AI Paper Atlas

Research map / Large language models / AI and society

AgentExpt: Automating AI Experiment Design with LLM-based Resource Retrieval Agent

Yu Li, Lehui Li, Lin Chen, Qingmin Liao, Fengli Xu, Yong Li

ICML 2026 · Large language models › AI and society · approach: Social-science view of AI evaluation · 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 collective perception (citation-context summary) to the retriever representation (ablation)AgentExpt retriever · Paper-Baseline recommendationRecall@20: 0.3716 -> 0.4523Improved
add collective perception (citation-context summary) to the retriever representation (ablation)AgentExpt retriever · Paper-Dataset recommendationRecall@20: 0.2493 -> 0.3001Improved
add first-person self-description to the retriever representation (ablation)AgentExpt retriever · Paper-Baseline recommendationRecall@20: 0.4197 -> 0.4523Improved
add first-person self-description to the retriever representation (ablation)AgentExpt retriever · Paper-Dataset recommendationRecall@20: 0.2709 -> 0.3001Improved
add reasoning supervision to the reranker (ablation)AgentExpt reranker · Paper-Baseline recommendationHitRate@5: 0.4284 -> 0.5933Improved
add reasoning supervision to the reranker (ablation)AgentExpt reranker · Paper-Dataset recommendationHitRate@5: 0.3641 -> 0.4557Improved
add interaction chains as evidence to the reranker (ablation)AgentExpt reranker · Paper-Baseline recommendationHitRate@5: 0.5245 -> 0.5933Improved
add interaction chains as evidence to the reranker (ablation)AgentExpt reranker · Paper-Dataset recommendationHitRate@5: 0.4126 -> 0.4557Improved
add the reasoning-augmented reranker after the retriever (ablation)AgentExpt pipeline · Paper-Baseline recommendationHitRate@10: 0.6757 -> 0.6938Improved
add the reasoning-augmented reranker after the retriever (ablation)AgentExpt pipeline · Paper-Dataset recommendationHitRate@10: 0.5308 -> 0.5549Improved
fine-tune the reranker on interaction chains instead of off-the-shelf GPT-4o (ablation)AgentExpt reranker · Paper-Baseline recommendationHitRate@10: 0.6501 -> 0.6938Improved
fine-tune the reranker on interaction chains instead of off-the-shelf GPT-4o (ablation)AgentExpt reranker · Paper-Dataset recommendationHitRate@10: 0.5213 -> 0.5549Improved

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