Skip to content
AI News HubLIVE
Original source2 min read

ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning

Summary

Large language models may abandon correct scientific answers after user criticism. ReCrit frames critic interaction as a correctness-transition problem, introduces a four-quadrant behavior decomposition and dynamic asynchronous rollout, achieving significant accuracy gains on three benchmarks.

SourcearXiv Machine LearningAuthor: Wanghan Xu, Yuhao Zhou, Hengyuan Zhao, Shuo Li, Dianzhi Yu, Zhenfei Yin, Yaowen Hu, Fengli Xu, Wanli Ouyang, Wenlong Zhang, Lei Bai
ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[2605.18799] ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning

[Submitted on 11 May 2026]

Title:ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning

View a PDF of the paper titled ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning, by Wanghan Xu and 10 other authors

View PDF HTML (experimental)

Abstract:Large language models can fail in critic interaction not only by answering incorrectly, but also by abandoning an initially correct scientific solution after user criticism. This is especially risky in scientific reasoning, where user criticism can turn a valid answer into an incorrect one. We frame critic interaction as an inter-turn correctness-transition problem rather than a final-answer accuracy problem, and identify three challenges: transition awareness, decoupling useful correction from harmful sycophancy, and scalable rollout. We propose ReCrit, a transition-aware reinforcement learning framework that decomposes Initial-to-Critic behavior into four quadrants: Correction, Sycophancy, Robustness, and Boundary. ReCrit rewards correction and robustness, penalizes sycophancy, and treats persistent errors as weak boundary signals. To make interaction training practical, ReCrit further uses dynamic asynchronous rollout with tail-adaptive completion to reduce rollout waiting. On three scientific reasoning benchmarks, ChemBench, TRQA, and EarthSE, ReCrit improves average Critic accuracy from 38.15 to 51.49 on Qwen3.5-4B and from 45.40 to 55.59 on Qwen3.5-9B. Ablations show that final-answer rewards provide little interaction-level gain, while transition-aware rewards and quadrant weighting produce more distinguishable training signals and larger net Critic-stage improvement. The code is available at this https URL .

Subjects:

Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)

Cite as: arXiv:2605.18799 [cs.LG]

(or arXiv:2605.18799v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2605.18799

arXiv-issued DOI via DataCite

Submission history

From: Wanghan Xu [view email] [v1] Mon, 11 May 2026 09:22:39 UTC (1,169 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning, by Wanghan Xu and 10 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-05

Change to browse by:

cs cs.AI cs.CL

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Traditional approaches focus on final answer accuracy, ignoring correctness transitions during interaction.
  • ReCrit categorizes initial-to-critic behavior into Correction, Sycophancy, Robustness, and Boundary.
  • Dynamic asynchronous rollout with tail-adaptive completion reduces waiting time.
  • Improves average critic accuracy by 13-15 points on three scientific benchmarks.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Models