





















Abstract:AI agents increasingly execute procedural workflows as sequential action traces, which obscures latent concurrency and induces repeated step-by-step reasoning. We introduce BPOP, a Bayesianframework that infers a latent dependency partial order from noisy linearized traces. BPOP models traces as stochastic linear extensions of an underlying graph and performs efficient MCMC inference via a tractable frontier-softmax likelihood that avoids #P-hard marginalization over linear extensions. We evaluate on our open-sourced Cloud-IaC-6, a suite of cloud provisioning tasks with heterogeneous LLM-generated traces, and WFCommons scientific workflows. BPOP recover dependency structure more accurately than trace-only and process-mining baselines, and the inferred graphs support a compiled executor that prunes irrelevant context, yielding substantial reductions in token usage and execution time.
| Subjects: | Applications (stat.AP) |
| Cite as: | arXiv:2602.02806 [stat.AP] |
| (or arXiv:2602.02806v3 [stat.AP] for this version) | |
| https://doi.org/10.48550/arXiv.2602.02806 arXiv-issued DOI via DataCite |
From: Dongqing Li [view email]
[v1]
Mon, 2 Feb 2026 21:03:30 UTC (6,538 KB)
[v2]
Wed, 4 Feb 2026 09:08:53 UTC (6,538 KB)
[v3]
Sun, 24 May 2026 18:12:04 UTC (8,641 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。