Agent Systems

One and Only at SemEval-2026 Task 2: Evaluating Zero-Shot Autonomous LLM Agents and Heuristic Proxies in Ecological Affect Forecasting SemEval 2026 Online Difficulty Filtering for Reasoning Oriented Reinforcement Learning EACL 2026 Online Multi-LLM Selection via Contextual Bandits Under Unstructured Context Evolution AAAI 2026 Online Robust Planning Under Model Uncertainty: A Sample-Based Approach AAAI 2026 Open-Domain Safety Policy Construction EACL 2026 OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior Simulation ACL 2026 Optimizing Urban Service Allocation with Time-Constrained Restless Bandits AAAI 2026 ORCA: Orchestrated Reasoning with Collaborative Agents for Document Visual Question Answering CVPR 2026 OrcheCause Agent: From Textual Knowledge to End-to-End Causal Inference AAAI 2026 Orion: Steering Personalized Web Agents via Global-Micro Profiling and Adaptive Intent Tracking AAAI 2026 ORVIT: Near-Optimal Online Distributionally Robust Reinforcement Learning AAAI 2026 OS-Oracle: A Comprehensive Framework for Cross-Platform GUI Critic Models CVPR 2026 OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows ACL 2026 OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agents ACL 2026 OxyGent: Making Multi-Agent Systems Modular, Observable, and Evolvable via Oxy Abstraction ACL 2026 PACE: Predictive Adaptive Context Extraction for Long-Horizon LLM Agents ACL 2026 PAGER: Proactive Monitoring Agent for Enterprise AI Assistant AAAI 2026 Paper2Figure: A Multi-Agent Collaborative System for Figure Generation Towards Academic Research Paper CVPR 2026 PaperSearchQA: Learning to Search and Reason over Scientific Papers with RLVR EACL 2026 ParaCodex: A Profiling-Guided Autonomous Coding Agent for Reliable Parallel Code Generation and Translation ACL 2026 PASS: Probabilistic Agentic Supernet Sampling for Interpretable and Adaptive Chest X-Ray Reasoning AAAI 2026 Patho-AgenticRAG: Towards Multimodal Agentic Retrieval-Augmented Generation for Pathology VLMs via Reinforcement Learning AAAI 2026 PatientVLM Meets DocVLM: Pre-Consultation Dialogue Between Vision-Language Models for Efficient Diagnosis AAAI 2026 PEARL: Self-Evolving Assistant for Time Management with Reinforcement Learning ACL 2026 PEAR: Planner-Executor Agent Robustness Benchmark EACL 2026