{"total":96,"rows":[{"id":"2507.22034","title":"UserBench: An Interactive Gym Environment for User-Centric Agents","created":"2025-07-29","cited_by_count":76,"area":"agents"},{"id":"2603.00729","title":"Qwen3-Coder-Next Technical Report","created":"2026-02-28","cited_by_count":71,"area":"agents"},{"id":"2510.01179","title":"TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments","created":"2025-10-01","cited_by_count":69,"area":"agents"},{"id":"2601.05808","title":"EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis","created":"2026-01-09","cited_by_count":63,"area":"agents"},{"id":"2509.13311","title":"Towards General Agentic Intelligence via Environment Scaling","created":"2025-09-16","cited_by_count":54,"area":"agents"},{"id":"2604.18292","title":"Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence","created":"2026-04-20","cited_by_count":54,"area":"agents"},{"id":"2505.18878","title":"CRMArena-Pro: Holistic Assessment of LLM Agents Across Diverse Business Scenarios and Interactions","created":"2025-05-24","cited_by_count":47,"area":"agents"},{"id":"2603.20278","title":"OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis","created":"2026-03-17","cited_by_count":37,"area":"agents"},{"id":"2602.13379","title":"Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents","created":"2026-02-13","cited_by_count":30,"area":"agents"},{"id":"2605.22166","title":"Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents","created":"2026-05-21","cited_by_count":27,"area":"agents"},{"id":"2511.04847","title":"Test-Time Adaptation for LLM Agents via Environment Interaction","created":"2025-11-06","cited_by_count":20,"area":"agents"},{"id":"2605.20876","title":"Terminal-World: Scaling Terminal-Agent Environments via Agent Skills","created":"2026-05-20","cited_by_count":20,"area":"agents"},{"id":"2510.10197","title":"Don't Just Fine-tune the Agent, Tune the Environment","created":"2025-10-11","cited_by_count":19,"area":"agents"},{"id":"2509.17325","title":"Generalizable End-to-End Tool-Use RL with Synthetic CodeGym","created":"2025-09-22","cited_by_count":17,"area":"agents"},{"id":"2511.01934","title":"Tool Zero: Training Tool-Augmented LLMs via Pure RL from Scratch","created":"2025-11-02","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":"2601.20144","title":"Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents","created":"2026-01-28","cited_by_count":14,"area":"agents"},{"id":"2602.12268","title":"CM2: Reinforcement Learning with Checklist Rewards for Multi-Turn and Multi-Step Agentic Tool Use","created":"2026-02-12","cited_by_count":14,"area":"agents"},{"id":"2603.21383","title":"PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost","created":"2026-03-22","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":"2509.14480","title":"Process-Supervised Reinforcement Learning for Interactive Multimodal Tool-Use Agents","created":"2025-09-17","cited_by_count":12,"area":"agents"},{"id":"2601.05163","title":"DocDancer: Towards Agentic Document-Grounded Information Seeking","created":"2026-01-08","cited_by_count":12,"area":"agents"},{"id":"2508.12685","title":"ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn Interaction","created":"2025-08-18","cited_by_count":11,"area":"agents"},{"id":"2508.19504","title":"Aegis: Taxonomy and Optimizations for Overcoming Agent-Environment Failures in LLM Agents","created":"2025-08-27","cited_by_count":10,"area":"agents"},{"id":"2510.07043","title":"COMPASS: Benchmarking Constrained Optimization in LLM Agents","created":"2025-10-08","cited_by_count":9,"area":"agents"},{"id":"2511.05951","title":"Klear-AgentForge: Forging Agentic Intelligence through Posttraining Scaling","created":"2025-11-08","cited_by_count":9,"area":"agents"},{"id":"2601.01498","title":"From Failure to Mastery: Generating Hard Samples for Tool-use Agents","created":"2026-01-04","cited_by_count":8,"area":"agents"},{"id":"2601.21558","title":"ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas","created":"2026-01-29","cited_by_count":8,"area":"agents"},{"id":"2601.22027","title":"CAR-bench: Evaluating the Consistency and Limit-Awareness of LLM Agents under Real-World Uncertainty","created":"2026-01-29","cited_by_count":8,"area":"agents"},{"id":"2603.05520","title":"Information-Theoretic Privacy Control for Sequential Multi-Agent LLM Systems","created":"2026-02-13","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":"2606.26027","title":"Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It","created":"2026-06-24","cited_by_count":7,"area":"agents"},{"id":"2602.09372","title":"AgentSkiller: Scaling Generalist Agent Intelligence through Semantically Integrated Cross-Domain Data Synthesis","created":"2026-02-10","cited_by_count":6,"area":"agents"},{"id":"2603.05553","title":"EigenData: A Self-Evolving Multi-Agent Platform for Function-Calling Data Synthesis, Auditing, and Repair","created":"2026-03-05","cited_by_count":6,"area":"agents"},{"id":"2603.10213","title":"Sabi\\'a-4 Technical Report","created":"2026-03-10","cited_by_count":6,"area":"agents"},{"id":"2604.09813","title":"Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning","created":"2026-04-10","cited_by_count":6,"area":"agents"},{"id":"2505.23662","title":"ToolHaystack: Stress-Testing Tool-Augmented Language Models in Realistic Long-Term Interactions","created":"2025-05-29","cited_by_count":5,"area":"agents"},{"id":"2509.14477","title":"Ticket-Bench: A Kickoff for Multilingual and Regionalized Agent Evaluation","created":"2025-09-17","cited_by_count":5,"area":"agents"},{"id":"2510.26167","title":"ToolRM: Towards Agentic Tool-Use Reward Modeling","created":"2025-10-30","cited_by_count":5,"area":"agents"},{"id":"2511.09572","title":"SynthTools: A Framework for Scaling Synthetic Tools for Agent Development","created":"2025-11-11","cited_by_count":5,"area":"agents"},{"id":"2601.00268","title":"Beyond Perfect APIs: A Comprehensive Evaluation of LLM Agents Under Real-World API Complexity","created":"2026-01-01","cited_by_count":5,"area":"agents"},{"id":"2602.03219","title":"Beyond Quantity: Trajectory Diversity Scaling for Code Agents","created":"2026-02-03","cited_by_count":5,"area":"agents"},{"id":"2509.23206","title":"PARL-MT: Learning to Call Functions in Multi-Turn Conversation with Progress Awareness","created":"2025-09-27","cited_by_count":4,"area":"agents"},{"id":"2508.20931","title":"How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on $\\tau$-bench","created":"2025-08-28","cited_by_count":3,"area":"agents"},{"id":"2510.06800","title":"FURINA: A Fully Customizable Role-Playing Benchmark via Scalable Multi-Agent Collaboration Pipeline","created":"2025-10-08","cited_by_count":3,"area":"agents"},{"id":"2511.21686","title":"Matrix: Peer-to-Peer Multi-Agent Synthetic Data Generation Framework","created":"2025-11-26","cited_by_count":3,"area":"agents"},{"id":"2512.13860","title":"Verification-Guided Context Optimization for Tool Calling via Hierarchical LLMs-as-Editors","created":"2025-12-15","cited_by_count":3,"area":"agents"},{"id":"2601.19914","title":"Simulating Complex Multi-Turn Tool Calling Interactions in Stateless Execution Environments","created":"2026-01-06","cited_by_count":3,"area":"agents"},{"id":"2603.24051","title":"FinToolSyn: A forward synthesis Framework for Financial Tool-Use Dialogue Data with Dynamic Tool Retrieval","created":"2026-03-25","cited_by_count":3,"area":"agents"},{"id":"2604.11557","title":"UniToolCall: Unifying Tool-Use Representation, Data, and Evaluation for LLM Agents","created":"2026-04-13","cited_by_count":3,"area":"agents"},{"id":"2606.12908","title":"SENTINEL: Failure-Driven Reinforcement Learning for Training Tool-Using Language Model Agents","created":"2026-06-11","cited_by_count":3,"area":"agents"},{"id":"2608.27260","title":"What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents","created":"2026-08-27","cited_by_count":3,"area":"agents"},{"id":"2602.11351","title":"Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization","created":"2026-02-11","cited_by_count":2,"area":"agents"},{"id":"2605.17558","title":"Firefly: Illuminating Large-Scale Verified Tool-Call Data Generation from Real APIs","created":"2026-05-17","cited_by_count":2,"area":"agents"},{"id":"2606.00135","title":"On Effectiveness and Efficiency of Agentic Tool-calling and RL Training","created":"2026-05-28","cited_by_count":2,"area":"agents"},{"id":"2606.02908","title":"WRIT: Write-Read Intensive Trajectory Synthesis for Multi-Turn User-Facing Agents","created":"2026-06-01","cited_by_count":2,"area":"agents"},{"id":"2606.11070","title":"T1-Bench: Benchmarking Multi-Scenario Agents in Real-World Domains","created":"2026-06-09","cited_by_count":2,"area":"agents"},{"id":"2607.14277","title":"Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making","created":"2026-07-15","cited_by_count":2,"area":"agents"},{"id":"2608.05141","title":"OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling","created":"2026-08-05","cited_by_count":2,"area":"agents"},{"id":"2608.22631","title":"Learning Generalizable Behaviors for Terminal Agents","created":"2026-08-23","cited_by_count":2,"area":"agents"},{"id":"2609.00949","title":"Calibration is the Bottleneck: An Action-Class Diagnostic of Multi-Turn Tool-Calling","created":"2026-09-01","cited_by_count":2,"area":"agents"},{"id":"2609.01736","title":"Harness Engineering in LLM Tool Use via Agent-Native Reusable Tool Primitives","created":"2026-09-01","cited_by_count":2,"area":"agents"},{"id":"2609.05837","title":"AgentBrew: Offline Tool-Use Agent Learning from Raw Real-World Trajectories","created":"2026-09-05","cited_by_count":2,"area":"agents"},{"id":"2512.11147","title":"MiniScope: A Least Privilege Framework for Authorizing Tool Calling Agents","created":"2025-12-11","cited_by_count":1,"area":"agents"},{"id":"2601.20412","title":"Beyond Accuracy: A Cognitive Load Framework for Mapping the Capability Boundaries of Tool-use Agents","created":"2026-01-28","cited_by_count":1,"area":"agents"},{"id":"2602.19218","title":"Gecko: A Simulation Environment with Stateful Feedback for Refining Agent Tool Calls","created":"2026-02-22","cited_by_count":1,"area":"agents"},{"id":"2603.21630","title":"EnterpriseLab: A Full-Stack Platform for developing and deploying agents in Enterprises","created":"2026-03-23","cited_by_count":1,"area":"agents"},{"id":"2605.03476","title":"CuraView: A Multi-Agent Framework for Medical Hallucination Detection with GraphRAG-Enhanced Knowledge Verification","created":"2026-05-05","cited_by_count":1,"area":"agents"},{"id":"2605.12521","title":"ToolWeave: Structured Synthesis of Complex Multi-Turn Tool-Calling Dialogues","created":"2026-04-03","cited_by_count":1,"area":"agents"},{"id":"2606.02001","title":"Scaling Agentic Capabilities via Grounded Interaction Synthesis","created":"2026-06-01","cited_by_count":1,"area":"agents"},{"id":"2606.11520","title":"ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories","created":"2026-06-09","cited_by_count":1,"area":"agents"},{"id":"2608.20314","title":"MidTool: Mid-training Data Synthesis for Agentic Tool Use","created":"2026-08-20","cited_by_count":1,"area":"agents"},{"id":"2609.06124","title":"SAP: State-Guided Data Synthesis with Argument Provenance for Multi-Turn Tool Use","created":"2026-09-05","cited_by_count":1,"area":"agents"},{"id":"2506.13818","title":"The Synthetic Mirror -- Synthetic Data at the Age of Agentic AI","created":"2025-06-15","cited_by_count":0,"area":"agents"},{"id":"2510.17235","title":"Coinvisor: An RL-Enhanced Chatbot Agent for Interactive Cryptocurrency Investment Analysis","created":"2025-10-20","cited_by_count":0,"area":"agents"},{"id":"2602.16379","title":"Label-Consistent Data Generation for Aspect-Based Sentiment Analysis Using LLM Agents","created":"2026-02-18","cited_by_count":0,"area":"agents"},{"id":"2604.10917","title":"HTAA: Enhancing LLM Planning via Hybrid Toolset Agentization & Adaptation","created":"2026-04-13","cited_by_count":0,"area":"agents"},{"id":"2605.18805","title":"RecoAtlas: From Semantic Plausibility to Set-Level Utility in LLM Recommendation Agents","created":"2026-05-11","cited_by_count":0,"area":"agents"},{"id":"2605.28556","title":"A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks","created":"2026-05-27","cited_by_count":0,"area":"agents"},{"id":"2605.29561","title":"ParaTool: Shifting Tool Representations from Context to Parameters","created":"2026-05-28","cited_by_count":0,"area":"agents"},{"id":"2607.29250","title":"Data Turnstile: A Scalable Open Framework for Function-Calling Data Generation","created":"2026-07-31","cited_by_count":0,"area":"agents"},{"id":"2608.03071","title":"Getting the Parameters Right: A Difficulty-Graded Benchmark and Probe-Guided Training for LLM Tool Calls","created":"2026-08-04","cited_by_count":0,"area":"agents"},{"id":"2608.06057","title":"When History Lies: Evaluating and Improving Tool Use under Misleading Multi-Turn Histories","created":"2026-08-06","cited_by_count":0,"area":"agents"},{"id":"2608.26133","title":"Agent Seer: Synthesizing Scenarios from Specification Understanding","created":"2026-06-24","cited_by_count":0,"area":"agents"},{"id":"2608.26563","title":"SPT: Skills as Pre-Training Data for Agentic Language Models","created":"2026-08-27","cited_by_count":0,"area":"agents"},{"id":"2609.05395","title":"Multi-Step Tool-Calling over Korean Open Public APIs: A Benchmark and a Data-Synthesis Recipe","created":"2026-09-04","cited_by_count":0,"area":"agents"},{"id":"2609.09072","title":"ToolLoop: Closed-Loop Tool-Use Data Synthesis via Decomposed Generation and Dynamic Self-Feedback","created":"2026-09-08","cited_by_count":0,"area":"agents"},{"id":"2609.22592","title":"AutoGym: Blueprint-First Generation of Verifiable Agent Gyms","created":"2026-09-18","cited_by_count":0,"area":"agents"},{"id":"2609.24115","title":"EDGEGEN: Improving Tool-Calling Agents Beyond Happy Paths with Synthetic Edge Case Generation","created":"2026-09-21","cited_by_count":0,"area":"agents"},{"id":"2609.36887","title":"WEFT: Scaling Tool-Use Post-Training for General-Purpose Agents","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2610.09163","title":"ToolRACER: A Robust Agentic Conversation Emulation Resource for Agent Training and Evaluation","created":"2026-10-06","cited_by_count":0,"area":"agents"},{"id":"2610.10549","title":"Synthesis Through Simulation: Generating Coherent Enterprise Data via Scalable Agent-System Interaction","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2610.12593","title":"Know What You Don't Know: Agentic Data Synthesis by Evolving Generation Space for Closed-Loop Learning","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.18459","title":"Teacher-Guided Tool Learning for Small Language Models via Bidirectional KL Constraints","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.18881","title":"Following the Flow the Law Requires: Training Voice Agents to Transfer to Unseen Regulated Procedures in Debt Collection","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.19686","title":"Interlock: From Local Correctness to Task Completion in Long-Horizon Agents","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}