EP268: How OpenWebRL masters the live web

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.

EP267: AI Agents That Update Their Own Imagination

Title: COMAP: Co-Evolving World Models and Agent Policies for LLM Agents Source: http://arxiv.org/abs/2606.02372v1 Summary: COMAP proposes a novel architectural primitive where textual world models and agent policies co-evolve through closed-loop interaction and self-distillation. This framework enables agents to adapt to dynamic environments by predicting future states and reflecting on action reliability, significantly improving long-horizon decision-making.

EP266: AI agents learn to think without words

Title: Adaptive Latent Agentic Reasoning Source: http://arxiv.org/abs/2606.02871v1 Summary: This paper introduces a dual-mode reasoning framework that dynamically alternates between compact latent reasoning and explicit chain-of-thought, optimizing the accuracy-efficiency trade-off for multi-turn agents. It establishes a significant architectural primitive by enabling agents to reserve heavy deliberation for complex decisions while maintaining high efficiency for routine tasks.

EP265: How AI agents rewrite their own tools

Title: SkillSmith: Co-Evolving Skills and Tools for Self-Improving Agent Systems Source: http://arxiv.org/abs/2606.01314v1 Summary: SkillSmith presents a foundational co-evolution framework that allows agents to simultaneously evolve their skill libraries and underlying toolsets through a synergy-aware reflection process. By utilizing an ecological utility model to manage skill-tool interactions, it establishes a novel architectural loop for autonomous, self-improving agent systems capable of repairing their own functional primitives.

EP264: Science Earth and Planet Scale AI Discovery

Title: Science Earth: Towards A Planet-Scale Operating System for AI-Native Scientific Discovery Source: http://arxiv.org/abs/2606.01316v1 Summary: It introduces a planet-scale scientific runtime and the EACN protocol, enabling decentralized AI capabilities to autonomously discover and negotiate task ownership. This shifts agentic orchestration from pre-designed workflows to emergent, self-correcting coordination for large-scale discovery.