{"total":11,"rows":[{"id":"2402.07221","title":"The Reasons that Agents Act: Intention and Instrumental Goals","created":"2024-02-11","cited_by_count":23,"area":"agents"},{"id":"2411.03865","title":"AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-Making","created":"2024-11-06","cited_by_count":20,"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":"2411.04679","title":"CaPo: Cooperative Plan Optimization for Efficient Embodied Multi-Agent Cooperation","created":"2024-11-07","cited_by_count":12,"area":"agents"},{"id":"2512.03318","title":"Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia","created":"2025-12-03","cited_by_count":12,"area":"agents"},{"id":"2406.05872","title":"STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Models","created":"2024-06-09","cited_by_count":8,"area":"agents"},{"id":"2411.12977","title":"MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Cultural Learning","created":"2024-11-20","cited_by_count":5,"area":"agents"},{"id":"2502.11312","title":"AI Generations: From AI 1.0 to AI 4.0","created":"2025-02-16","cited_by_count":2,"area":"agents"},{"id":"2507.14995","title":"LLM-Enhanced Multi-Agent Reinforcement Learning with Expert Workflow for Real-Time P2P Energy Trading","created":"2025-07-20","cited_by_count":2,"area":"agents"},{"id":"2604.17502","title":"Towards Shutdownable Agents: Generalizing Stochastic Choice in RL Agents and LLMs","created":"2026-04-19","cited_by_count":1,"area":"agents"},{"id":"2603.15418","title":"MA-VLCM: A Vision Language Critic Model for Value Estimation of Policies in Multi-Agent Team Settings","created":"2026-03-16","cited_by_count":0,"area":"agents"}],"next_cursor":null}