AI Paper Atlas

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

Achieving Expert-Level Agent from Foundation Model via Complexity Curriculum Reinforcement Learning with Synthetic Data

Haiteng Zhao, Junhao Shen, Yiming Zhang, Songyang Gao, Kuikun Liu, Tianyou Ma, Fan Zheng, Dahua Lin, Wenwei Zhang, Kai Chen

ICLR 2026 · Multi-agent systems and games › LLM agents · approach: LLM multi-agent collaboration and safety

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 a complexity-curriculum reinforcement learning approach with synthetic data to train LLM agents for olympiad geometry problem solving, aiming to match expert systems like AlphaGeometry 2.

Problem

LLM agents struggle with geometry problem solving because of weak heuristics for auxiliary constructions, so the field relies on expert models such as AlphaGeometry 2 that depend on large-scale data synthesis and search.

Approach

Uses a complexity curriculum within reinforcement learning on synthetic geometry data to train a foundation-model agent to produce auxiliary constructions, instead of relying on large-scale search-based expert systems.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use InternGeometry LLM agent instead of expert modelsAlphaGeometry 2 · IMO 50 pass@256problems solved: 42 -> 44Improved
add proposition proving steps (ablation)InternGeometry · IMO 50 pass@256problems solved: 35 -> 44Improved
add slow thinking (ablation)InternGeometry · IMO 50 pass@256problems solved: 23 -> 35Improved
add context compression (dynamic memory) (ablation)InternGeometry · IMO 50 pass@256problems solved: 20 -> 44Improved
add rejection sampling against repeated actions (ablation)InternGeometry · IMO 50 pass@256problems solved: 38 -> 44Improved
add CBRL after SFT cold start (ablation)InternGeometry · IMO 50 pass@256problems solved: 22 -> 44Improved
use only easy synthetic data in RL (ablation)InternGeometry · IMO 50 pass@256problems solved: 44 -> 29Hurt
use only challenging data in RL (ablation)InternGeometry · IMO 50 pass@256problems solved: 44 -> 24Hurt
add complexity schedule over synthesized data (ablation)InternGeometry · IMO 50 pass@256problems solved: 38 -> 44Improved
lengthen agent trajectory instead of more sampling (ablation)InternGeometry · IMO 50 pass@256pass@KImproved

Experimental setup

Baselines: AlphaGeometry 2

Builds on: AlphaGeometry 2

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