11 posts published in the last hour
- 09:33Reasoning Externalization for Faithful Large Language Model Narratives of Stock Return Predictions
- 09:33When Context Changes: Understanding Update Failures in LLMs
- 09:33Talk2Agent: Benchmarking Voice Interfaces for Text Agents
- 09:33Consistent Plan-Act for Long-Horizon Agentic Tasks
- 09:33STRATA: Self-Learning Through Role-Aligned Tiered Agents for Real-Time Strategy Games
- 09:03Whose Voice Survives the Summary? A Voice-Retention Audit of LLM Employee Listening
- 09:03More Choices, Fewer Decisions: Ordinal-Scale Bias in JEV-like Direct-Decision Models
- 09:03OpenJev-RLCD: A Working RLCD Implementation
- 09:03When Reasoning Goes Astray: Attention Dynamics of Uncontrolled Reasoning
- 09:03Diversity Combining for Multi-Path LLM Reasoning
- 09:00AI News Brief Hourly Summary 2026-10-01 11h : 12 posts
