// Automata from agent traces // How much of your agent's behavior comes from the model, and how much from the harness you wrapped around it…

// Automata from agent traces // How much of your agent's behavior comes from the model, and how much from the harness you wrapped around it? New work collapses an entire corpus of agent traces into a single compact finite-state machine. Across twelve public datasets the induced machines run 7 to 43 states, replay held-out data at 0.997 fitness with near-identical topology across splits, and build in milliseconds. FSM-state context beats Agent Workflow Memory on every ground-truth-matched dataset for next-step prediction. Per-state behavioral features reach held-out AUROC up to 0.94 for failure prediction, and an online monitor ranks failing runs above passing ones from a partial trace, triggering early stopping well before completion. The authors suggest that behavioral topology gets shaped more by the deployment harness than by the LLM underneath it. Paper: https://arxiv.org/abs/2608.23670 Chat with Paper: https://academy.dair.ai/papers/automata-from-agent-traces-2608.23670

Related

• // OCR-Memory // Well this is a unique approach to store memory for long-horizon agents. Most of the agent memory systems compress trajector…
• Very interesting new work from Microsoft. (bookmark it) This work is related to this emerging theme of leveraging harnesses for model post-t…
• Very cool idea to convert memory to skills. (bookmark it) Most agent memory systems retrieve past traces as passive context. MSCE turns them…
• Very interesting new work Amazon and colleagues. (bookmark it) This connects to the emerging theme of treating the corpus as part of the har…
• // Model or Harness // Great paper if you are building with agents in production. (bookmark it) It organizes 41 agent failure modes by the i…

Source: DAIR.AI (X) | 2026-08-27