Agent Systems

SOAR: Supervision from Observation for Agentic Reinforcement Learning ACL 2026 SoMe: A Realistic Benchmark for LLM-based Social Media Agents AAAI 2026 SPARK: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning ACL 2026 SpatialActor: Exploring Disentangled Spatial Representations for Robust Robotic Manipulation AAAI 2026 SpatialScore: Towards Comprehensive Evaluation for Spatial Intelligence CVPR 2026 Speech-Hands: A Self-Reflection Voice Agentic Approach to Speech Recognition and Audio Reasoning with Omni Perception ACL 2026 SPIO: Ensemble and Selective Strategies via LLM-Based Multi-Agent Planning in Automated Data Science ACL 2026 SPIRAL: Symbolic LLM Planning via Grounded and Reflective Search AAAI 2026 STAPO: Selective Trajectory-Aware Policy Optimization for LLM Agent Training ACL 2026 Steering Visuomotor Policy in Open Worlds via Cross-View Goal Alignment AAAI 2026 Stop Fixating on Prompts: Reasoning Hijacking and Constraint Tightening for Red-Teaming LLM Agents ACL 2026 Structural Approach to Guiding a Present-Biased Agent AAAI 2026 Structure Detection for Contextual Reinforcement Learning AAAI 2026 Surgical AI Copilot: Energy-Based Fourier Gradient Low-Rank Adaptation for Surgical LLM Agent Reasoning and Planning AAAI 2026 Symphony: A Cognitively-Inspired Multi-Agent System for Long-Video Understanding CVPR 2026 SynthAgent: Adapting Web Agents with Synthetic Supervision ACL 2026 Synthia: Scalable Grounded Persona Generation from Social Media Data ACL 2026 T2Agent: A Tool-augmented Multimodal Misinformation Detection Agent with Monte Carlo Tree Search AAAI 2026 T4NMTD: Transition-Centric Reinforcement Learning for Non-Markovian Task Decomposition AAAI 2026 TacpAgent: Enhancing Student Engagement in Classroom Exercises Through LLM-Generated Feedback AAAI 2026 Tailoring Memory Granularity for Multi-Hop Reasoning over Long Contexts EACL 2026 Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment ACL 2026 Taming "Zombie" Agents: A Markov State-Aware Framework for Resilient Multi-Agent Evolution ACL 2026 Tapas Are Free! Training-Free Adaptation of Programmatic Agents via LLM-Guided Program Synthesis in Dynamic Environments AAAI 2026 TAPO: Dynamic Teacher and Perturbed Answer Injection for Policy Optimization AAAI 2026