Artificial Intelligence › Core AI ›

Agent Systems

3885 directly classified papers

Papers per year

Papers

La VIDA: Towards a Motivated Goal Reasoning Agent (Abstract Reprint) AAAI 2026

A Compliant Robotic Leg Based on Fibre Jamming (Abstract Reprint) AAAI 2026

PRIMP: PRobabilistically-Informed Motion Primitives for Efficient Affordance Learning from Demonstration (Abstract Reprint) AAAI 2026

SICNav: Safe and Interactive Crowd Navigation Using Model Predictive Control and Bilevel Optimization (Abstract Reprint) AAAI 2026

Physics-Informed Autonomous LLM Agents for Explainable Power Electronics Modulation Design AAAI 2026

LLM-Based Agent for Competitive Landscape Mapping in Drug Asset Due Diligence AAAI 2026

InfrastructureSentinel: Policy Enforced Guardrails for Secure MCP-driven Infrastructure Agents AAAI 2026

MobileSafetyBench: Evaluating Safety of Autonomous Agents in Mobile Device Control AAAI 2026

FindTheFlaws: Annotated Errors for Detecting Flawed Reasoning and Scalable Oversight Research AAAI 2026

Promoting Sustainable Web Agents: Benchmarking and Estimating Energy Consumption Through Empirical and Theoretical Analysis AAAI 2026

Optimizing Urban Service Allocation with Time-Constrained Restless Bandits AAAI 2026

Toward Simulating Networked Societies with Formal Institutions Using AI Agents AAAI 2026

Probabilistic Hierarchical Goal Network Planning with UCT AAAI 2026

Incremental Data-Driven Policy Synthesis via Game Abstractions AAAI 2026

Online Robust Planning Under Model Uncertainty: A Sample-Based Approach AAAI 2026

Co-EPG: A Framework for Co-Evolution of Planning and Grounding in Autonomous GUI Agents AAAI 2026

A Parallel CPU-GPU Framework for Batching Heuristic Operations in Depth-First Heuristic Search AAAI 2026

MoralReason: Generalizable Moral Decision Alignment for LLM Agents Using Reasoning-Level Reinforcement Learning AAAI 2026

Unintended Misalignment from Agentic Fine-Tuning: Risks and Mitigation AAAI 2026

RealWebAssist: A Benchmark for Long-Horizon Web Assistance with Real-World Users AAAI 2026

ToolACE-R: Model-aware Iterative Training and Adaptive Refinement for Tool learning AAAI 2026

Prune4Web: DOM Tree Pruning Programming for Web Agent AAAI 2026

When Instinct Guides and Insight Grounds: Staged RL Training for LLM Agents AAAI 2026

AgentCDM: Enhancing Multi-Agent Collaborative Decision-Making via ACH-Inspired Structured Reasoning AAAI 2026

LaF-GRPO: In-Situ Navigation Instruction Generation for the Visually Impaired via GRPO with LLM-as-Follower Reward AAAI 2026