A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM Paper • 2609.07821 • Published 2 days ago • 10
RealSWE: A Compositional Evaluation of Coding Agents under Realistic User Requests Paper • 2608.27831 • Published 10 days ago • 31
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments Paper • 2609.04148 • Published 7 days ago • 290
Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training Paper • 2608.26730 • Published 14 days ago • 150