DAIR.AI发现智能体行为更多受部署框架影响而非底层模型，能提前预测任务失败。
DAIR.AI团队发布新论文，将智能体轨迹压缩为有限状态机。研究显示，12个公共数据集上状态机仅需7-43个状态，回放数据拟合度达0.997。有限状态机上下文在12个数据集上均优于Agent Workflow Memory，失败预测AUROC最高达0.94。
Another good paper. Interesting finding on the benefits of the agent harness.
Another good paper. Interesting finding on the benefits of the agent harness. DAIR.AI @dair_ai // 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: arxiv.org/abs/2608.23670 Chat with Paper: academy.dair.ai/papers/automat… 🔗 View Quoted Tweet 💬 0 🔄 0 ❤️ 0 👀 478 ⚡