AI Paper Atlas

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

SR-Scientist: Scientific Equation Discovery With Agentic AI

Shijie Xia, Yuhan Sun, Pengfei Liu

ICLR 2026 · Large language models › Agents, code and math · approach: Agent instruction-following benchmarks · 30 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
Replace LLM-SR pipeline with SR-Scientist agent (GPT-OSS-120B)GPT-OSS-120B · LSR-Synth (overall)Acc_0.01: 28.16 -> 63.57Improved
Replace LLM-SR pipeline with SR-Scientist agent (Qwen3-Coder-480B)Qwen3-Coder-480B-A35B · LSR-Synth (overall)Acc_0.01: 41.08 -> 49.09Improved
Replace LLM-SR pipeline with SR-Scientist agent (GPT-OSS-20B)GPT-OSS-20B · LSR-Synth (overall)Acc_0.01: 33.33 -> 42.64Improved
Replace LLM-SR pipeline with SR-Scientist agent (Qwen3-Coder-30B, no RL)Qwen3-Coder-30B-A3B · LSR-Synth (overall)Acc_0.01: 24.55 -> 32.30Improved
Add RL training to SR-ScientistQwen3-Coder-30B-A3B · LSR-Synth (overall)Acc_0.01: 32.30 -> 40.92Improved
Add RL training to SR-ScientistQwen3-32B · LSR-Synth (overall, Qwen3-32B)Acc_0.01: 29.46 -> 39.53Improved
Add RL training to SR-ScientistQwen3-14B · LSR-Synth (overall, Qwen3-14B)Acc_0.01: 18.60 -> 23.26Improved
Add RL training to SR-ScientistQwen3-8B · LSR-Synth (overall, Qwen3-8B)Acc_0.01: 15.50 -> 20.93Improved
Use log-linear reward instead of stepwise reward in RL (ablation)SR-Scientist + RL · LSR-Synth (overall)Acc_0.01: 37.21 -> 40.92Improved
Add data analyzer tool (data analysis) (ablation)SR-Scientist · LSR-Synth (overall)Acc_0.01Improved
Add experience buffer of best equations (ablation)SR-Scientist · LSR-Synth (overall)Acc_0.01Improved
Increase maximum turns per iteration from 10 to 25 (ablation)SR-Scientist · LSR-Synth (overall)Acc_0.01Improved

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