{"total":79,"rows":[{"id":"2507.20534","title":"Kimi K2: Open Agentic Intelligence","created":"2025-07-28","cited_by_count":567,"area":"agents"},{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2604.02268","title":"SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization","created":"2026-04-02","cited_by_count":94,"area":"agents"},{"id":"2509.21240","title":"Tree Search for LLM Agent Reinforcement Learning","created":"2025-09-25","cited_by_count":79,"area":"agents"},{"id":"2508.07999","title":"WideSearch: Benchmarking Agentic Broad Info-Seeking","created":"2025-08-11","cited_by_count":69,"area":"agents"},{"id":"2508.12752","title":"Deep Research: A Survey of Autonomous Research Agents","created":"2025-08-18","cited_by_count":66,"area":"agents"},{"id":"2603.08754","title":"Hindsight Credit Assignment for Long-Horizon LLM Agents","created":"2026-03-07","cited_by_count":65,"area":"agents"},{"id":"2509.13311","title":"Towards General Agentic Intelligence via Environment Scaling","created":"2025-09-16","cited_by_count":54,"area":"agents"},{"id":"2601.07055","title":"Dr. Zero: Self-Evolving Search Agents without Training Data","created":"2026-01-11","cited_by_count":44,"area":"agents"},{"id":"2510.14545","title":"Agentic Entropy-Balanced Policy Optimization","created":"2025-10-16","cited_by_count":40,"area":"agents"},{"id":"2605.05242","title":"Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction","created":"2026-05-03","cited_by_count":38,"area":"agents"},{"id":"2510.18821","title":"Search Self-play: Pushing the Frontier of Agent Capability without Supervision","created":"2025-10-21","cited_by_count":34,"area":"agents"},{"id":"2603.28716","title":"Dynamic Dual-Granularity Skill Bank for Agentic RL","created":"2026-03-30","cited_by_count":34,"area":"agents"},{"id":"2508.18669","title":"MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use","created":"2025-08-26","cited_by_count":32,"area":"agents"},{"id":"2605.26684","title":"Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning","created":"2026-05-26","cited_by_count":31,"area":"agents"},{"id":"2510.20022","title":"SALT: Step-level Advantage Assignment for Long-horizon Agents via Trajectory Graph","created":"2025-10-22","cited_by_count":28,"area":"agents"},{"id":"2512.16301","title":"Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills","created":"2025-12-18","cited_by_count":22,"area":"agents"},{"id":"2601.04786","title":"AgentOCR: Reimagining Agent History via Optical Self-Compression","created":"2026-01-08","cited_by_count":22,"area":"agents"},{"id":"2510.20168","title":"DeepWideSearch: Benchmarking Depth and Width in Agentic Information Seeking","created":"2025-10-23","cited_by_count":21,"area":"agents"},{"id":"2602.19225","title":"Proximity-Based Multi-Turn Optimization: Practical Credit Assignment for LLM Agent Training","created":"2026-02-22","cited_by_count":18,"area":"agents"},{"id":"2511.07800","title":"From Experience to Strategy: Empowering LLM Agents with Trainable Graph Memory","created":"2025-11-11","cited_by_count":17,"area":"agents"},{"id":"2512.22857","title":"AutoForge: Automated Environment Synthesis for Agentic Reinforcement Learning","created":"2025-12-28","cited_by_count":17,"area":"agents"},{"id":"2512.04535","title":"GTM: Simulating the World of Tools for AI Agents","created":"2025-12-04","cited_by_count":14,"area":"agents"},{"id":"2601.04888","title":"SmartSearch: Process Reward-Guided Query Refinement for Search Agents","created":"2026-01-08","cited_by_count":14,"area":"agents"},{"id":"2511.09586","title":"Environment Scaling for Interactive Agentic Experience Collection: A Survey","created":"2025-11-12","cited_by_count":13,"area":"agents"},{"id":"2508.00344","title":"PilotRL: Training Language Model Agents via Global Planning-Guided Progressive Reinforcement Learning","created":"2025-08-01","cited_by_count":11,"area":"agents"},{"id":"2510.25320","title":"GAP: Graph-Based Agent Planning with Parallel Tool Use and Reinforcement Learning","created":"2025-10-29","cited_by_count":11,"area":"agents"},{"id":"2510.26575","title":"InfoFlow: Reinforcing Search Agent Via Reward Density Optimization","created":"2025-10-30","cited_by_count":11,"area":"agents"},{"id":"2508.04026","title":"VeriWeb: Verifiable Long-Chain Web Benchmark for Agentic Information-Seeking","created":"2025-08-06","cited_by_count":10,"area":"agents"},{"id":"2509.25598","title":"Hybrid Reward Normalization for Process-supervised Non-verifiable Agentic Tasks","created":"2025-09-29","cited_by_count":10,"area":"agents"},{"id":"2510.00568","title":"ReSeek: A Self-Correcting Framework for Search Agents with Instructive Rewards","created":"2025-10-01","cited_by_count":10,"area":"agents"},{"id":"2604.17931","title":"LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent","created":"2026-04-20","cited_by_count":10,"area":"agents"},{"id":"2601.03261","title":"DeepResearch-Slice: Bridging the Retrieval-Utilization Gap via Explicit Text Slicing","created":"2025-12-16","cited_by_count":9,"area":"agents"},{"id":"2605.17734","title":"Harnessing LLM Agents with Skill Programs","created":"2026-05-18","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":"2602.11541","title":"Budget-Constrained Agentic Large Language Models: Intention-Based Planning for Costly Tool Use","created":"2026-02-12","cited_by_count":8,"area":"agents"},{"id":"2602.19526","title":"How to Train Your Deep Research Agent? Prompt, Reward, and Policy Optimization in Search-R1","created":"2026-02-23","cited_by_count":8,"area":"agents"},{"id":"2603.11327","title":"Meta-Reinforcement Learning with Self-Reflection for Agentic Search","created":"2026-03-11","cited_by_count":8,"area":"agents"},{"id":"2606.12191","title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","created":"2026-06-10","cited_by_count":8,"area":"agents"},{"id":"2604.13787","title":"ToolOmni: Enabling Open-World Tool Use via Agentic learning with Proactive Retrieval and Grounded Execution","created":"2026-04-15","cited_by_count":7,"area":"agents"},{"id":"2606.05885","title":"When Denser Credit Is Not Enough: Evidence-Calibrated Policy Optimization for Long-Horizon LLM Agent Training","created":"2026-06-04","cited_by_count":7,"area":"agents"},{"id":"2608.16156","title":"TRCA: Transition-wise Rubric Credit Assignment for Long-horizon LLM Agents","created":"2026-08-17","cited_by_count":7,"area":"agents"},{"id":"2509.24107","title":"Fathom-DeepResearch: Unlocking Long Horizon Information Retrieval and Synthesis for SLMs","created":"2025-09-28","cited_by_count":5,"area":"agents"},{"id":"2509.26048","title":"RE-Searcher: Robust Agentic Search with Goal-oriented Planning and Self-reflection","created":"2025-09-30","cited_by_count":5,"area":"agents"},{"id":"2510.26270","title":"Graph-Enhanced Policy Optimization in LLM Agent Training","created":"2025-10-30","cited_by_count":5,"area":"agents"},{"id":"2606.14885","title":"Dr-DCI: Scaling Direct Corpus Interaction via Dynamic Workspace Expansion","created":"2026-06-12","cited_by_count":5,"area":"agents"},{"id":"2509.23694","title":"SafeSearch: Automated Red-Teaming of LLM-Based Search Agents","created":"2025-09-28","cited_by_count":4,"area":"agents"},{"id":"2510.04695","title":"Beyond Outcome Reward: Decoupling Search and Answering Improves LLM Agents","created":"2025-10-06","cited_by_count":4,"area":"agents"},{"id":"2601.15141","title":"CLEANER: Self-Purified Trajectories Boost Agentic Reinforcement Learning","created":"2026-01-21","cited_by_count":4,"area":"agents"},{"id":"2606.10917","title":"Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution","created":"2026-06-09","cited_by_count":4,"area":"agents"},{"id":"2604.17555","title":"CoSearch: Joint Training of Reasoning and Document Ranking via Reinforcement Learning for Agentic Search","created":"2026-04-19","cited_by_count":3,"area":"agents"},{"id":"2605.09287","title":"PiCA: Pivot-Based Credit Assignment for Search Agentic Reinforcement Learning","created":"2026-05-10","cited_by_count":3,"area":"agents"},{"id":"2606.26122","title":"DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agents","created":"2026-05-27","cited_by_count":3,"area":"agents"},{"id":"2608.00432","title":"Deep Research Pretraining via Predictive Navigation","created":"2026-08-01","cited_by_count":3,"area":"agents"},{"id":"2510.11851","title":"Deep Research Agents Brings Deeper Harm","created":"2025-10-13","cited_by_count":2,"area":"agents"},{"id":"2603.10069","title":"Improving Search Agent with One Line of Code","created":"2026-03-10","cited_by_count":2,"area":"agents"},{"id":"2603.18079","title":"SLEA-RL: Step-Level Experience Augmented Reinforcement Learning for Multi-Turn Agentic Training","created":"2026-03-18","cited_by_count":2,"area":"agents"},{"id":"2604.01195","title":"ORBIT: Scalable and Verifiable Data Generation for Search Agents on a Tight Budget","created":"2026-04-01","cited_by_count":2,"area":"agents"},{"id":"2605.05702","title":"Knowledge-Graph Paths as Intermediate Supervision for Self-Evolving Search Agents","created":"2026-05-07","cited_by_count":2,"area":"agents"},{"id":"2607.06223","title":"Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agents","created":"2026-07-07","cited_by_count":2,"area":"agents"},{"id":"2607.21419","title":"PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning","created":"2026-07-23","cited_by_count":2,"area":"agents"},{"id":"2608.18613","title":"CTIFoundry: An Agent-Native Corpus Scaffold for Cyber Threat Intelligence","created":"2026-08-19","cited_by_count":2,"area":"agents"},{"id":"2512.13059","title":"An Open and Reproducible Deep Research Agent for Long-Form Question Answering","created":"2025-12-15","cited_by_count":1,"area":"agents"},{"id":"2603.08117","title":"UIS-Digger: Towards Comprehensive Research Agent Systems for Real-world Unindexed Information Seeking","created":"2026-03-09","cited_by_count":1,"area":"agents"},{"id":"2604.17739","title":"Democratizing Tool Learning with Environments Fully Simulated by a Free 8B Language Model","created":"2026-04-20","cited_by_count":1,"area":"agents"},{"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":"2607.04963","title":"STAPO: Selective Trajectory-Aware Policy Optimization for LLM Agent Training","created":"2026-07-06","cited_by_count":1,"area":"agents"},{"id":"2607.16257","title":"From Outcomes to Actions: Leveraging Hindsight for Long-Horizon Language Agent Training","created":"2026-06-28","cited_by_count":1,"area":"agents"},{"id":"2609.19830","title":"Dual-Axis Policy Optimization for LLM Agents: Bayesian Feedback Attribution and Trajectory Mass Normalization","created":"2026-09-17","cited_by_count":1,"area":"agents"},{"id":"2606.01830","title":"CAPF: Guiding Search-Agent Rollouts with Credit-Attenuated Privileged Feedback","created":"2026-06-01","cited_by_count":0,"area":"agents"},{"id":"2608.00974","title":"Search-GRT: Guided Retrieval Training of Search Agents to Optimize for Complex Question Answering","created":"2026-08-02","cited_by_count":0,"area":"agents"},{"id":"2608.01867","title":"CRISP: Critical Step Perception for Training Efficient Deep Search Agents","created":"2026-08-03","cited_by_count":0,"area":"agents"},{"id":"2608.04588","title":"EASy: Towards Efficient LLM-Based Agentic System","created":"2026-08-05","cited_by_count":0,"area":"agents"},{"id":"2609.00935","title":"DualStake: Dual-Path Confidence Calibration in Deep Research Agents","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.34633","title":"GenMem: Generative Symbolic Memory for Self-Evolving Harness","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.37111","title":"Learning from Viable Failure Prefixes: Milestone Viability Potential Policy Optimization for Long-Horizon LLM Agents","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2609.40221","title":"PhantomEnvironments: Training LLM Agents in Fictional Worlds","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.04911","title":"VideoResearchAgent: Grounded Task Synthesis and Sim-to-Real RL for Open-Web Video Research","created":"2026-10-04","cited_by_count":0,"area":"agents"},{"id":"2610.09832","title":"SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles","created":"2026-10-07","cited_by_count":0,"area":"agents"}],"next_cursor":null}