EP259: The ESPO Kill Switch For AI Reasoning

EP275: AI Agents Building Their Own Coding Curriculum

Title: Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills Source: http://arxiv.org/abs/2606.07412v1 Summary: This work presents a closed-loop self-evolution framework where software agents learn by distilling their own historical solving traces into structured skills. This approach enables agents to autonomously generate and solve a targeted curriculum of tasks, significantly advancing the field of self-improving agentic systems.

EP274: Knowledge graphs fix AI memory loss

Title: TokenMizer: Graph-Structured Session Memory for Long-Horizon LLM Context Management Source: http://arxiv.org/abs/2606.06337v1 Summary: TokenMizer introduces a graph-structured architectural primitive for managing long-horizon session memory, replacing inefficient flat-text history with a typed knowledge graph. This system achieves significant token compression while preserving the structural rationale of complex tasks, solving a critical bottleneck in agentic context management.

EP273: Why agents make code disposable

Title: The End of Software Engineering: How AI Agents Are Fundamentally Restructuring the Software Paradigm Source: http://arxiv.org/abs/2606.05608v1 Summary: This paper formalizes the shift from code-centric logic to LLM-driven reasoning loops, defining the emergent discipline of "Agentic Engineering." It provides a theoretical framework for self-evolving agent ecosystems and a roadmap for the transition from SaaS to Agent-as-a-Service.

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.