AI Paper Atlas

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

SCI-Verifier: Scientific Verifier with Thinking

Shenghe Zheng, Chenyu Huang, Fangchen Yu, Junchi Yao, Jingqi Ye, Tao Chen, Yun Luo, Ning Ding, LEI BAI, Ganqu Cui, Peng Ye

ICLR 2026 · Large language models › Agents, code and math · approach: Mathematical and structural reasoning benchmarks

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
enable chain-of-thought reasoning before the verdict in verifiers (ablation)verifier models of different scales · VerifierBench and VerifyBench-hardaccuracyImproved
train with reasoning mode instead of no chain-of-thought (ablation)SCI-Verifier · SCI-VerifyBench and two other benchmarksaccuracyImproved
add RL after SFT on the base model (ablation)SCI-Verifier (4B and 8B) · SCI-VerifyBench and generalization benchmarksaccuracyImproved
apply RL directly on the Base model without SFT warm-up (ablation)SCI-Verifier · SCI-VerifyBenchaccuracyHurt
distill complete CoT instead of short CoT in SFT (ablation)SCI-Verifier SFT · SCI-VerifyBenchaccuracy and output lengthHurt
train on the proposed filtered dataset instead of the 180K-sample RM dataset (ablation)Qwen3-4B-Base with SFT and SFT+RL · three verification benchmarksaccuracyImproved
use a larger model sizeverifiers on SCI-VerifyBench · SCI-VerifyBenchaccuracyNo clear effect
use reasoning models instead of chat modelsgeneral LLMs as verifiers · SCI-VerifyBenchaccuracyNo clear effect
change the prompt from the default to the xVerify-style prompt (ablation)SCI-Verifier-8B · SCI-VerifyBenchaccuracy: 86.28 -> 85.50No clear effect
change the prompt from the default to the xVerify-style prompt (ablation)Qwen3-30B-A3B-Instruct-2507 · VerifyBench-Hardaccuracy: 88.70 -> 75.40Hurt
add equivalence-transformed answers and targeted post-trainingSCI-Verifier vs GPT-5 · equivalence-augmented test setaccuracyImproved

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