The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents Paper • 2610.36077 • Published 8 days ago • 48
Bridging Exploration and Persona: Information-Directed Dueling for Test-Time Agent Personalization Paper • 2610.24385 • Published 17 days ago • 8
GroundGUI: GUI Grounding by High-Quality Data and Distillation-to-Reinforcement Learning Paper • 2610.19100 • Published 21 days ago • 14
Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AI Paper • 2610.09146 • Published 28 days ago • 4
DecepEval: A Benchmark for Evaluating Deception in LLM Agents Paper • 2610.07967 • Published 28 days ago • 48
ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research Paper • 2610.02202 • Published Oct 1 • 12
Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents Paper • 2609.17708 • Published Sep 15 • 59