EP255: MUSE-Autoskill creates self-evolving AI agents

EP302: Transferable interaction patterns for web agents

Title: Beyond Domains: Reusing Web Skills via Transferable Interaction Patterns Source: http://arxiv.org/abs/2606.17645v1 Summary: This paper introduces SkillMigrator and Transferable Interaction Patterns, a novel framework that allows web agents to generalize interaction skills across diverse sites by matching layout structures rather than specific element references. This approach addresses a core scalability bottleneck in agentic AI by significantly reducing action counts and token consumption while maintaining high success rates.

EP301: VeriGraph Makes AI Data Analysis Verifiable

Title: VeriGraph: Towards Verifiable Data-Analytic Agents Source: http://arxiv.org/abs/2606.16603v1 Summary: This paper introduces a novel neuro-symbolic reasoning framework that replaces linear text trajectories with explicit evidence-based directed acyclic graphs to ensure structural traceability. It provides a significant breakthrough in agentic verifiability by grounding natural-language claims in deterministic computations and raw data sources.

EP300: Tensors prevent multi-agent LLM collisions

Title: Tensor-Coord: Algebraic Decomposition of Joint Plan Tensors for Conflict-Free Multi-Agent LLM Planning Source: http://arxiv.org/abs/2606.16478v1 Summary: This work establishes a foundational algebraic primitive for multi-agent coordination by representing joint plans as third-order tensors and using Canonical Polyadic decomposition to identify latent conflicts. It introduces a computable coordination complexity measure that allows agents to localize and resolve planning failures through interpretable mathematical factors.

EP299: STRIDE grades the AI scratchpad

Title: STRIDE: Strategic Trajectory Reasoning via Discriminative Estimation for Verifiable Reinforcement Learning Source: http://arxiv.org/abs/2606.15866v1 Summary: STRIDE introduces a novel Reinforcement Learning with Verifiable Rewards (RLVR) framework that identifies and rewards specific decision-relevant strategic patterns using discriminative estimation. By solving the sparse supervision bottleneck and enabling precise credit assignment, it provides a foundational methodology for advancing the reasoning capabilities of large language models.

EP298: LLM-as-Code Fixes Unreliable AI Agents

Title: LLM-as-Code Agentic Programming for Agent Harness Source: http://arxiv.org/abs/2606.15874v1 Summary: This paper proposes a fundamental architectural shift by replacing probabilistic LLM-based orchestration with deterministic 'Agentic Programming' where code governs the control flow. This framework eliminates control-flow hallucinations and token explosion, establishing a robust new primitive for building reliable, long-horizon agentic systems.