AI Paper Atlas

Research map / Large language models / Agents, code and math

ECCO: Evidence-Driven Causal Reasoning for Compiler Optimization

Haolin Pan, Lianghong Huang, Dong Jinyuan, Mingjie Xing, Yanjun Wu

ICML 2026 · Large language models › Agents, code and math · approach: Code generation benchmarks · 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
add chain-of-thought rationale training (vs w/o CoT) (ablation)ECCO-1.5B (w/o GA) · Average of 7 suites, greedy N=1cycle reduction vs -O3 (%): 1.27 -> 4.38Improved
add chain-of-thought rationale training (vs w/o CoT) (ablation)ECCO-1.5B (w/o GA) · Average of 7 suites, Best-of-32cycle reduction vs -O3 (%): 16.25 -> 19.02Improved
add execution evidence to the CoT data (vs w/o Evidence) (ablation)ECCO-1.5B (w/o GA) · Average of 7 suites, greedy N=1cycle reduction vs -O3 (%): 3.52 -> 4.38Improved
add execution evidence to the CoT data (vs w/o Evidence) (ablation)ECCO-1.5B (w/o GA) · Average of 7 suites, Best-of-32cycle reduction vs -O3 (%): 17.55 -> 19.02Improved
scale model from 1.5B to 7B (ablation)ECCO (w/o GA) · Average of 7 suites, Best-of-32cycle reduction vs -O3 (%): 19.02 -> 19.43No clear effect
scale model from 3B to 7B (ablation)ECCO (w/o GA) · Average of 7 suites, greedy N=1cycle reduction vs -O3 (%): 7.03 -> 5.04Hurt
add GA tactician guided by LLM intent to the LLM policy (ablation)ECCO-7B · Average of 7 suites, Best-of-32cycle reduction vs -O3 (%): 19.43 -> 24.44Improved
replace GA with iterative LLM refiner (ablation)ECCO · Average of 7 suitescycle reduction vs -O3 (%): 24.44 -> 19.36Hurt
use ECCO (LLM strategist + GA) instead of CFASTbest traditional baseline · Average of 7 suitescycle reduction vs -O3 (%): 23.70 -> 24.44Improved
use direct LLM prompting instead of TPEDirect LLM prompting Best-of-32 · Average of 7 suitescycle reduction vs -O3 (%): 19.88 -> 16.06Hurt

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