11 posts published in the last hour
- 09:33RegulaTutor: A Theory-Informed Framework for Long-Term Personalized Learning
- 09:33Local Diagnostics of Learned Event Representations for Anomaly Detection at the HL-LHC
- 09:32SWE-Critix: Post-Training Generalist Verifiers for Assessing Coding-Agent Trajectories
- 09:32Rollout-Time Intervention: Unlocking Agentic Reinforcement Learning Beyond Policy Limits
- 09:32Web$hell: A Unified Interface for Agentic Web Access
- 09:02BoundaryEvo: Data-Model Co-Evolution at the Capability Boundary for Long-Chain Reasoning Distillation
- 09:02JANUS: Enhancing Long-Horizon Autonomous Research with Co-Evolving World Models
- 09:02AlphaNIST: Emergent Assembly Skills from Binary Task Rewards
- 09:02Masked Diffusion Language Agents for Tool-Integrated Chemical Reasoning
- 09:02Forgetting is Not Always Bad: A Neuro-Inspired Memory Repair Mechanism for Poisoned LLM Agents
- 09:00AI News Brief Hourly Summary 2026-10-12 11h : 10 posts