EP202: Why ADEMA AI Never Loses The Plot

EP231: Amazon PIVOT solves the AI execution gap

Title: PIVOT: Bridging Planning and Execution in LLM Agents via Trajectory Refinement Source: http://arxiv.org/abs/2605.11225v1 Summary: PIVOT introduces a novel self-supervised framework that treats agent trajectories as optimizable objects refined through iterative environment feedback, bridging the gap between high-level planning and execution. This methodology establishes a principled approach to trajectory optimization that enhances both constraint satisfaction and computational efficiency in autonomous systems.

EP230: DeepRefine fixes messy AI knowledge bases

Title: DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning Source: http://arxiv.org/abs/2605.10488v1 Summary: DeepRefine establishes a general reinforcement learning framework for the autonomous refinement of agent-compiled knowledge bases using abductive diagnosis and a novel Gain-Beyond-Draft reward. It provides a foundational reasoning loop for maintaining persistent, high-fidelity external knowledge, which is essential for long-term agentic performance in knowledge-intensive tasks.

EP229: Ending the AI verbosity tax with LEAD

Title: LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models Source: http://arxiv.org/abs/2605.09806v1 Summary: LEAD establishes a foundational reinforcement learning mechanism for reasoning models that dynamically calibrates the balance between correctness and verbosity at each training step. It solves the critical issue of 'overthinking' in modern reasoning models by introducing online, per-problem length estimation, paving the way for more efficient and scalable reasoning architectures.

EP228: Why self-evolving AI forgets basic tasks

Title: Do Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptation Source: http://arxiv.org/abs/2605.09315v1 Summary: This paper introduces the 'capability erosion' framework to quantify how autonomous self-evolution can degrade an agent's prior knowledge across workflows and models. It proposes Capability-Preserving Evolution (CPE) as a necessary architectural constraint for building stable, lifelong learning agents that can adapt to new tasks without catastrophic forgetting.

EP227: FlowAgent fixes the AI tool bottleneck

Title: Tools as Continuous Flow for Evolving Agentic Reasoning Source: http://arxiv.org/abs/2605.07339v1 Summary: FlowAgent reconceptualizes agentic reasoning by replacing discrete, step-wise tool orchestration with continuous trajectory generation using conditional flow matching. This foundational framework provides theoretical guarantees for error attenuation and global planning, representing a significant shift in how agents execute long-horizon reasoning tasks.