Trustworthy Recursive Self-Improvement in the Era of Large Models: Foundation, Risks, Evaluation and Open Challenges Paper • 2610.35193 • Published 22 days ago • 24
PhysSkin++: Real-Time and Generalizable Physics-Based Animation via Self-Supervised Neural Skinning Paper • 2610.26067 • Published 29 days ago • 23
MolLean: A Process-Verifiable Language for Chemical Reasoning Paper • 2610.20459 • Published Oct 14 • 11
Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition Paper • 2610.28578 • Published 28 days ago • 73
Scaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention Residuals Paper • 2610.11570 • Published Oct 8 • 9
HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing Agents Paper • 2610.03574 • Published Oct 2 • 23
PDE-JEPA: Predictive Representation Learning of Latent Dynamics Modeling for Parametric PDEs Paper • 2609.34715 • Published Sep 28 • 27
Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite Paper • 2610.02826 • Published Oct 2 • 38
Schrödinger's Code Repository: Have LLMs Learned SWE-bench or Memorized It? Paper • 2609.27891 • Published Aug 21 • 20
ParaTempo: Efficient Parallel Reasoning via Temporal Confidence Paper • 2608.16425 • Published Aug 17 • 41
Apodex Discovery: Reality Benchmarks and Environments for Evaluating and Building Discoverative Artificial Intelligence Paper • 2608.11341 • Published Aug 11 • 73
Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development Paper • 2608.13417 • Published Aug 13 • 60
Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search Paper • 2608.15669 • Published Aug 16 • 64
ChronoVision: Temporal Reasoning via Latent State Reconstruction Paper • 2608.05631 • Published Aug 6 • 18
Apple-π: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence Paper • 2607.16401 • Published Jul 17 • 44
UP: Unbounded Positive Asymmetric Optimization for Breaking the Exploration-Stability Dilemma Paper • 2607.06987 • Published Jul 8 • 9
Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation Paper • 2607.08758 • Published Jul 9 • 37
Holistic Data Scheduler for LLM Pre-training via Multi-Objective Reinforcement Learning Paper • 2606.24133 • Published Jun 23 • 12