-04","cited_by_count":2,"area":"lr"},{"id":"2608.16742","title":"TDD-Agent: Test-Driven Reasoning for Code Generation","created":"2026-08-17","cited_by_count":2,"area":"lr"},{"id":"2608.22753","title":"Beyond Factual Knowledge: Benchmarking and Learning Step-Level Procedural Rule Reasoning in Large Language Models","created":"2026-08-24","cited_by_count":2,"area":"lr"},{"id":"2608.26070","title":"Prefix Sliding for efficient test-time scaling","created":"2026-08-26","cited_by_count":2,"area":"lr"},{"id":"2601.04853","title":"RAAR: Retrieval Augmented Agentic Reasoning for Cross-Domain Misinformation Detection","created":"2026-01-08","cited_by_count":1,"area":"lr"},{"id":"2601.04996","title":"AlgBench: To What Extent Do Large Reasoning Models Understand Algorithms?","created":"2026-01-08","cited_by_count":1,"area":"lr"},{"id":"2601.07148","title":"Measuring Iterative Temporal Reasoning with Time Puzzles","created":"2026-01-12","cited_by_count":1,"area":"lr"},{"id":"2601.22297","title":"Learning from Self-Debate: Preparing Reasoning Models for Multi-Agent Debate","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2602.08030","title":"Free(): Learning to Forget in Malloc-Only Reasoning Models","created":"2026-02-08","cited_by_count":1,"area":"lr"},{"id":"2602.08520","title":"Reinforcement Inference: Leveraging Uncertainty for Self-Correcting Language Model Reasoning","created":"2026-02-09","cited_by_count":1,"area":"lr"},{"id":"2602.08533","title":"Dialogue Model Optimization via Agent Game and Adaptive Tree-based GRPO","created":"2026-02-09","cited_by_count":1,"area":"lr"}],"next_cursor":"100"}