Thinking Inertia: LLMs Keep Thinking When Told Not To Paper • 2610.11765 • Published 11 days ago • 250
Behavioral Persistence and Incomplete Functional Transfer of Co-evolved Communication in Evolutionary Robotics Paper • 2609.38527 • Published 20 days ago • 4
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness Paper • 2609.20519 • Published Sep 17 • 140
DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training Paper • 2609.04094 • Published Sep 3 • 27