{"total":61,"rows":[{"id":"2502.01600","title":"Reinforcement Learning for Long-Horizon Interactive LLM Agents","created":"2025-02-03","cited_by_count":108,"area":"agents"},{"id":"2503.23037","title":"Agentic Large Language Models, a survey","created":"2025-03-29","cited_by_count":108,"area":"agents"},{"id":"2509.21240","title":"Tree Search for LLM Agent Reinforcement Learning","created":"2025-09-25","cited_by_count":79,"area":"agents"},{"id":"2505.16944","title":"AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios","created":"2025-05-22","cited_by_count":49,"area":"agents"},{"id":"2602.21320","title":"Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data","created":"2026-02-24","cited_by_count":34,"area":"agents"},{"id":"2509.17158","title":"ARE: Scaling Up Agent Environments and Evaluations","created":"2025-09-21","cited_by_count":30,"area":"agents"},{"id":"2510.08529","title":"CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards","created":"2025-10-09","cited_by_count":29,"area":"agents"},{"id":"2510.01051","title":"GEM: A Gym for Agentic LLMs","created":"2025-10-01","cited_by_count":23,"area":"agents"},{"id":"2512.04388","title":"Learning to Orchestrate Agents in Natural Language with the Conductor","created":"2025-12-04","cited_by_count":23,"area":"agents"},{"id":"2509.22601","title":"Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning","created":"2025-09-26","cited_by_count":11,"area":"agents"},{"id":"2601.16206","title":"Computer Environments Elicit General Agentic Intelligence in LLMs","created":"2026-01-22","cited_by_count":11,"area":"agents"},{"id":"2601.11007","title":"AdaMARP: An Adaptive Multi-Agent Interaction Framework for General Immersive Role-Playing","created":"2026-01-16","cited_by_count":9,"area":"agents"},{"id":"2605.13909","title":"TERMS-Bench: Diagnosing LLM Negotiation Agents Beyond Deal Rate","created":"2026-05-13","cited_by_count":9,"area":"agents"},{"id":"2510.02557","title":"Orchestrating Human-AI Teams: The Manager Agent as a Unifying Research Challenge","created":"2025-10-02","cited_by_count":8,"area":"agents"},{"id":"2604.03675","title":"OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search","created":"2026-04-04","cited_by_count":7,"area":"agents"},{"id":"2603.16733","title":"IQuest-Coder-V1 Technical Report","created":"2026-03-17","cited_by_count":6,"area":"agents"},{"id":"2605.27209","title":"Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments","created":"2026-05-26","cited_by_count":6,"area":"agents"},{"id":"2508.03117","title":"Toward a Trustworthy Optimization Modeling Agent via Verifiable Synthetic Data Generation","created":"2025-08-05","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":"2602.19439","title":"OptiRepair: Closed-Loop Diagnosis and Repair of Supply Chain Optimization Models with LLM Agents","created":"2026-02-23","cited_by_count":5,"area":"agents"},{"id":"2605.11518","title":"AutoLLMResearch: Training Research Agents for Automating LLM Experiment Configuration - Learning from Cheap, Optimizing Expensive","created":"2026-05-12","cited_by_count":5,"area":"agents"},{"id":"2603.15432","title":"Gym-V: A Unified Vision Environment System for Agentic Vision Research","created":"2026-03-16","cited_by_count":3,"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":"2605.20061","title":"Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents","created":"2026-05-19","cited_by_count":3,"area":"agents"},{"id":"2608.21156","title":"Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence","created":"2026-08-21","cited_by_count":3,"area":"agents"},{"id":"2601.11658","title":"Towards AGI A Pragmatic Approach Towards Self Evolving Agent","created":"2026-01-15","cited_by_count":2,"area":"agents"},{"id":"2602.19000","title":"MagicAgent: Towards Generalized Agent Planning","created":"2026-02-22","cited_by_count":2,"area":"agents"},{"id":"2603.07853","title":"SynPlanResearch-R1: Encouraging Tool Exploration for Deep Research with Synthetic Plans","created":"2026-03-09","cited_by_count":2,"area":"agents"},{"id":"2604.10480","title":"Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs","created":"2026-04-12","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":"2604.23815","title":"DRACULA: Hunting for the Actions Users Want Deep Research Agents to Execute","created":"2026-04-26","cited_by_count":1,"area":"agents"},{"id":"2605.11280","title":"Discovery of Interpretable Surrogates via Agentic AI: Application to Gravitational Waves","created":"2026-05-11","cited_by_count":1,"area":"agents"},{"id":"2606.07513","title":"Agentopia: Long-Term Life Simulation and Learning in Agent Societies","created":"2026-06-05","cited_by_count":1,"area":"agents"},{"id":"2608.15763","title":"Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report","created":"2026-08-16","cited_by_count":1,"area":"agents"},{"id":"2609.18916","title":"Higher-order pruning of experts in mixture-of-experts language models","created":"2026-09-16","cited_by_count":1,"area":"agents"},{"id":"2510.13248","title":"Automated Network Protocol Testing with LLM Agents","created":"2025-10-15","cited_by_count":0,"area":"agents"},{"id":"2512.07474","title":"Living the Novel: A System for Generating Self-Training Timeline-Aware Conversational Agents from Novels","created":"2025-12-08","cited_by_count":0,"area":"agents"},{"id":"2605.30727","title":"MosaicLeaks:Privacy Risks in Querying-in-the-Open for Deep Research Agents","created":"2026-05-29","cited_by_count":0,"area":"agents"},{"id":"2606.03800","title":"Trading Human Curation for Synthetic Augmentation in RLVR","created":"2026-06-02","cited_by_count":0,"area":"agents"},{"id":"2606.06698","title":"RECAP: Regression Evaluation for Continual Adaptation of Prompts","created":"2026-06-04","cited_by_count":0,"area":"agents"},{"id":"2606.31693","title":"ShopX: A Foundation Model for Intent-to-Item Fulfillment in Agentic Shopping","created":"2026-06-30","cited_by_count":0,"area":"agents"},{"id":"2607.18147","title":"LLMs and Agentic AI Systems for Smart Grids: A Tutorial on Architectures and Applications","created":"2026-07-20","cited_by_count":0,"area":"agents"},{"id":"2607.25369","title":"ODYSSE: Episode-wise Policy Optimization for Personalized Agentic Reasoning","created":"2026-07-28","cited_by_count":0,"area":"agents"},{"id":"2607.27984","title":"Share the Judge, Learn the Deferral: Where Specialization Helps LLM Evaluation","created":"2026-07-30","cited_by_count":0,"area":"agents"},{"id":"2608.10579","title":"Agentic Instruction Data Selection: Let DataMaster Interpret Your Intent","created":"2026-08-11","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":"2608.30322","title":"Ignorance or Incompetence? Constructing Knowledge-Gated, Verifiable Tasks for LLM Agents","created":"2026-08-31","cited_by_count":0,"area":"agents"},{"id":"2609.00058","title":"CUDA-Harness: Harnessing Agentic CUDA Kernel Generation and Optimization from Natural Language","created":"2026-08-30","cited_by_count":0,"area":"agents"},{"id":"2609.13356","title":"ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search","created":"2026-09-11","cited_by_count":0,"area":"agents"},{"id":"2609.18779","title":"CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents","created":"2026-09-16","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":"2609.32081","title":"Toward Interactive Understanding of Code APIs","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2609.35741","title":"Shockingly Simple Self-retrospection Improves Agentic Models Without RL","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.37501","title":"Evaluating Bounded Autonomy in Regulated Agentic AI: A Diagnostic Harness with Constitutional Rewards, Escalation Labels, and Runtime Governance","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.00890","title":"Cross-Benchmark Transfer from RL on Agentic Coding Tasks","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.01207","title":"Dependency-Aware Reward Shaping for Agentic Reinforcement Learning","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.05923","title":"VERA: Scaling Verifiable Environments for Agentic co-Evolution","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"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":"2610.11922","title":"Project Greenhouse: Progress Toward Fully Open and Sovereign Agentic Search","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.17528","title":"ATTUNE: Agentic Throughput Tuning for LLM Training","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.19868","title":"Explorer-Zero: Improving Self-Play for Long-Horizon Tasks with Decomposable Verifiable Rewards","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}