Agent Systems

Scene Map-based Prompt Tuning for Navigation Instruction Generation CVPR 2025 SCE: Semantic Consistency Enhanced Reinforcement Learning for Multi-Hop Knowledge Graph Reasoning EMNLP 2025 SciCompanion: Graph-Grounded Reasoning for Structured Evaluation of Scientific Arguments EMNLP 2025 ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery ICLR 2025 SCRIBE: Structured Chain Reasoning for Interactive Behaviour Explanations using Tool Calling EMNLP 2025 ScriptSmith: A Unified LLM Framework for Enhancing IT Operations via Automated Bash Script Generation, Assessment, and Refinement AAAI 2025 SD2Actor: Continuous State Decomposition via Diffusion Embeddings for Robotic Manipulation ICCV 2025 SDPO: Segment-Level Direct Preference Optimization for Social Agents ACL 2025 Searching for the Most Human-like Emergent Language EMNLP 2025 Search-o1: Agentic Search-Enhanced Large Reasoning Models EMNLP 2025 Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing Uncertainty EMNLP 2025 See, Point, Fly: A Learning-Free VLM Framework for Universal Unmanned Aerial Navigation CoRL 2025 Self-Correcting Code Generation Using Small Language Models EMNLP 2025 Self-Correcting Robot Manipulation via Gaussian-Splatted Foresight AAAI 2025 SELF-EVOLVED REWARD LEARNING FOR LLMS ICLR 2025 Self-Evolving Multi-Agent Collaboration Networks for Software Development ICLR 2025 SELFGOAL: Your Language Agents Already Know How to Achieve High-level Goals NAACL 2025 Self-Guided Function Calling in Large Language Models via Stepwise Experience Recall EMNLP 2025 Self Knowledge-Tracing for Tool Use (SKT-Tool): Helping LLM Agents Understand Their Capabilities in Tool Use NAACL 2025 Self-Play Q-Learners Can Provably Collude in the Iterated Prisoner’s Dilemma ICML 2025 Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models ICLR 2025 Self-Taught Agentic Long Context Understanding ACL 2025 Self-Training Large Language Models for Tool-Use Without Demonstrations NAACL 2025 Semantic Exploration with Adaptive Gating for Efficient Problem Solving with Language Models ACL 2025 Semantic Glitch: Agency and Artistry in an Autonomous Pixel Cloud NeurIPS 2025