Artificial Intelligence › Core AI ›

Agent Systems

3885 directly classified papers

Papers per year

Papers

MEDDxAgent: A Unified Modular Agent Framework for Explainable Automatic Differential Diagnosis ACL 2025

Augmenting Multi-Agent Communication with State Delta Trajectory EMNLP 2025

MasRouter: Learning to Route LLMs for Multi-Agent Systems ACL 2025

EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safety EMNLP 2025

BOOKWORLD: From Novels to Interactive Agent Societies for Story Creation ACL 2025

Learning to Ask: When LLM Agents Meet Unclear Instruction EMNLP 2025

KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents NAACL 2025

Evaluating Cultural and Social Awareness of LLM Web Agents NAACL 2025

MMAU: A Holistic Benchmark of Agent Capabilities Across Diverse Domains NAACL 2025

Infogent: An Agent-Based Framework for Web Information Aggregation NAACL 2025

Adapting LLM Agents with Universal Communication Feedback NAACL 2025

Breaking ReAct Agents: Foot-in-the-Door Attack Will Get You In NAACL 2025

Guideline Compliance in Task-Oriented Dialogue: The Chained Prior Approach NAACL 2025

Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting NAACL 2025

Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents NAACL 2025

Hypothesis Generation for Materials Discovery and Design Using Goal-Driven and Constraint-Guided LLM Agents NAACL 2025

Tooling or Not Tooling? The Impact of Tools on Language Agents for Chemistry Problem Solving NAACL 2025

Meta-Reasoning Improves Tool Use in Large Language Models NAACL 2025

LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models NAACL 2025

A Human-LLM Note-Taking System with Case-Based Reasoning as Framework for Scientific Discovery NAACL 2025

Using LLMs to improve RL policies in personalized health adaptive interventions NAACL 2025

Creolization versus code-switching: An agent-based cognitive model for bilingual strategies in language contact NAACL 2025

Self Knowledge-Tracing for Tool Use (SKT-Tool): Helping LLM Agents Understand Their Capabilities in Tool Use NAACL 2025

Hybrid AI for Responsive Multi-Turn Online Conversations with Novel Dynamic Routing and Feedback Adaptation NAACL 2025

Open-World Skill Discovery from Unsegmented Demonstration Videos ICCV 2025