Artificial Intelligence › Core AI ›

Agent Systems

3885 directly classified papers

Papers per year

Papers

Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone Agents AAAI 2026

IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks AAAI 2026

An Epistemic Perspective on Agent Awareness AAAI 2026

MCPTox: A Benchmark for Tool Poisoning on Real-World MCP Servers AAAI 2026

MPMA: Preference Manipulation Attack Against Model Context Protocol AAAI 2026

PRIME: Planning and Retrieval-Integrated Memory for Enhanced Reasoning AAAI 2026

Deep Research Arena: The First Exam of LLMs’ Research Abilities via Seminar-Grounded Tasks AAAI 2026

ShoppingBench: A Real-World Intent-Grounded Shopping Benchmark for LLM-based Agents AAAI 2026

Towards Closed-Loop Embodied Empathy Evolution: Probing LLM-Centric Lifelong Empathic Motion Generation in Unseen Scenarios AAAI 2026

Beyond Accuracy: A Cognitive Load Framework for Mapping the Capability Boundaries of Tool-use Agents AAAI 2026

A Rolling Stone Gathers No Moss: Adaptive Policy Optimization for Stable Self-Evaluation in Large Multimodal Models AAAI 2026

CP-Search: A Chain Progressive Search Training Framework Incentivizing the Cognitive Behaviors for Searching in LLMs AAAI 2026

Knowledge Boundary Discovery for Large Language Models AAAI 2026

SheetBrain: A Neuro-Symbolic Agent for Accurate Reasoning over Complex and Large Spreadsheets AAAI 2026

AutoLink: Autonomous Schema Exploration and Expansion for Scalable Schema Linking in Text-to-SQL at Scale AAAI 2026

Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning AAAI 2026

MetaAct-RL: Training Language Models for Reasoning Through Meta-Action-Based Reinforcement Learning AAAI 2026

AutoTool: Efficient Tool Selection for Large Language Model Agents AAAI 2026

MedS³: Towards Medical Slow Thinking with Self-Evolved Soft Dual-sided Process Supervision AAAI 2026

Efficient Thought Space Exploration Through Strategic Intervention AAAI 2026

Navigating the Infinite Dynamic Web Space: Effective In-Context Exploration via Cognitive Multi-Agent Collaboration EACL 2026

RefRea: Reference-Guided Reasoning with Meta-Cognition for Accurate Language Model Agents AAAI 2026

GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging AAAI 2026

ProgRAG: Hallucination-Resistant Progressive Retrieval and Reasoning over Knowledge Graphs AAAI 2026

Facilitating Early Maladaptive Schema–Guided Polite and Empathetic Psychotherapeutic Support: An LLM-Driven MoE-RL-Based Dialogue System AAAI 2026