11 posts published in the last hour
- 10:33RealWorldShop: Benchmarking and Improving Conversational Shopping Agents in Real-World E-commerce
- 10:33Alleviating Hallucination in Reasoning Tasks with Training-Free Uncertainty-Guided Steering
- 10:33Targeted Retrieval, Compact Representations: How CoT Reasoning Improves Long-Context Counting
- 10:33When Order Matters: First-Speaker Bias and Mitigation through Personality in Sequential Multi-Agent Debate
- 10:32Routing Probes Can Improve Without New Information: An Exact-Null Audit of Uncertainty Beyond Model Outputs
- 10:03Prototype-guided Bilateral Alignment Multimodal Federated Learning
- 10:03Risk-Aware Adaptive Evaluation: Finding High-Impact Failures Under Limited Budgets
- 10:03Learning What to Forget: Distributional Unlearning for LLM Representation Spaces
- 10:03How Much Can Reliability Drift Under a Fixed Confidence Distribution?
- 10:03Composing Task-specific Agent Harnesses at Test Time with Reusable Primitives
- 10:00AI News Brief Hourly Summary 2026-10-01 12h : 11 posts
