EP235: How SAGE Fixes AI Memory

EP241: Accelerating game theory with linear algebra

Title: Parallelizing Counterfactual Regret Minimization Source: http://arxiv.org/abs/2605.14277v1 Summary: This work introduces a generalized framework that reframes counterfactual regret minimization as linear algebra operations, allowing for massive parallelization on modern hardware. By achieving a four-order-of-magnitude speedup, it provides a foundational efficiency breakthrough for the reasoning algorithms central to strategic decision-making in complex environments.

EP240: Small AI agents beat giants with Orchard

Title: Orchard: An Open-Source Agentic Modeling Framework Source: http://arxiv.org/abs/2605.15040v1 Summary: Orchard provides a scalable open-source framework for agentic modeling, introducing reusable environment primitives and training recipes that enable LLMs to achieve state-of-the-art performance on complex tasks. It addresses critical gaps in agent infrastructure by standardizing sandbox management and introducing credit-assignment SFT for learning from unresolved trajectories.

EP239: The shift from chatbots to AI societies

Title: Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems Source: http://arxiv.org/abs/2605.14892v1 Summary: This work introduces the LIFE progression framework, which formally characterizes the causal dependencies between agent foundation, collaboration, failure attribution, and autonomous self-evolution. It establishes a foundational conceptual roadmap for building self-organizing multi-agent systems that can continuously diagnose and refine their own collective intelligence.

EP238: SepsisAgent outperforms clinicians using clinical world models

Title: Agentifying Patient Dynamics within LLMs through Interacting with Clinical World Model Source: http://arxiv.org/abs/2605.14723v1 Summary: This work presents a novel world-model-augmented agentic reasoning loop that utilizes a 'propose-simulate-refine' workflow to ground LLM decisions in action-conditioned dynamics. It demonstrates how integrating world models with agentic reinforcement learning can significantly improve decision-making safety and efficacy in complex environments.

EP237: Why AI agents must map before acting

Title: MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning Source: http://arxiv.org/abs/2605.13037v1 Summary: MAP proposes a paradigm shift for interactive agents by establishing environmental understanding through structured cognitive mapping before task execution. This approach overcomes the epistemic bottlenecks and inefficient failure cycles inherent in traditional reactive, goal-conditioned stepwise planning.