ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments Paper • 2609.19134 • Published 3 days ago • 73
ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents Paper • 2609.17523 • Published 4 days ago • 23
Discovery Foundation Models: Toward Open-Ended Discovery Intelligence Paper • 2609.15973 • Published 5 days ago • 30
CritICL: Inference-Time Weak-to-Strong Generalization from Small Language Model Failure Modes Paper • 2608.27455 • Published 23 days ago • 12
Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses Paper • 2608.24876 • Published 25 days ago • 30
FocusMem: Factorizing Content, Readout, and Trust in Latent GUI Memory Paper • 2608.04530 • Published Aug 5 • 14
Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning Paper • 2608.05139 • Published Aug 5 • 28
OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured Recalibration Paper • 2605.28805 • Published May 27 • 8
PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models Paper • 2606.19534 • Published Jun 17 • 66
LoomVideo: Unifying Multimodal Inputs into Video Generation and Editing Paper • 2606.06042 • Published Jun 4 • 25
Benchmarking and Evolving Reason-Reflect-Rectify for Reflective Visual Generation Paper • 2605.19639 • Published May 19
PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models Paper • 2606.19534 • Published Jun 17 • 66