DONIC: Generalist Dexterous Bimanual Tracking Control from Human Demonstrations Paper • 2610.29997 • Published 4 days ago • 160
Running Agents Featured 78 Demo Groq Tool Use 💬 78 Chat with a smart bot that can calculate expressions
More Memory, Worse Agents: Error Reproduction and Anti-Persistence in LLM Agents Paper • 2610.27406 • Published 6 days ago • 16
Self-Credit: Credit Assignment for Long-Horizon Agentic RL via Intra-group Rescaling Paper • 2610.28388 • Published 5 days ago • 11
EAU: Environment-Agent-User Co-evolution for Training User-Centric Agents Paper • 2610.16523 • Published 13 days ago • 22
FlowState: Execution State as Memory for Long-Horizon LLM Agents Paper • 2609.34565 • Published 17 days ago • 24
VLA-Rolling: Fewer Denoising Steps, Better Control via Adaptive Action Reuse Paper • 2610.25043 • Published 7 days ago • 64
OR-License: Evaluating LLM Agents as Real-World Operations Research Practitioners Paper • 2610.24087 • Published 9 days ago • 53
AdaExploreBench: Benchmarking LLM Agents for Proactive Exploration and Test-time Adaptation in Evolving Environments Paper • 2610.25950 • Published 6 days ago • 34
MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM Agents Paper • 2610.06830 • Published 20 days ago • 39
Think Visually Across Space and Time: Grounded Reasoning for Video Segmentation Paper • 2610.25090 • Published 7 days ago • 24