{"total":79,"rows":[{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2604.10688","title":"SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting","created":"2026-04-12","cited_by_count":43,"area":"lr"},{"id":"2605.06130","title":"Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning","created":"2026-05-07","cited_by_count":35,"area":"lr"},{"id":"2506.03610","title":"Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games","created":"2025-06-04","cited_by_count":31,"area":"agents"},{"id":"2511.12159","title":"CriticSearch: Fine-Grained Credit Assignment for Search Agents via a Retrospective Critic","created":"2025-11-15","cited_by_count":30,"area":"agents"},{"id":"2604.09459","title":"From Reasoning to Agentic: Credit Assignment in Reinforcement Learning for Large Language Models","created":"2026-04-10","cited_by_count":23,"area":"lr"},{"id":"2512.20745","title":"AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent","created":"2025-12-23","cited_by_count":17,"area":"lr"},{"id":"2603.08561","title":"RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback","created":"2026-03-09","cited_by_count":17,"area":null},{"id":"2510.15414","title":"MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs","created":"2025-10-17","cited_by_count":16,"area":"lr"},{"id":"2603.00656","title":"InfoPO: Information-Driven Policy Optimization for User-Centric Agents","created":"2026-02-28","cited_by_count":12,"area":"agents"},{"id":"2605.10923","title":"Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning","created":"2026-05-11","cited_by_count":12,"area":"agents"},{"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":"2606.29502","title":"UCOB: Learning to Utilize and Evolve Agentic Skills via Credit-Aware On-Policy Bidirectional Self-Distillation","created":"2026-06-28","cited_by_count":12,"area":"agents"},{"id":"2511.02303","title":"Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberation","created":"2025-11-04","cited_by_count":11,"area":"lr"},{"id":"2510.25510","title":"MTIR-SQL: Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQL","created":"2025-10-29","cited_by_count":10,"area":"lr"},{"id":"2512.00908","title":"Beyond High-Entropy Exploration: Correctness-Aware Low-Entropy Segment-Based Advantage Shaping for Reasoning LLMs","created":"2025-11-30","cited_by_count":10,"area":"lr"},{"id":"2603.06859","title":"Exact Is Easier: Credit Assignment for Cooperative LLM Agents","created":"2026-03-06","cited_by_count":9,"area":"agents"},{"id":"2604.14267","title":"Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization","created":"2026-04-15","cited_by_count":9,"area":"lr"},{"id":"2605.13217","title":"GAGPO: Generalized Advantage Grouped Policy Optimization","created":"2026-05-13","cited_by_count":9,"area":"agents"},{"id":"2605.28424","title":"Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning","created":"2026-05-27","cited_by_count":9,"area":"agents"},{"id":"2510.16720","title":"Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AI","created":"2025-10-19","cited_by_count":8,"area":"agents"},{"id":"2511.11113","title":"VIDEOP2R: Video Understanding from Perception to Reasoning","created":"2025-11-14","cited_by_count":8,"area":"lr"},{"id":"2604.18401","title":"CAPO: Critic-Guided Action-Aligned Policy Optimization for Advancing LLM Agent Capabilities","created":"2026-04-20","cited_by_count":8,"area":"agents"},{"id":"2602.11767","title":"TSR: Trajectory-Search Rollouts for Multi-Turn RL of LLM Agents","created":"2026-02-12","cited_by_count":7,"area":"agents"},{"id":"2604.01840","title":"Not All Tokens See Equally: Perception-Grounded Policy Optimization for Large Vision-Language Models","created":"2026-04-02","cited_by_count":7,"area":"lr"},{"id":"2606.25556","title":"BiPACE: Bisimulation-Guided Policy Optimization with Action Counterfactual Estimation for LLM Agents","created":"2026-06-24","cited_by_count":7,"area":"agents"},{"id":"2602.06554","title":"SeeUPO: Sequence-Level Agentic-RL with Convergence Guarantees","created":"2026-02-06","cited_by_count":6,"area":"agents"},{"id":"2606.09348","title":"PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment","created":"2026-06-08","cited_by_count":6,"area":"lr"},{"id":"2510.15990","title":"Can GRPO Help LLMs Transcend Their Pretraining Origin?","created":"2025-10-14","cited_by_count":5,"area":"lr"},{"id":"2601.22776","title":"TSPO: Breaking the Double Homogenization Dilemma in Multi-turn Search Policy Optimization","created":"2026-01-30","cited_by_count":5,"area":"lr"},{"id":"2602.22193","title":"Improving Parametric Knowledge Access in Reasoning Language Models","created":"2026-02-25","cited_by_count":5,"area":"lr"},{"id":"2606.30251","title":"TACO: Tool-Augmented Credit Optimization for Agentic Tool Use","created":"2026-06-29","cited_by_count":5,"area":"agents"},{"id":"2607.13501","title":"LOTAPO: Leave-One-Turn Attribution for Self-Generated Process Rewards in Multi-Turn Search Reasoning","created":"2026-07-15","cited_by_count":5,"area":"lr"},{"id":"2510.26020","title":"PORTool: Importance-Aware Policy Optimization with Rewarded Tree for Multi-Tool-Integrated Reasoning","created":"2025-10-29","cited_by_count":4,"area":"lr"},{"id":"2605.04984","title":"Self-Induced Outcome Potential: Turn-Level Credit Assignment for Agents without Verifiers","created":"2026-05-06","cited_by_count":4,"area":"lr"},{"id":"2608.13179","title":"Teach the Magnitude, Not the Direction: Verifier-Bounded Credit Assignment for Multi-Turn Multi-step LLM Agents","created":"2026-08-13","cited_by_count":4,"area":"agents"},{"id":"2602.15012","title":"Cold-Start Personalization via Training-Free Priors from Structured World Models","created":"2026-02-16","cited_by_count":3,"area":"wm"},{"id":"2603.06194","title":"MICA: Multi-granularity Intertemporal Credit Assignment for Long-Horizon Emotional Support Dialogue","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2604.13491","title":"FiRe: Fine-grained Multimodal Reasoning for Enhanced Image Generation","created":"2026-04-15","cited_by_count":3,"area":"lr"},{"id":"2605.08778","title":"Not All Turns Matter: Credit Assignment for Multi-Turn Jailbreaking","created":"2026-05-09","cited_by_count":3,"area":"safety"},{"id":"2606.14211","title":"Closing the Reflection Gap: A Free Calibration Bonus for Agentic RL","created":"2026-06-12","cited_by_count":3,"area":"agents"},{"id":"2607.28990","title":"Scaling Scientific Discovery Environments for Turn-Level Agentic RL","created":"2026-07-31","cited_by_count":3,"area":"agents"},{"id":"2602.23720","title":"The Auton Agentic AI Framework","created":"2026-02-27","cited_by_count":2,"area":"agents"},{"id":"2603.01481","title":"Harmonizing Dense and Sparse Signals in Multi-turn RL: Dual-Horizon Credit Assignment for Industrial Sales Agents","created":"2026-03-02","cited_by_count":2,"area":"agents"},{"id":"2604.17912","title":"Learning to Correct: Calibrated Reinforcement Learning for Multi-Attempt Chain-of-Thought","created":"2026-04-20","cited_by_count":2,"area":"lr"},{"id":"2605.29697","title":"Beyond Trajectory Rewards: Step-level Credit Assignment for Agentic Search via Graph Modeling","created":"2026-05-28","cited_by_count":2,"area":"agents"},{"id":"2607.07435","title":"RLVP: Penalize the Path, Reward the Outcome","created":"2026-07-08","cited_by_count":2,"area":null},{"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":"2608.06861","title":"Gated-BEPO: Confidence-Gated Bellman Credit Assignment for Large Language Model Agents","created":"2026-08-07","cited_by_count":2,"area":"agents"},{"id":"2601.16480","title":"TL-GRPO: Turn-Level RL for Reasoning-Guided Iterative Optimization","created":"2026-01-23","cited_by_count":1,"area":"lr"},{"id":"2604.18235","title":"Negative Advantages Is a Double-Edged Sword: Calibrating advantages in GRPO for Search Agents","created":"2026-04-20","cited_by_count":1,"area":"lr"},{"id":"2605.08013","title":"Learning CLI Agents with Structured Action Credit under Selective Observation","created":"2026-05-08","cited_by_count":1,"area":"agents"},{"id":"2606.22164","title":"Drowning in Routine: Signal Dilution in Multi-Turn Agent Training","created":"2026-06-20","cited_by_count":1,"area":null},{"id":"2608.03499","title":"WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2608.08255","title":"Learning from Environmental Feedback: Credit Assignment across Multiple Timescales for Agentic Reinforcement Learning","created":"2026-08-08","cited_by_count":1,"area":"agents"},{"id":"2608.17499","title":"Towards Better Agents for Multi-Turn User Interaction: The Next User Turn Is More Than Context","created":"2026-08-18","cited_by_count":1,"area":null},{"id":"2609.24526","title":"ME-VLM: A Unified VLM for Embodied Cognition and Agent Coordination","created":"2026-09-21","cited_by_count":1,"area":"agents"},{"id":"2609.29050","title":"SLCA-GRPO: Resolving Cross-Segment Credit Misattribution in Tool-Calling RL","created":"2026-09-24","cited_by_count":1,"area":"lr"},{"id":"2601.13142","title":"TVWorld: Foundations for Remote-Control TV Agents","created":"2026-01-19","cited_by_count":0,"area":"mllm"},{"id":"2602.23440","title":"Truncated Step-Level Sampling with Process Rewards for Retrieval-Augmented Reasoning","created":"2026-02-26","cited_by_count":0,"area":"lr"},{"id":"2605.07202","title":"Towards Autonomous Business Intelligence via Data-to-Insight Discovery Agent","created":"2026-05-08","cited_by_count":0,"area":"agents"},{"id":"2605.18799","title":"ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2606.08875","title":"Can the Environment Speak for Itself? $T^{2}$-GRPO: A Turn-Trajectory Group Relative Policy Optimization for Caregiver Agents","created":"2026-06-07","cited_by_count":0,"area":"lr"},{"id":"2607.04713","title":"RSPO: Reward-Swap Policy Optimization for Multi-Turn LLM Agents","created":"2026-07-06","cited_by_count":0,"area":"agents"},{"id":"2607.10350","title":"ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory","created":"2026-07-11","cited_by_count":0,"area":"agents"},{"id":"2607.18999","title":"MedDDC-Eval: Diagnosis-Decoupled Evaluation of Multi-Turn Medical Consultation Agents","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2607.27652","title":"Harness-G: A Graph-Structured Harness for Search Agents","created":"2026-07-30","cited_by_count":0,"area":"lr"},{"id":"2608.05139","title":"Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning","created":"2026-08-05","cited_by_count":0,"area":"lr"},{"id":"2608.07959","title":"SCOUT: Self-Checking and Recovery-Aware Tool-Thought Agents for Ultra-Long Egocentric Video Reasoning","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.15041","title":"LLM-Based Hierarchical Coordinated Control with Continuation-Aware Policy Learning","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2609.16268","title":"Spurious Tool Use: When RL Agents Learn the Wrong Reason to Act","created":"2026-09-14","cited_by_count":0,"area":"lr"},{"id":"2609.24985","title":"Critical-State RL: Diagnosing Trainable States for Multi-Turn Tool Use","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.25463","title":"Rollout Efficiency in Reinforcement Learning for Reasoning Large Language Models: A Taxonomy and Future Directions","created":"2026-09-21","cited_by_count":0,"area":"lr"},{"id":"2609.27321","title":"Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.27532","title":"ProCredit: From Outcome Rewards to Progress Credit in Agentic Reinforcement Learning","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.35472","title":"Why Deterministic PRM Guidance Underperforms in Discrete Diffusion Reasoning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.01128","title":"Grounding Large Language Models in DSGE Simulators for Policy Generation and Forecasting","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.06204","title":"Do Small Language Models Learn to Negotiate? A Controlled Scaling Study of RL-Trained Sellers","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.11171","title":"VAMR: Multi-Question Agentic Reasoning for Efficient Long-Form Video Understanding","created":"2026-10-08","cited_by_count":0,"area":"agents"}],"next_cursor":null}