AI Paper Atlas

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

TestExplora: Benchmarking LLMs for Proactive Bug Discovery via Repository-Level Test Generation

Steven Liu, Jane Luo, Xin Zhang, Aofan Liu, Hao Liu, Jie Wu, Ziyang Huang, Yangyu Huang, Yu Kang, Scarlett Li

ICML 2026 · Large language models › Agents, code and math · approach: Software engineering agents · 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 full code and dependencies (White Box instead of Black Box)GPT-5-mini · TestExploraF2P: 5.17 -> 7.54Improved
add dependency code (White Box instead of Black Box)GPT-4o · TestExplora-LiteF2P: 3.61 -> 2.20Hurt
add full dependency code (White Box instead of Black Box)o4-mini · TestExplora-LiteF2P: 3.74 -> 6.45Improved
replace human-written docs with DocAgent-generated docs (ablation)GPT-5-mini · TestExplora-Lite (Black Box)F2P: +6.06Improved
replace human-written docs with DocAgent-generated docs (ablation)LLMs on Black Box · TestExplora-Litenumber of tests: -0.16 to +0.70No clear effect
replace human-written docs with DocAgent-generated docs (ablation)Gemini-2.5-pro · TestExplora-Lite (Black Box)F2P: +0.61Improved
use SWEAgent instead of plain static contextGPT-5-mini · TestExplora (White Box)F2P: 12.79 -> 17.27Improved
use SWEAgent instead of plain static contexto4-mini · TestExplora (White Box)F2P: 5.92 -> 9.42Improved
use TraeAgent instead of plain static contexto4-mini · TestExplora (White Box)F2P: 5.92 -> 12.16Improved
use TraeAgent instead of plain static contextGPT-5-mini · TestExplora (White Box)F2P: 12.79 -> 14.55Improved
increase samples from pass@1 to pass@5SWEAgent GPT-5-mini · TestExplora-LiteF2P: 17.3 -> 29.7Improved
increase samples from pass@1 to pass@5SWEAgent o4-mini · TestExplora-LiteF2P: 9.4 -> 21.2Improved

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