{"total":31,"rows":[{"id":"2504.06821","title":"Inducing Programmatic Skills for Agentic Tasks","created":"2025-04-09","cited_by_count":111,"area":"agents"},{"id":"2311.16714","title":"Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld","created":"2023-11-28","cited_by_count":65,"area":"agents"},{"id":"2405.16247","title":"AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning","created":"2024-05-25","cited_by_count":61,"area":"agents"},{"id":"2404.16660","title":"Benchmarking Mobile Device Control Agents across Diverse Configurations","created":"2024-04-25","cited_by_count":55,"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":"2406.11978","title":"Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner","created":"2024-06-17","cited_by_count":13,"area":"agents"},{"id":"2503.02077","title":"M3HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality","created":"2025-03-03","cited_by_count":11,"area":"agents"},{"id":"2505.16086","title":"Optimizing LLM-Based Multi-Agent System with Textual Feedback: A Case Study on Software Development","created":"2025-05-22","cited_by_count":7,"area":"agents"},{"id":"2404.09248","title":"Knowledgeable Agents by Offline Reinforcement Learning from Large Language Model Rollouts","created":"2024-04-14","cited_by_count":6,"area":"agents"},{"id":"2511.21572","title":"BAMAS: Structuring Budget-Aware Multi-Agent Systems","created":"2025-11-26","cited_by_count":6,"area":"agents"},{"id":"2505.19905","title":"EMAC+: Embodied Multimodal Agent for Collaborative Planning with VLM+LLM","created":"2025-05-26","cited_by_count":5,"area":"agents"},{"id":"2507.20796","title":"Aligning Large Language Model Agents with Rational and Moral Preferences: A Supervised Fine-Tuning Approach","created":"2025-07-28","cited_by_count":5,"area":"agents"},{"id":"2605.23989","title":"Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security","created":"2026-05-17","cited_by_count":5,"area":"agents"},{"id":"2310.04579","title":"Self-Confirming Transformer for Belief-Conditioned Adaptation in Offline Multi-Agent Reinforcement Learning","created":"2023-10-06","cited_by_count":4,"area":"agents"},{"id":"2606.04421","title":"Trivium: Temporal Regret as a First-Class Objective for Causal-Memory Controllers","created":"2026-06-03","cited_by_count":4,"area":"agents"},{"id":"2607.05458","title":"Learning to Control LLM Agent Harnesses with Offline Reinforcement Learning","created":"2026-07-05","cited_by_count":3,"area":"agents"},{"id":"2604.07784","title":"Automotive Engineering-Centric Agentic AI Workflow Framework","created":"2026-04-09","cited_by_count":2,"area":"agents"},{"id":"2604.11304","title":"BankerToolBench: Evaluating AI Agents in End-to-End Investment Banking Workflows","created":"2026-04-13","cited_by_count":2,"area":"agents"},{"id":"2604.19907","title":"SceneOrchestra: Efficient Agentic 3D Scene Synthesis via Full Tool-Call Trajectory Generation","created":"2026-04-21","cited_by_count":2,"area":"agents"},{"id":"2607.19450","title":"REGEN: Replay-recycling for Expert-to-Generalist distillation with Offline Reinforcement Learning","created":"2026-07-21","cited_by_count":2,"area":"agents"},{"id":"2406.04208","title":"Aligning Agents like Large Language Models","created":"2024-06-06","cited_by_count":1,"area":"agents"},{"id":"2602.02961","title":"Generative Engine Optimization: A VLM and Agent Framework for Pinterest Acquisition Growth","created":"2026-02-03","cited_by_count":1,"area":"agents"},{"id":"2603.05294","title":"STRUCTUREDAGENT: Planning with AND/OR Trees for Long-Horizon Web Tasks","created":"2026-03-05","cited_by_count":1,"area":"agents"},{"id":"2603.07148","title":"Agentic Planning with Reasoning for Image Styling via Offline RL","created":"2026-03-07","cited_by_count":1,"area":"agents"},{"id":"2604.06618","title":"PoC-Adapt: Semantic-Aware Automated Vulnerability Reproduction with LLM Multi-Agents and Reinforcement Learning-Driven Adaptive Policy","created":"2026-04-08","cited_by_count":1,"area":"agents"},{"id":"2604.07745","title":"The Cartesian Cut in Agentic AI","created":"2026-04-09","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":"2607.24779","title":"HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising","created":"2026-06-17","cited_by_count":0,"area":"agents"},{"id":"2608.03606","title":"Learning Clinical-Trial Strategy: Offline Policy Training for Decision Agents","created":"2026-08-04","cited_by_count":0,"area":"agents"},{"id":"2609.26261","title":"Coding Agents are Strong Prompt Optimizers","created":"2026-08-13","cited_by_count":0,"area":"agents"},{"id":"2610.02554","title":"Test-time Multi-agent Coordination by Decomposed Value Gradient Flow","created":"2026-10-01","cited_by_count":0,"area":"agents"}],"next_cursor":null}