{"total":45,"rows":[{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808,"area":"agents"},{"id":"2402.02716","title":"Understanding the planning of LLM agents: A survey","created":"2024-02-05","cited_by_count":421,"area":"agents"},{"id":"2504.20073","title":"RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning","created":"2025-04-24","cited_by_count":386,"area":"agents"},{"id":"2205.12255","title":"TALM: Tool Augmented Language Models","created":"2022-05-24","cited_by_count":197,"area":"agents"},{"id":"2302.10329","title":"Harms from Increasingly Agentic Algorithmic Systems","created":"2023-02-20","cited_by_count":135,"area":"agents"},{"id":"2306.11706","title":"RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation","created":"2023-06-20","cited_by_count":111,"area":"agents"},{"id":"2305.16554","title":"Emergent Agentic Transformer from Chain of Hindsight Experience","created":"2023-05-26","cited_by_count":33,"area":"agents"},{"id":"2305.12487","title":"Augmenting Autotelic Agents with Large Language Models","created":"2023-05-21","cited_by_count":30,"area":"agents"},{"id":"2307.07871","title":"The SocialAI School: Insights from Developmental Psychology Towards Artificial Socio-Cultural Agents","created":"2023-07-15","cited_by_count":24,"area":"agents"},{"id":"2305.16183","title":"Passive learning of active causal strategies in agents and language models","created":"2023-05-25","cited_by_count":21,"area":"agents"},{"id":"2409.00134","title":"MAPF-GPT: Imitation Learning for Multi-Agent Pathfinding at Scale","created":"2024-08-29","cited_by_count":17,"area":"agents"},{"id":"2308.01552","title":"InterAct: Exploring the Potentials of ChatGPT as a Cooperative Agent","created":"2023-08-03","cited_by_count":16,"area":"agents"},{"id":"2405.15821","title":"Reinforcing Language Agents via Policy Optimization with Action Decomposition","created":"2024-05-23","cited_by_count":16,"area":"agents"},{"id":"2402.08078","title":"Large Language Models as Agents in Two-Player Games","created":"2024-02-12","cited_by_count":10,"area":"agents"},{"id":"2403.03141","title":"Language Guided Exploration for RL Agents in Text Environments","created":"2024-03-05","cited_by_count":9,"area":"agents"},{"id":"2405.17009","title":"Position: Foundation Agents as the Paradigm Shift for Decision Making","created":"2024-05-27","cited_by_count":9,"area":"agents"},{"id":"2412.11499","title":"Embodied CoT Distillation From LLM To Off-the-shelf Agents","created":"2024-12-16","cited_by_count":9,"area":"agents"},{"id":"2508.19506","title":"Learning Game-Playing Agents with Generative Code Optimization","created":"2025-08-27","cited_by_count":8,"area":"agents"},{"id":"2307.10936","title":"PASTA: Pretrained Action-State Transformer Agents","created":"2023-07-20","cited_by_count":6,"area":"agents"},{"id":"2409.04617","title":"Sparse Rewards Can Self-Train Dialogue Agents","created":"2024-09-06","cited_by_count":6,"area":"agents"},{"id":"2506.06366","title":"AI Agent Behavioral Science","created":"2025-06-04","cited_by_count":6,"area":"agents"},{"id":"2603.05044","title":"WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents","created":"2026-03-05","cited_by_count":6,"area":"agents"},{"id":"2508.08574","title":"DeepFleet: Multi-Agent Foundation Models for Mobile Robots","created":"2025-08-12","cited_by_count":4,"area":"agents"},{"id":"2604.27955","title":"GUI Agents with Reinforcement Learning: Toward Digital Inhabitants","created":"2026-04-30","cited_by_count":3,"area":"agents"},{"id":"2606.10507","title":"HIPIF: Hierarchical Planning and Information Folding for Long-Horizon LLM Agent Learning","created":"2026-06-09","cited_by_count":3,"area":"agents"},{"id":"2409.18538","title":"A Survey on Complex Tasks for Goal-Directed Interactive Agents","created":"2024-09-27","cited_by_count":2,"area":"agents"},{"id":"2602.00948","title":"FinEvo: From Isolated Backtests to Ecological Market Games for Multi-Agent Financial Strategy Evolution","created":"2026-02-01","cited_by_count":2,"area":"agents"},{"id":"2604.05808","title":"Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents","created":"2026-04-07","cited_by_count":2,"area":"agents"},{"id":"2606.12916","title":"MDForge: Agentic Molecular Dynamics Pipeline Design under Sparse Simulator Feedback","created":"2026-06-11","cited_by_count":2,"area":"agents"},{"id":"2402.05829","title":"Limitations of Agents Simulated by Predictive Models","created":"2024-02-08","cited_by_count":1,"area":"agents"},{"id":"2406.04208","title":"Aligning Agents like Large Language Models","created":"2024-06-06","cited_by_count":1,"area":"agents"},{"id":"2505.14727","title":"The Evolution of Alpha in Finance Harnessing Human Insight and LLM Agents","created":"2025-05-20","cited_by_count":1,"area":"agents"},{"id":"2604.13533","title":"Evolvable Embodied Agent for Robotic Manipulation via Long Short-Term Reflection and Optimization","created":"2026-04-15","cited_by_count":1,"area":"agents"},{"id":"2605.16024","title":"ScreenSearch: Uncertainty-Aware OS Exploration","created":"2026-05-15","cited_by_count":1,"area":"agents"},{"id":"2605.23652","title":"One Policy, Infinite NPCs: Persona-Traceable Shared RL Policies for Scalable Game Agents","created":"2026-05-22","cited_by_count":1,"area":"agents"},{"id":"2412.00949","title":"STEVE-Audio: Expanding the Goal Conditioning Modalities of Embodied Agents in Minecraft","created":"2024-12-01","cited_by_count":0,"area":"agents"},{"id":"2603.09641","title":"PRECEPT: Planning Resilience via Experience, Context Engineering & Probing Trajectories A Unified Framework for Test-Time Adaptation with Compositional Rule Learning and Pareto-Guided Prompt Evolution","created":"2026-03-10","cited_by_count":0,"area":"agents"},{"id":"2604.05943","title":"MARL-GPT: Foundation Model for Multi-Agent Reinforcement Learning","created":"2026-04-07","cited_by_count":0,"area":"agents"},{"id":"2604.23557","title":"DLM: Unified Decision Language Models for Offline Multi-Agent Sequential Decision Making","created":"2026-04-26","cited_by_count":0,"area":"agents"},{"id":"2606.22385","title":"MetaPS: Adaptive Programmatic Strategy Selection for Market Agents","created":"2026-06-21","cited_by_count":0,"area":"agents"},{"id":"2607.24779","title":"HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising","created":"2026-06-17","cited_by_count":0,"area":"agents"},{"id":"2608.01949","title":"A Self-Triggered Agentic Push Recommendation System","created":"2026-08-03","cited_by_count":0,"area":"agents"},{"id":"2608.03606","title":"Learning Clinical-Trial Strategy: Offline Policy Training for Decision Agents","created":"2026-08-04","cited_by_count":0,"area":"agents"},{"id":"2608.05954","title":"Training a Conditioned Video Game Agent on a VLM Annotated Dataset","created":"2026-08-06","cited_by_count":0,"area":"agents"},{"id":"2610.20597","title":"Co-Evolving Acting and Forecasting for Language Agents","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}