AI Paper Atlas

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

ALGO: Synthesizing Algorithmic Programs with Generated Oracle Verifiers

Kexun Zhang, Danqing Wang, Jingtao Xia, William Yang Wang, Lei Li

NeurIPS 2023 · Large language models › Agents, code and math · approach: Execution-based code verification · 2 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
rerank Codex programs with ALGO verifier instead of CodeTCodex · CodeContests1@k: 2.10 -> 5.60Improved
rerank Codex programs with ALGO verifier vs raw CodexCodex · CodeContests1@k: 0.70 -> 5.60Improved
add ALGO verifier to PG-TD (replace generated tests)PG-TD · CodeContests1@k: 0.67 -> 1.57Improved
add ALGO oracle verifier to ChatGPTChatGPT · CodeContests1@k: 4.40 -> 12.00Improved
increase n toward k (100@k)ALGO w/ Codex · CodeContestsn@k gain over Codex: +4.90 -> +3.60Mixed
replace example tests with ALGO generated tests for ChatGPT coder (ablation)ChatGPT coder · LeetCode1@20: 4.4% -> 12.0%Improved
replace ChatGPT-generated tests with ALGO tests (ablation)ChatGPT coder · LeetCode1@20: 6.8% -> 12.0%Improved
use ChatGPT-generated tests instead of example tests at 7@20 (ablation)ChatGPT coder · LeetCode7@20: 12.2% -> 11.7%No clear effect
use ALGO generated test cases instead of example casesverifier · CodeContestsagreement with judge: 57.39% -> 94.78%Improved
use ALGO generated test cases instead of example casesverifier · LeetCodeagreement with judge: 68.57% -> 74.29%Improved
use ALGO test cases for coverageverifier · CodeContestsstatement coverage: 85.78% -> 89.39%Improved
increase number of generated test cases beyond 30 (ablation)ALGO w/ Codex · CodeContestsn@kNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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