Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents Paper • 2610.20344 • Published 30 days ago • 46
Does Learning Protein Folding Generalize to Broader Reasoning? Paper • 2609.38879 • Published Sep 30 • 39
GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis Paper • 2609.38923 • Published Sep 30 • 60
DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents Paper • 2608.18524 • Published Aug 19 • 33