{"total":96,"rows":[{"id":"2508.10925","title":"gpt-oss-120b & gpt-oss-20b Model Card","created":"2025-08-08","cited_by_count":1386,"area":"lr"},{"id":"2508.06471","title":"GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models","created":"2025-08-08","cited_by_count":467,"area":"lr"},{"id":"2506.13585","title":"MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention","created":"2025-06-16","cited_by_count":263,"area":"lr"},{"id":"2505.24298","title":"AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning","created":"2025-05-30","cited_by_count":250,"area":"lr"},{"id":"2503.24235","title":"A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?","created":"2025-03-31","cited_by_count":223,"area":"lr"},{"id":"2504.19678","title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","created":"2025-04-28","cited_by_count":149,"area":"lr"},{"id":"2505.01441","title":"Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning","created":"2025-04-28","cited_by_count":110,"area":"lr"},{"id":"2505.08638","title":"TRAIL: Trace Reasoning and Agentic Issue Localization","created":"2025-05-13","cited_by_count":104,"area":"lr"},{"id":"2512.17102","title":"Reinforcement Learning for Self-Improving Agent with Skill Library","created":"2025-12-18","cited_by_count":100,"area":"lr"},{"id":"2504.10903","title":"Efficient Reasoning Models: A Survey","created":"2025-04-15","cited_by_count":95,"area":"lr"},{"id":"2505.04921","title":"Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models","created":"2025-05-08","cited_by_count":90,"area":"lr"},{"id":"2412.13147","title":"Are Your LLMs Capable of Stable Reasoning?","created":"2024-12-17","cited_by_count":65,"area":"lr"},{"id":"2503.23077","title":"Efficient Inference for Large Reasoning Models: A Survey","created":"2025-03-29","cited_by_count":61,"area":"lr"},{"id":"2511.01824","title":"Simulating Environments with Reasoning Models for Agent Training","created":"2025-11-03","cited_by_count":57,"area":"lr"},{"id":"2511.17006","title":"Budget-Aware Tool Use Enables Effective Agent Scaling","created":"2025-11-21","cited_by_count":44,"area":"lr"},{"id":"2507.11407","title":"EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes","created":"2025-07-15","cited_by_count":32,"area":"lr"},{"id":"2507.08616","title":"AgentsNet: Coordination and Collaborative Reasoning in Multi-Agent LLMs","created":"2025-07-11","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":"2511.15718","title":"ToolMind Technical Report: A Large-Scale, Reasoning-Enhanced Tool-Use Dataset","created":"2025-11-12","cited_by_count":30,"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":"2510.13554","title":"Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization","created":"2025-10-15","cited_by_count":25,"area":"lr"},{"id":"2505.07215","title":"Measuring General Intelligence with Generated Games","created":"2025-05-12","cited_by_count":24,"area":"lr"},{"id":"2506.23139","title":"Benchmarking Deep Search over Heterogeneous Enterprise Data","created":"2025-06-29","cited_by_count":23,"area":"lr"},{"id":"2605.09252","title":"LLM Agents Already Know When to Call Tools -- Even Without Reasoning","created":"2026-05-10","cited_by_count":19,"area":"lr"},{"id":"2503.04479","title":"ToolFuzz -- Automated Agent Tool Testing","created":"2025-03-06","cited_by_count":18,"area":"lr"},{"id":"2606.05806","title":"When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents","created":"2026-06-04","cited_by_count":17,"area":"lr"},{"id":"2510.04265","title":"Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation","created":"2025-10-05","cited_by_count":15,"area":"lr"},{"id":"2602.12984","title":"SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents","created":"2026-02-13","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":"2505.13328","title":"Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challenges","created":"2025-05-19","cited_by_count":12,"area":"lr"},{"id":"2605.11853","title":"GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation","created":"2026-05-12","cited_by_count":12,"area":"lr"},{"id":"2601.15625","title":"Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors","created":"2026-01-22","cited_by_count":10,"area":"lr"},{"id":"2607.07405","title":"Reason Less, Verify More: Deterministic Gates Recover a Silent Policy-Violation Failure Mode in Tool-Using LLM Agents","created":"2026-07-08","cited_by_count":10,"area":"lr"},{"id":"2601.09215","title":"UserLM-R1: Modeling Human Reasoning in User Language Models with Multi-Reward Reinforcement Learning","created":"2026-01-14","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":"2510.08189","title":"R-Horizon: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?","created":"2025-10-09","cited_by_count":8,"area":"lr"},{"id":"2512.04601","title":"Natural Language Actor-Critic: Scalable Off-Policy Learning in Language Space","created":"2025-12-04","cited_by_count":8,"area":"lr"},{"id":"2512.13159","title":"SpeakRL: Synergizing Reasoning, Speaking, and Acting in Language Models with Reinforcement Learning","created":"2025-12-15","cited_by_count":8,"area":"lr"},{"id":"2601.07226","title":"Lost in the Noise: How Reasoning Models Fail with Contextual Distractors","created":"2026-01-12","cited_by_count":8,"area":"lr"},{"id":"2603.07915","title":"Ares: Adaptive Reasoning Effort Selection for Efficient LLM Agents","created":"2026-03-09","cited_by_count":8,"area":"lr"},{"id":"2511.01365","title":"The Ouroboros of Benchmarking: Reasoning Evaluation in an Era of Saturation","created":"2025-11-03","cited_by_count":7,"area":"lr"},{"id":"2604.02869","title":"Multi-Turn Reinforcement Learning for Tool-Calling Agents with Iterative Reward Calibration","created":"2026-04-03","cited_by_count":7,"area":"lr"},{"id":"2602.01566","title":"FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based Agents","created":"2026-02-02","cited_by_count":6,"area":"lr"},{"id":"2603.02091","title":"Learning from Synthetic Data Improves Multi-hop Reasoning","created":"2026-03-02","cited_by_count":6,"area":"lr"},{"id":"2606.26080","title":"Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents","created":"2026-06-24","cited_by_count":6,"area":"lr"},{"id":"2510.23458","title":"BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents","created":"2025-10-27","cited_by_count":5,"area":"lr"},{"id":"2603.02119","title":"Pencil Puzzle Bench: A Benchmark for Multi-Step Verifiable Reasoning","created":"2026-03-02","cited_by_count":5,"area":"lr"},{"id":"2606.23301","title":"EHR-Complex: Benchmarking Medical Agents for Complex Clinical Reasoning","created":"2026-06-22","cited_by_count":5,"area":"lr"},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"id":"2603.14602","title":"PA3: Policy-Aware Agent Alignment through Chain-of-Thought","created":"2026-03-15","cited_by_count":4,"area":"lr"},{"id":"2604.00304","title":"Asymmetric Actor-Critic for Multi-turn LLM Agents","created":"2026-03-31","cited_by_count":4,"area":"lr"},{"id":"2605.12213","title":"Goal-Oriented Reasoning for RAG-based Memory in Conversational Agentic LLM Systems","created":"2026-05-12","cited_by_count":4,"area":"lr"},{"id":"2509.00971","title":"CoreThink: A Symbolic Reasoning Layer to reason over Long Horizon Tasks with LLMs","created":"2025-08-31","cited_by_count":3,"area":"lr"},{"id":"2511.05589","title":"CoPRIS: Efficient and Stable Reinforcement Learning via Concurrency-Controlled Partial Rollout with Importance Sampling","created":"2025-11-05","cited_by_count":3,"area":"lr"},{"id":"2511.21638","title":"Iterative GRPO: Batch-Online Multi-Turn RL via Single-Turn RLHF","created":"2025-11-26","cited_by_count":3,"area":"lr"},{"id":"2608.25920","title":"Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systems","created":"2026-08-26","cited_by_count":3,"area":"lr"},{"id":"2510.07958","title":"A$^2$Search: Ambiguity-Aware Question Answering with Reinforcement Learning","created":"2025-10-09","cited_by_count":2,"area":"lr"},{"id":"2510.17491","title":"Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents","created":"2025-10-20","cited_by_count":2,"area":"lr"},{"id":"2510.26495","title":"Rethinking Text-to-SQL: Dynamic Multi-turn SQL Interaction for Real-world Database Exploration","created":"2025-10-30","cited_by_count":2,"area":"lr"},{"id":"2512.17206","title":"Reasoning Palette: Modulating Reasoning via Latent Contextualization for Controllable Exploration for (V)LMs","created":"2025-12-19","cited_by_count":2,"area":"lr"},{"id":"2601.08225","title":"User-Oriented Multi-Turn Dialogue Generation with Tool Use at scale","created":"2026-01-13","cited_by_count":2,"area":"lr"},{"id":"2602.11202","title":"interwhen: A Generalizable Framework for Steering Reasoning Models with Test-time Verification","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2605.28532","title":"Do Agents Know What They Can't Do? Evaluating Feasibility Awareness in Tool-Using Agents","created":"2026-05-27","cited_by_count":2,"area":"lr"},{"id":"2607.25816","title":"Speculate While You Reason: Teaching Agents to Predict Their Next Tool Call via Joint Agent-Speculator RL","created":"2026-07-28","cited_by_count":2,"area":"lr"},{"id":"2607.26977","title":"TREK: A Travel Reasoning and Evaluation Kit for LLM Agents in Complex Trip Planning","created":"2026-07-29","cited_by_count":2,"area":"lr"},{"id":"2608.04719","title":"Diagnosing Tool-Selection Reasoning in LLM Agents with Canary Tools","created":"2026-08-05","cited_by_count":2,"area":"lr"},{"id":"2609.04518","title":"Multi-Harness Reinforcement Learning for Coding Agents: Training Gains and Harness Dependence","created":"2026-09-03","cited_by_count":2,"area":"lr"},{"id":"2602.17022","title":"ReIn: Conversational Error Recovery with Reasoning Inception","created":"2026-02-19","cited_by_count":1,"area":"lr"},{"id":"2603.10960","title":"Ranking Reasoning LLMs under Test-Time Scaling","created":"2026-03-11","cited_by_count":1,"area":"lr"},{"id":"2605.27820","title":"EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2606.02113","title":"A Primer in Post-Training Reasoning Data: What We Know About How It Works","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2607.08093","title":"CausalDS: Benchmarking Causal Reasoning in Data-Science Agents","created":"2026-07-09","cited_by_count":1,"area":"lr"},{"id":"2608.00181","title":"Cross-Benchmark Generalization in Long-Horizon Agents","created":"2026-07-31","cited_by_count":1,"area":"lr"},{"id":"2608.06663","title":"The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agents","created":"2026-08-07","cited_by_count":1,"area":"lr"},{"id":"2608.26432","title":"SpeechGym: An Audio-Native Gym for Training Voice Agents via Reinforcement Learning","created":"2026-08-26","cited_by_count":1,"area":"lr"},{"id":"2509.21998","title":"GSM-Agent: Understanding Agentic Reasoning Using Controllable Environments","created":"2025-09-26","cited_by_count":0,"area":"lr"},{"id":"2510.22898","title":"On Generalization in Agentic Tool Calling: CoreThink Agentic Reasoner and MAVEN Dataset","created":"2025-10-27","cited_by_count":0,"area":"lr"},{"id":"2602.02160","title":"D-CORE: Incentivizing Task Decomposition in Large Reasoning Models for Complex Tool Use","created":"2026-02-02","cited_by_count":0,"area":"lr"},{"id":"2602.07796","title":"Thinking Is Not Telling: Information Disclosure in User-Service LLM Agents","created":"2026-02-08","cited_by_count":0,"area":"lr"},{"id":"2603.23964","title":"From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments","created":"2026-03-25","cited_by_count":0,"area":"lr"},{"id":"2605.09544","title":"TIDE-Bench: Task-Aware and Diagnostic Evaluation of Tool-Integrated Reasoning","created":"2026-05-10","cited_by_count":0,"area":"lr"},{"id":"2606.07845","title":"GRPO Does Not Close the Multi-Agent Coordination Gap","created":"2026-06-05","cited_by_count":0,"area":"lr"},{"id":"2607.04096","title":"Forethought: Verifiable Reasoning from Neurosymbolic Primitive Programming","created":"2026-07-05","cited_by_count":0,"area":"lr"},{"id":"2607.08758","title":"Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation","created":"2026-07-09","cited_by_count":0,"area":"lr"},{"id":"2607.18438","title":"Relay-Bench: Evaluating LLMs on Multi-Domain Reasoning Chains","created":"2026-07-20","cited_by_count":0,"area":"lr"},{"id":"2607.23123","title":"SQBench: A Benchmark for Evaluating Task Delivery by Language-Model Agents in Production-Oriented Workflows","created":"2026-07-25","cited_by_count":0,"area":"lr"},{"id":"2608.06735","title":"IB-RL: Isolated Bilateral Reinforcement Learning for Strategic Dialogue Agents","created":"2026-08-07","cited_by_count":0,"area":"lr"},{"id":"2608.07885","title":"Reason Wide, Not Deep: Amortizing the Reasoning Premium into Distilled Skills","created":"2026-08-08","cited_by_count":0,"area":"lr"},{"id":"2608.08146","title":"Long SKILL Compliance as Logical Reasoning: Closure-Grounded Detection with Scaling-Guided On-Policy Distillation","created":"2026-08-08","cited_by_count":0,"area":"lr"},{"id":"2608.13787","title":"From Passive Delegates to Strategic Negotiators: Reinforcing Social Reasoning in Small Language Models with SocialRL","created":"2026-08-13","cited_by_count":0,"area":"lr"},{"id":"2608.30650","title":"Geometry of Divergence: Tracking Hidden-State Trajectories for Adaptive Multi-Turn Reasoning","created":"2026-08-31","cited_by_count":0,"area":"lr"},{"id":"2609.16887","title":"QART: A Quantum-Classical Hybrid Architecture for Long-Horizon Reasoning -- Exploring a Conditional Path toward Quantum Scaling","created":"2026-09-15","cited_by_count":0,"area":"lr"},{"id":"2609.17848","title":"SFT or RL for Tool-Calling Agents? A Controlled Study Across Data, Method, and Scale","created":"2026-09-15","cited_by_count":0,"area":"lr"},{"id":"2609.20089","title":"UnifiedPlayers: Enhance Tool-Integrated Reasoning in Agentic Reinforcement Learning","created":"2026-09-17","cited_by_count":0,"area":"lr"},{"id":"2609.22194","title":"A Pinch of SFT, A Dash of RL: When Reinforcement Learning Helps Long-Horizon Advertising Agents","created":"2026-08-29","cited_by_count":0,"area":"lr"},{"id":"2609.38018","title":"Prompts Live on an Arc: Gaussian Curricula in Fisher--Rao Coordinates for Rollout-Efficient GRPO","created":"2026-09-29","cited_by_count":0,"area":"lr"}],"next_cursor":null}