ACL2025中agent论文

1. LegalAgentBench: Evaluating LLM Agents in Legal Domain
2. INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent
3. MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation
4. Context-Aware Sentiment Forecasting via LLM-based Multi-Perspective Role-Playing Agents
5. RAG-Critic: Leveraging Automated Critic-Guided Agentic Workflow for Retrieval Augmented Generation
6. Leveraging Dual Process Theory in Language Agent Framework for Real-time Simultaneous Human-AI Collaboration
7. BELLE: A Bi-Level Multi-Agent Reasoning Framework for Multi-Hop Question Answering
8. Self-Taught Agentic Long Context Understanding
9. OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis
10. GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent
11. X-TURING: Towards an Enhanced and Efficient Turing Test for Long-Term Dialogue Agents
12. AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection
13. In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents
14. SCALE: Towards Collaborative Content Analysis in Social Science with Large Language Model Agents and Human Intervention
15. KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph
16. GuideBench: Benchmarking Domain-Oriented Guideline Following for LLM Agents
17. Can a Single Model Master Both Multi-turn Conversations and Tool Use? CALM: A Unified Conversational Agentic Language Model
18. SDPO: Segment-Level Direct Preference Optimization for Social Agents
19. ReflecTool: Towards Reflection-Aware Tool-Augmented Clinical Agents
20. MEDDxAgent: A Unified Modular Agent Framework for Explainable Automatic Differential Diagnosis
21. Contextual Experience Replay for Continual Learning of Language Agents
22. ACT: Knowledgeable Agents to Design and Perform Complex Tasks
23. LLMs Can Simulate Standardized Patients via Agent Coevolution
24. ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents
25. Agent-RewardBench: Towards a Unified Benchmark for Reward Modeling across Perception, Planning, and Safety in Real-World Multimodal Agents
26. Tunable LLM-based Proactive Recommendation Agent
27. nvAgent: Automated Data Visualization from Natural Language via Collaborative Agent Workflow
28. Substance over Style: Evaluating Proactive Conversational Coaching Agents
29. CAMI: A Counselor Agent Supporting Motivational Interviewing through State Inference and Topic Exploration
30. Beyond Frameworks: Unpacking Collaboration Strategies in Multi-Agent Systems
31. AgentDropout: Dynamic Agent Elimination for Token-Efficient and High-Performance LLM-Based Multi-Agent Collaboration
32. SOTOPIA-Ω: Dynamic Strategy Injection Learning and Social Instruction Following Evaluation for Social Agents
33. OmniCharacter: Towards Immersive Role-Playing Agents with Seamless Speech-Language Personality Interaction
34. Controllable and Reliable Knowledge-Intensive Task Agents with Declarative GenieWorksheets
35. GETReason: Enhancing Image Context Extraction through Hierarchical Multi-Agent Reasoning
36. R2D2: Remembering, Replaying and Dynamic Decision Making with a Reflective Agentic Memory
37. CityNavAgent: Aerial Vision-and-Language Navigation with Hierarchical Semantic Planning and Global Memory
38. Teaching Text Agents to Learn Sequential Decision Making from Failure
39. EducationQ: Evaluating LLMs’ Teaching Capabilities Through Multi-Agent Dialogue Framework