AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

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

Dongqing li, Zheqiao Cheng, Geoff Nicholls, Quyu Kong

ICML 2026 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Nonparametric and PAC-Bayes Bayesian learning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use BPOP instead of Heuristics Minertrace-only baselines · SRASearchEdge F1: 0.43 -> 0.91Improved
use BPOP instead of Heuristics Minertrace-only baselines · EpigenomicsEdge F1: 0.38 -> 0.79Improved
use BPOP instead of Heuristics Miner on cloud scenariosprocess mining · Cloud-IaC-6 (IP-Cov=1.0)Edge F1: 0.60 -> 0.95Improved
use BPOP instead of Majority / Heuristics Minergraph recovery · EpigenomicsFeasibility: 0.00 -> 0.84Improved
use Inductive Miner instead of BPOPBPOP · Cloud-IaC-6Edge F1 vs feasibility: Feasibility 0.85 -> 1.00; Edge F1 0.95 -> 0.46Mixed
increase trace diversity IP-Cov from 0.8 to 0.9 (ablation)BPOP · Cloud-IaC-6Edge F1: 0.413 -> 0.872Improved
increase trace diversity IP-Cov from 0.8 to 0.9 (ablation)BPOP compiled executor · Cloud-IaC-6Tokens per task: 17,479 -> ~583Improved
increase trace diversity IP-Cov from 0.6 to 0.9 (ablation)BPOP compiled executor · Cloud-IaC-6Fallback rate (%): 50.0 -> 0.0Improved
vary noise epsilon over 0.005 to 0.05 (ablation)BPOP · Cloud-IaC-6 (IP-Cov>=0.9)Edge F1: varies by less than 0.02No clear effect
add LLM fallback to compiled execution (Hybrid vs Expert) (ablation)BPOP executor · Cloud-IaC-6 six scenariosSuccess rate (%): 66.7% -> 100.0%Improved
compiled Expert execution instead of LLM Explore (CoT)agent execution · Cloud-IaC-6 six scenariosTotal LLM tokens: 381,794 -> 3,501Improved
use Bayesian Queue-Jump likelihood instead of frontier-softmaxBPOP · WFCommons SRASearchruntime: predicted runtime exceeding 1,000 hoursHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy