{"total":167,"rows":[{"id":"2506.07982","title":"$\\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment","created":"2025-06-09","cited_by_count":627,"area":null},{"id":"2508.14444","title":"NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model","created":"2025-08-20","cited_by_count":108,"area":"lr"},{"id":"2510.08558","title":"Agent Learning via Early Experience","created":"2025-10-09","cited_by_count":85,"area":null},{"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":"2505.00024","title":"Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning","created":"2025-04-25","cited_by_count":68,"area":"lr"},{"id":"2602.10090","title":"Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning","created":"2026-02-10","cited_by_count":66,"area":"wm"},{"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":"2511.01824","title":"Simulating Environments with Reasoning Models for Agent Training","created":"2025-11-03","cited_by_count":57,"area":"lr"},{"id":"2508.20722","title":"rStar2-Agent: Agentic Reasoning Technical Report","created":"2025-08-28","cited_by_count":54,"area":"lr"},{"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":"2602.06820","title":"ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Training","created":"2026-02-06","cited_by_count":32,"area":null},{"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":"2602.13379","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":"2507.20152","title":"Goal Alignment in LLM-Based User Simulators for Conversational AI","created":"2025-07-27","cited_by_count":21,"area":null},{"id":"2601.22607","title":"From Self-Evolving Synthetic Data to Verifiable-Reward RL: Post-Training Multi-turn Interactive Tool-Using Agents","created":"2026-01-30","cited_by_count":21,"area":null},{"id":"2510.17797","title":"Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analytics","created":"2025-10-20","cited_by_count":20,"area":null},{"id":"2511.04847","title":"Test-Time Adaptation for LLM Agents via Environment Interaction","created":"2025-11-06","cited_by_count":20,"area":"agents"},{"id":"2601.06966","title":"RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction","created":"2026-01-11","cited_by_count":20,"area":null},{"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":"2509.23124","title":"Non-Collaborative User Simulators for Tool Agents","created":"2025-09-27","cited_by_count":18,"area":null},{"id":"2509.11963","title":"ToolRM: Outcome Reward Models for Tool-Calling Large Language Models","created":"2025-09-15","cited_by_count":17,"area":"lr"},{"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":"2511.09148","title":"LoopTool: Closing the Data-Training Loop for Robust LLM Tool Calls","created":"2025-11-12","cited_by_count":17,"area":null},{"id":"2512.22857","title":"AutoForge: Automated Environment Synthesis for Agentic Reinforcement Learning","created":"2025-12-28","cited_by_count":17,"area":"agents"},{"id":"2506.02918","title":"World Modelling Improves Language Model Agents","created":"2025-06-03","cited_by_count":14,"area":"wm"},{"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":"2601.10355","title":"Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text","created":"2026-01-15","cited_by_count":13,"area":null},{"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":"2607.22529","title":"Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills","created":"2026-07-24","cited_by_count":10,"area":"synth"},{"id":"2506.00235","title":"MedOrch: Medical Diagnosis with Tool-Augmented Reasoning Agents for Flexible Extensibility","created":"2025-05-30","cited_by_count":9,"area":"lr"},{"id":"2510.07043","title":"COMPASS: Benchmarking Constrained Optimization in LLM Agents","created":"2025-10-08","cited_by_count":9,"area":"agents"},{"id":"2510.24645","title":"FunReason-MT Technical Report: Advanced Data Synthesis Solution for Real-world Multi-Turn Tool-use","created":"2025-10-28","cited_by_count":9,"area":"lr"},{"id":"2511.05951","title":"Klear-AgentForge: Forging Agentic Intelligence through Posttraining Scaling","created":"2025-11-08","cited_by_count":9,"area":"agents"},{"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":"2505.18917","title":"Behavior Injection: Preparing Language Models for Reinforcement Learning","created":"2025-05-25","cited_by_count":8,"area":"lr"},{"id":"2510.06499","title":"Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels","created":"2025-10-07","cited_by_count":8,"area":"offlinerl"},{"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":"2603.07915","title":"Ares: Adaptive Reasoning Effort Selection for Efficient LLM Agents","created":"2026-03-09","cited_by_count":8,"area":"lr"},{"id":"2605.10832","title":"Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents","created":"2026-05-11","cited_by_count":8,"area":"lr"},{"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":"2508.05118","title":"Reasoning through Exploration: A Reinforcement Learning Framework for Robust Function Calling","created":"2025-08-07","cited_by_count":7,"area":"lr"},{"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":"2512.07287","title":"Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory","created":"2025-12-08","cited_by_count":6,"area":null},{"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":"2605.02572","title":"On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length","created":"2026-05-04","cited_by_count":6,"area":null},{"id":"2605.07847","title":"Measuring and Mitigating the Distributional Gap Between Real and Simulated User Behaviors","created":"2026-05-08","cited_by_count":6,"area":null},{"id":"2505.20192","title":"FunReason: Enhancing Large Language Models' Function Calling via Self-Refinement Multiscale Loss and Automated Data Refinement","created":"2025-05-26","cited_by_count":5,"area":"lr"},{"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":"2511.12429","title":"Tailored Primitive Initialization is the Secret Key to Reinforcement Learning","created":"2025-11-16","cited_by_count":4,"area":"lr"},{"id":"2511.13254","title":"Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance","created":"2025-11-17","cited_by_count":4,"area":null},{"id":"2603.01714","title":"TopoCurate:Modeling Interaction Topology for Tool-Use Agent Training","created":"2026-03-02","cited_by_count":4,"area":null},{"id":"2603.01940","title":"CoVe: Training Interactive Tool-Use Agents via Constraint-Guided Verification","created":"2026-03-02","cited_by_count":4,"area":null},{"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":"2607.07050","title":"When Top-K Misses the Decision: Tool-Call Drift in Multi-Teacher On-Policy Distillation","created":"2026-07-08","cited_by_count":4,"area":"distill"},{"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":"2602.12172","title":"Pedagogically-Inspired Data Synthesis for Language Model Knowledge Distillation","created":"2026-02-12","cited_by_count":3,"area":"synth"},{"id":"2603.16759","title":"TurnWise: The Gap between Single- and Multi-turn Language Model Capabilities","created":"2026-03-17","cited_by_count":3,"area":null},{"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":"2606.16215","title":"PACT: Privileged Trace Co-Training for Multi-Turn Tool-Use Agents","created":"2026-06-15","cited_by_count":3,"area":null},{"id":"2607.15660","title":"ToolVerse: Unlocking Massive Environments and Long-Horizon Tasks for Agentic Reinforcement Learning","created":"2026-07-17","cited_by_count":3,"area":"lr"},{"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":"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":"2602.01709","title":"ARTIS: Agentic Risk-Aware Test-Time Scaling via Iterative Simulation","created":"2026-02-02","cited_by_count":2,"area":"lr"},{"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":"2603.13348","title":"AutoTool: Automatic Scaling of Tool-Use Capabilities in RL via Decoupled Entropy Constraints","created":"2026-03-07","cited_by_count":2,"area":"lr"},{"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"}],"next_cursor":"100"}