AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

Eigen-1: Scientific Reasoning through Adaptive Multi-Agent Refinement and Monitor-based RAG

Xiangru Tang, Wanghan Xu, Yujie Wang, Zijie Guo, Daniel Shao, Cixuan Zhang, Ziyi Wang, Lixin Zhang, Guancheng Wan, Zhenfei Yin, Wenlong Zhang, LEI BAI and 3 more

ICLR 2026 · Multi-agent systems and games › LLM agents · approach: Self-evolving language agent learning

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes Eigen-1, a framework for scientific reasoning in LLMs that combines implicit retrieval with structured multi-agent refinement to address retrieval-induced token overhead and solution dilution in multi-agent pipelines.

Problem

Scientific reasoning with LLMs suffers from explicit retrieval fragmenting reasoning (a hidden tool tax of extra tokens and steps) and multi-agent pipelines diluting strong solutions by averaging across all candidates.

Approach

Unifies implicit retrieval (monitor-based RAG) with adaptive multi-agent refinement so that strong candidate solutions are not averaged away with weaker ones; the abstract only partially describes the mechanism.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace explicit paper-retrieval RAG with Monitor-based implicit RAG (ablation)Eigen-Agent baseline · HLE Bio/Chem Goldtokens (K): 470.6 -> 218.4Improved
replace explicit paper-retrieval RAG with Monitor-based implicit RAG (ablation)Eigen-Agent baseline · HLE Bio/Chem Goldaccuracy (%): 41.4 -> 34.5Hurt
add explicit paper retrieval to the no-RAG baseline (ablation)Eigen-Agent baseline · HLE Bio/Chem Goldaccuracy (%): 25.3 -> 41.4Improved
add explicit paper retrieval to the no-RAG baseline (ablation)Eigen-Agent baseline · HLE Bio/Chem Goldagent steps: 43.4 -> 94.8Hurt
add Querier to Monitor-based RAG (ablation)Monitor-based RAG · HLE Bio/Chem Goldaccuracy (%): 34.5 -> 36.8Improved
add Injector to Monitor + Querier (ablation)Monitor-based RAG · HLE Bio/Chem Goldaccuracy (%): 36.8 -> 40.3Improved
add Hierarchical Solution Refinement (HSR) (ablation)Monitor + Querier + Injector · HLE Bio/Chem Goldaccuracy (%): 40.3 -> 43.7Improved
add Quality-Aware Iterative Reasoning (QAIR) (ablation)Monitor + Querier + Injector + HSR · HLE Bio/Chem Goldaccuracy (%): 43.7 -> 48.3Improved
add Monitor, Querier and Injector to the full pipeline (vs removing them) (ablation)Eigen-Agent · HLE Bio/Chem Goldaccuracy (%): 48.5 -> 48.3No clear effect
add Monitor, Querier and Injector to the full pipeline (vs removing them) (ablation)Eigen-Agent · HLE Bio/Chem Goldtokens (K): 461.3 -> 218.9Improved
Eigen-Agent Pass@1 versus the strongest agent baseline on HLESciMaster (DeepSeek V3.1) · HLE Bio/Chem Goldaccuracy (%): 34.92 -> 48.30Improved
use Eigen-Agent instead of SciMaster on SuperGPQA hard biologyDeepSeek V3.1 · SuperGPQA Biology (hard)accuracy (%): 66.30 -> 69.57Improved

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