ACL2025中agent论文

白白要坚持

583人浏览 · 2025-10-16 20:31:19

白白要坚持 · 2025-10-16 20:31:19 发布

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