11 posts published in the last hour
- 13:33STAR-GRPO: Canonical Anchoring and Reliability-First Advantages against Representation-Dependent Reward Hacking
- 13:33Beyond Sub-Gaussian Detector Scores: Robust Weighted Profile-Loss Change Point Detection for Human-LLM Text Segmentation
- 13:33HorizonFlow: Variable-Length Planning for Offline Goal-Conditioned RL
- 13:33PrecogUI: Proactive GUI Agents via Pre-cognitive Simulation and Experience Retrieval
- 13:33Harness Evolution as Learning: Approximation, Generalization, and Optimization Limits of Self-Improving Personal Agents
- 13:04State Trace Rationale As Auxiliary Task in Reinforcement Learning
- 13:04IronLLM: Forging Compact Edge-Native Language Models for Real-Time Embodied Intelligence
- 13:03WEFT: Scaling Tool-Use Post-Training for General-Purpose Agents
- 13:03When Upstream Messages Override Correct Answers: A Controlled Study of Multi-Agent LLM Collaboration
- 13:03Automated Screw Planning for Reduced Pelvic Fractures Based on Statistical Shape Models and Deep Learning
- 13:00AI News Brief Hourly Summary 2026-09-30 15h : 14 posts
