Agent Systems

Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors ACL 2026 rosaOS: Agentic Operating System for Embodied LLMs ACL 2026 ROVER: Robust Generative Continual Identity Unlearning Against Relearning Attacks AAAI 2026 RSMeM: Knowledge-Enhanced Memory Evolution for Remote Sensing Agents with Systematic Evaluation ACL 2026 Run, Ruminate, and Regulate: A Dual-process Thinking System for Vision-and-Language Navigation AAAI 2026 S2O: Static to Openable Enhancement for Articulated 3D Objects WACV 2026 SABER: Switchable and Balanced Training for Efficient LLM Reasoning AAAI 2026 SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator ACL 2026 SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning ACL 2026 SafeSearch: Do Not Trade Safety for Utility in LLM Search Agents EACL 2026 SAGE: A Compositional Multi-Agent LLM Framework with Pedagogical Reasoning for Structured Collaborative Problem Solving AAAI 2026 SAGE : A Top-Down Bottom-Up Knowledge-Grounded User Simulator for Multi-turn Agent Evaluation EACL 2026 SAGE: Scalable Agentic 3D Scene Generation for Embodied AI CVPR 2026 SAGE: Steerable Agentic Data Generation for Deep Search with Execution Feedback EACL 2026 SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning CVPR 2026 SALT: Step-level Advantage Assignment for Long-horizon Agents via Trajectory Graph EACL 2026 SARA: Leveraging LLM Agents and Jurisprudential Ontologies for Automated Legal Reasoning AAAI 2026 Scaling Equitable Reflection Assessment in Education via Large Language Models and Role-Based Feedback Agents AAAI 2026 Scope Delineation Before Localization: A Two-Stage Framework for Enhancing Failure Attribution in Multi-Agent Systems AAAI 2026 SCoPE VLM: Selective Context Processing for Efficient Document Navigation in Vision-Language Models EACL 2026 SDialog: A Python Toolkit for End-to-End Agent Building, User Simulation, Dialog Generation, and Evaluation EACL 2026 SearchGym: Bootstrapping Real-World Search Agents via Cost-Effective and High-Fidelity Environment Simulation ACL 2026 SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents ACL 2026 Securing the Tool Layer: A Threat Taxonomy and Runtime Defense Framework for Model Context Protocol Deployments ACL 2026 See and Fix the Flaws: Enabling VLMs and Diffusion Models to Comprehend Visual Artifacts via Agentic Data Synthesis CVPR 2026