EP262: Web agents that learn from failure

EP272: AI rewiring its own brain live

Title: Scaling Self-Evolving Agents via Parametric Memory Source: http://arxiv.org/abs/2606.04536v1 Summary: This paper introduces a foundational framework for self-evolving agents that moves beyond static prompts by using online LoRA updates to adapt the model's parametric memory within a single episode. It establishes a new architectural paradigm where agents can genuinely learn and evolve their policy from experience, overcoming the limitations of frozen-weight architectures.

EP271: Steer locked AI with Agentic Monte Carlo

Title: Agentic Monte Carlo: Simulating Reinforcement Learning for Black-Box Agents Source: http://arxiv.org/abs/2606.05296v1 Summary: This work presents a foundational breakthrough for optimizing black-box LLM agents by applying the theoretical equivalence between reinforcement learning and Bayesian inference through Sequential Monte Carlo sampling. It enables principled, RL-style performance improvements for proprietary models by scaling test-time compute, providing a critical framework for steering agents without parameter-level access.

EP270: AI agents building their own reasoning tools

Title: Inducing Reasoning Primitives from Agent Traces Source: http://arxiv.org/abs/2606.02994v1 Summary: This work introduces a foundational reasoning loop that autonomously mines successful agent traces to codify recurrent reasoning moves into a reusable library of typed primitives. This method enables agents to systematically improve their own performance by discovering and abstracting their reasoning routines, matching or surpassing expert-authored decompositions.

EP269: Securing AI Agents with Agent libOS

Title: Agent libOS: A Library-OS-Inspired Runtime for Long-Running, Capability-Controlled LLM Agents Source: http://arxiv.org/abs/2606.03895v1 Summary: This paper introduces a novel architectural substrate that treats LLM agents as managed operating system processes with persistent identity, state, and capability-controlled resource access. It establishes a foundational runtime for long-running agentic actors by standardizing their lifecycle and authorization boundaries beyond simple tool-dispatch mechanisms.

EP268: How OpenWebRL masters the live web

Title: OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents Source: http://arxiv.org/abs/2606.02031v1 Summary: This paper introduces a comprehensive open framework for training visual web agents using online multi-turn reinforcement learning, overcoming the scalability limits of static datasets. It establishes a new state-of-the-art for open-source agents by providing the complete pipeline for browser interaction, multimodal context management, and policy optimization.