12 posts published in the last hour
- 23:32MeClear: Cooperative Game-Theoretic Attribution and Risk-Aware Memory Clearance for Long-Horizon LLM Agents
- 23:32SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?
- 23:32Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails
- 23:32A Generalization of Amari’s Bayesian Duality
- 23:32ExecCritic: Learn to Test, Test to Improve for Coding Agents
- 23:03Deposon: An Auditable, Conservation-Guaranteed, Game-Theoretically Tested Scattering Layer over LLM Reasoning Paths
- 23:03Time-Varying Data as Sheaves: an Invitation to Narratives
- 23:03The Surprising Effectiveness of Approximate Value Iteration in Self-Play
- 23:03Answer-Distribution Trajectories: A Stochastic-Dynamics View of LLM Reasoning
- 23:03Meet Redis LangCache: A Managed Semantic Cache That Cuts LLM API Costs by Up to 90% and Returns Cache Hits Up to 15x Faster
- 23:03Everything in Moderation: Per-Domain Coverage Optima and Alignment-Resistant Domain Gaps in Multi-Domain Mid-Training
- 23:00AI News Brief Hourly Summary 2026-09-11 01h : 16 posts