De-Linearizing Agent Traces: Bayesian Inference of Latent Partial Orders for Efficient Execution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Dongqing, Cheng, Zheqiao, Nicholls, Geoff K., Kong, Quyu
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916044192350208
author Li, Dongqing
Cheng, Zheqiao
Nicholls, Geoff K.
Kong, Quyu
author_facet Li, Dongqing
Cheng, Zheqiao
Nicholls, Geoff K.
Kong, Quyu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_02806
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle De-Linearizing Agent Traces: Bayesian Inference of Latent Partial Orders for Efficient Execution
Li, Dongqing
Cheng, Zheqiao
Nicholls, Geoff K.
Kong, Quyu
Applications
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.
title De-Linearizing Agent Traces: Bayesian Inference of Latent Partial Orders for Efficient Execution
topic Applications
url https://arxiv.org/abs/2602.02806