Episode Details

Today's papers: - X-AgentRed: Red-Teaming Personal Agents in Evolving Multi-Service Ecosystems: https://arxiv.org/abs/2610.13886v1 - Learning More by Training Less: Uncertainty-Guided Progressive Contraction for Efficient Reasoning Post-Training: https://arxiv.org/abs/2610.12933v1 - ReplaySSM: Cache SSM Inputs, Not State: https://arxiv.org/abs/2610.13778v1 - COFFEQA: Counterfactual-Guided Few-Shot Distillation for LLM Question Answering: https://arxiv.org/abs/2610.12837v1 - A Multi-Agent LLM System for Automated Tuning of Specialized Neural Network Models: https://arxiv.org/abs/2610.13663v1 This podcast is from Colin Davis (colin-davis.com) using Claude & Elevenlabs.