Agent Systems

KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents NAACL 2025 Knowing More, Acting Better: Hierarchical Representation for Embodied Decision-Making EMNLP 2025 Knowledge-Aware Co-Reasoning for Multidisciplinary Collaboration EMNLP 2025 Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles ACL 2025 L3GO: Language Agents with Chain-of-3D-Thoughts for Generating Unconventional Objects NAACL 2025 LAL: Enhancing 3D Human Motion Prediction with Latency-aware Auxiliary Learning CVPR 2025 LaMDAgent: An Autonomous Framework for Post-Training Pipeline Optimization via LLM Agents EMNLP 2025 LAM SIMULATOR: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedback ACL 2025 Language Guided Skill Discovery ICLR 2025 Language-Informed Synthesis of Rational Agent Models for Grounded Theory-of-Mind Reasoning On-the-fly EMNLP 2025 Language Models Can Infer Action Semantics for Symbolic Planners from Environment Feedback NAACL 2025 Large Language Model-driven Large Neighborhood Search for Large-Scale MILP Problems ICML 2025 Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning AAAI 2025 LATTE-MV: Learning to Anticipate Table Tennis Hits from Monocular Videos CVPR 2025 LAW: Legal Agentic Workflows for Custody and Fund Services Contracts COLING 2025 LeanAgent: Lifelong Learning for Formal Theorem Proving ICLR 2025 LEAP & LEAN: Look-ahead Planning and Agile Navigation for LLM Agents ACL 2025 Learn-by-interact: A Data-Centric Framework For Self-Adaptive Agents in Realistic Environments ICLR 2025 Learning 3D Scene Analogies with Neural Contextual Scene Maps ICCV 2025 Learning and Evaluating Factual Clarification Question Generation Without Examples ACL 2025 Learning API Functionality from In-Context Demonstrations for Tool-based Agents EMNLP 2025 Learning Evolving Tools for Large Language Models ICLR 2025 Learning Fine-Grained Alignment for Aerial Vision-Dialog Navigation AAAI 2025 Learning Hierarchical Task Knowledge for Planning AAAI 2025 Learning Logic Specifications for Policy Guidance in POMDPs: an Inductive Logic Programming Approach AAAI 2025