De-Linearizing Agent Traces: Bayesian Inference of Latent Partial Orders for Efficient Execution
Year: 2026
Type: preprint
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.
Source: arXiv (Cornell University)
Institutions: University of Oxford, Zhejiang University
Subfield: Management Information Systems
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W7127713807
Cites:
Cited by:
Related to: