12 posts published in the last hour
- 05:32TimeEvo: Failure-Driven Self-Evolution of a Time Series Agent
- 05:32Enhancing Small Language Models for Power Outage Report Generation via Minimum Risk Training
- 05:32CAVEAT: Towards Robust Computer-Use Agents in Incentive-Misaligned Environments
- 05:32DRSR: Learning Set-Level Deletion Risk for Efficient Long-Horizon Agents
- 05:32Contrastive-LM Releases CLM-8B: An Open System One Model That Scores Agent Actions Up to 9× Faster Than Jev
- 05:32XLOG: A CUDA-Native Engine for Neurosymbolic Integration
- 05:03Math Reasoning in LLMs is Organized by Approach, Not Topic
- 05:03Policy-as-Skill: Governed LLM Decision Support with Evidence, Deterministic Control, and Audit
- 05:03Provably Complete Generalized Planning with LLMs
- 05:03Propose, Don’t Judge: An Anytime-Valid Referee for LLM Agents That Mine Investment Factors
- 05:03Do We Need Complex Topology Control? Distinct-Peer Random Routing Improves Cost-Efficiency in Sparse Multi-Agent Debate
- 05:00AI News Brief Hourly Summary 2026-09-24 07h : 11 posts