Latent Reasoning Guidance for Parallel Code Translation

[2606.05518] Latent Reasoning Guidance for Parallel Code Translation Skip to main content Search Submit Donate Log in Computer Science > Distributed, Parallel, and Cluster Computing arXiv:2606.05518 (cs) [Submitted on 3 Jun 2026 ( v1 ), last revised 21 Aug 2026 (this version, v2)] Title: Latent Reasoning Guidance for Parallel Code Translation Authors: Tomer Bitan , Erel Kaplan , Roee Bar-Yadin , Lian Ghrayeb , Le Chen , Samyak Jhaveri , Niranjan Hasabnis , Gal Oren View PDF HTML (experimental) Abstract: Tackling complex coding tasks often requires autonomous agents and iterative repair pipelines. These increasingly rely on large amounts of test-time computation, often spending many decoding and repair steps before discovering whether a program compiles, runs, or validates. Executable parallel-code translation is an effective setting for earlier guidance because success is behavioral rather than textual. However, most guidance methods act only after complete programs or textual traces are decoded. This motivates the question: can latent reasoning provide an earlier intervention point, before the model commits to code? We study a test-time latent guidance method for this setting that trains a smaller Process Reward Model (PRM) over continuous latent prefixes and uses it to select among alternate hidden-state trajectories before final code decoding, separately from but compatible with post-decoding optimization. On a 76-task ParaTrans benchmark evaluation, latent PRM guidance improves mean validation rate from 32.89\% with unguided latent reasoning to 42.1\%, outperforming fine-tuned and vanilla baselines in the same setting. These gains persist under the same three-attempt repair loop. These results provide bounded evidence that useful alternative latent continuations exist and that PRM-scored latent branch selection can improve executable outcomes in this setting without retraining the main generative model. Subjects: Distributed, Parallel, and Cluster Computing (cs.DC) Cite as: arXiv:2606.05518 [cs.DC] (or arXiv:2606.05518v2 [cs.DC] for this version) https://doi.org/10.48550/arXiv.2606.05518 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Tomer Bitan [ view email ] [v1] Wed, 3 Jun 2026 23:45:49 UTC (237 KB) [v2] Fri, 21 Aug 2026 19:52:41 UTC (240 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.DC < prev | next > new | recent | 2026-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Bookmark 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? ) 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? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Latent Reasoning Guidance for Parallel Code Translation#665797
• Latent Reasoning Guidance for Parallel Code Translation#259424
• Learning Reasoning World Models for Parallel Code#126598
• Evaluating LLMs Code Reasoning Under Real-World Context#13159
• Correctness, Convergence, and AI-Generated Code Detection: A Longitudinal Study of Student and Large Language Model Code in Introductory Programming#1169629