Agent Systems

Towards Capable and Secure Autonomous Computer-Use Agents (Student Abstract) AAAI 2026 Towards Closed-Loop Embodied Empathy Evolution: Probing LLM-Centric Lifelong Empathic Motion Generation in Unseen Scenarios AAAI 2026 Towards Effective and Efficient Multi-Agent Language Model Systems: Foundations, Prospects, and Applications ACL 2026 Towards Effective Code-Integrated Reasoning AAAI 2026 Towards Effective Offensive Security LLM Agents: Hyperparameter Tuning, LLM as a Judge, and a Lightweight CTF Benchmark AAAI 2026 Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling AAAI 2026 Towards GUI Agents: Vision-Language Diffusion Models for GUI Grounding CVPR 2026 Toward Simulating Networked Societies with Formal Institutions Using AI Agents AAAI 2026 Towards Open Environments and Instructions: General Vision-Language Navigation via Fast-Slow Interactive Reasoning CVPR 2026 TowerMind: A Tower Defence Game Learning Environment and Benchmark for LLM as Agents AAAI 2026 TPS-Bench: Evaluating AI Agents’ Tool Planning & Scheduling Abilities in Compounding Tasks ACL 2026 Training High-Level Schedulers with Execution-Feedback Reinforcement Learning for Long-Horizon GUI Automation CVPR 2026 Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning CVPR 2026 Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents ACL 2026 Transferable RL for Real-World Navigation Using Semantic Segmentation and Bird’s-Eye View Abstraction AAAI 2026 TraveLLaMA: A Multimodal Travel Assistant with Large-Scale Dataset and Structured Reasoning AAAI 2026 TTF-VLA: Temporal Token Fusion via Pixel-Attention Integration for Vision-Language-Action Models AAAI 2026 Turn-PPO: Turn-Level Advantage Estimation with PPO for Improved Multi-Turn RL in Agentic LLMs EACL 2026 UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization ACL 2026 UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning AAAI 2026 Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities ACL 2026 UniDataBench: Evaluating Data Analytics Agents Across Structured and Unstructured Data ACL 2026 Unintended Misalignment from Agentic Fine-Tuning: Risks and Mitigation AAAI 2026 UniToolBench: A Benchmark for Tool-Augmented LLMs in Cross-Domain, Universal Task Automation EACL 2026 Universal Guideline-Driven Image Clustering via a Hybrid LLM Agent CVPR 2026