{"total":17,"rows":[{"id":"2403.08715","title":"SOTOPIA-$\\pi$: Interactive Learning of Socially Intelligent Language Agents","created":"2024-03-13","cited_by_count":93,"area":"agents"},{"id":"2404.11972","title":"Aligning Language Models to Explicitly Handle Ambiguity","created":"2024-04-18","cited_by_count":56,"area":"agents"},{"id":"2502.17543","title":"Training a Generally Curious Agent","created":"2025-02-24","cited_by_count":31,"area":"agents"},{"id":"2505.24787","title":"Draw ALL Your Imagine: A Holistic Benchmark and Agent Framework for Complex Instruction-based Image Generation","created":"2025-05-30","cited_by_count":30,"area":"agents"},{"id":"2510.10666","title":"BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions","created":"2025-10-12","cited_by_count":17,"area":"agents"},{"id":"2607.04763","title":"Multi-Turn On-Policy Distillation with Prefix Replay","created":"2026-07-06","cited_by_count":15,"area":"agents"},{"id":"2503.23427","title":"CoRanking: Collaborative Ranking with Small and Large Ranking Agents","created":"2025-03-30","cited_by_count":10,"area":"agents"},{"id":"2510.14008","title":"Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignment","created":"2025-10-15","cited_by_count":7,"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":"2503.12532","title":"STEVE: A Step Verification Pipeline for Computer-use Agent Training","created":"2025-03-16","cited_by_count":5,"area":"agents"},{"id":"2503.15129","title":"Aligning Crowd-sourced Human Feedback for Reinforcement Learning on Code Generation by Large Language Models","created":"2025-03-19","cited_by_count":3,"area":"agents"},{"id":"2510.13709","title":"Training LLM Agents to Empower Humans","created":"2025-10-15","cited_by_count":3,"area":"agents"},{"id":"2609.32805","title":"Decision-Sufficient State Representations: Measuring and Reducing Write-Time Regret","created":"2026-09-26","cited_by_count":1,"area":"agents"},{"id":"2606.02812","title":"Traj-Evolve: A Self-Evolving Multi-Agent System for Patient Trajectory Modeling in Lung Cancer Early Detection","created":"2026-06-01","cited_by_count":0,"area":"agents"},{"id":"2608.27672","title":"First Make It Playable, Then Make It Good: Staged Interaction Learning for Small Dialogue-Game Agents","created":"2026-08-27","cited_by_count":0,"area":"agents"},{"id":"2609.32827","title":"Improving LLM Collaboration via Multi-Agent Preference Learning","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2610.03631","title":"NeutronGym: Physics-Graded Neutron Instrument Design for LLM Agents","created":"2026-10-02","cited_by_count":0,"area":"agents"}],"next_cursor":null}