11 posts published in the last hour
- 07:32LongHarness: Advancing Agentic Reasoning over 100M-Token Corpora via Stateful Evidence Management
- 07:32VETR: Execution-Grounded Self-Improving Agent for Symbolic Graphics Reasoning
- 07:32When Faster Decisions Do Not Make Better Agents: An Empirical Study of Jev in Agent Workflows
- 07:32SWEAR: Section-Wise Efficient Audio Reasoning via Self-Rated Difficulty
- 07:32Attention Sees, MLP Refuses: Tracing the Attention-to-MLP Safety Pathway in LLMs
- 07:02Travel Back To Move Forward: Retrospective Exploration and Evolving for Long Horizon Agents
- 07:02Hindsight Structured Advice Distillation: Steering Executor Agents with Advisors Trained on Their Failures and Task Characteristics
- 07:02EmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied Agents
- 07:02Provenance-Aware Belief Updating in Human-AI Feedback Loops
- 07:02Scaling Empowered Agents
- 07:00AI News Brief Hourly Summary 2026-10-12 09h : 11 posts