AI Paper Atlas

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

Discovering Novel LLM Experts via Task-Capability Coevolution

Andrew Dai, Boris Meinardus, Ciaran Regan, Yingtao Tian, Yujin Tang

ICLR 2026 · Large language models › Agents, code and math · approach: Agent instruction-following 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
Use AC/DC task force instead of hand-picked experts3 expert models · Benchmark Coverage, N=3coverage: +3.99 pp avgImproved
Use AC/DC N=8 task force instead of single larger modelBig Model · Benchmark Coverage, N=8coverage: +10.19 pp avgImproved
AC/DC N=3 vs GPT-4oGPT-4o · Benchmark Coverage, N=3coverage: -4.52 pp avgMixed
AC/DC N=8 vs GPT-4oGPT-4o · Benchmark Coverage, N=8coverage: +2.99 pp avgImproved
AC/DC task force vs sampling instruct model repeatedly (control)Control · Benchmark Coverage, N=3 and N=8coverage: +2.45 / +2.04 pp avg (Qwen2 -0.45, -1.04)Mixed
Select with Best-of-N instead of Coverage: AC/DC vs experts3 expert models · Benchmark Best-of-N, N=3accuracy: +1.34 pp avg (Qwen -1.31, -1.26, -0.49; DeepSeek +11.73)Mixed
AC/DC Best-of-N vs big modelBig Model · Benchmark Best-of-Naccuracy: -3.89 pp (N=3), -0.25 pp (N=8)Hurt
AC/DC Best-of-N vs GPT-4oGPT-4o · Benchmark Best-of-Naccuracy: -10.82 pp (N=3), -7.17 pp (N=8)Hurt
Add QD (DNS) selection (ablation)AC/DC · Coverage ablationcoverage: +2.39 pp (N=3), +0.88 pp (N=8)Improved
Add gibberish filter (ablation)AC/DC · Coverage ablationcoverage: +2.46 pp (N=3), +1.18 pp (N=8)Improved
Add mutation or novelty filtering (ablation)AC/DC · Coverage ablationcoverage: +0.50-1.16 pp (N=3), +0.37-1.19 pp (N=8)Improved
Add task coevolution vs static synthetic dataset (ablation)AC/DC · Coverage N=8coverage: +3.62 ppImproved

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