코딩 AI의 잠재적 미래 예측 능력 입증

--> Computer Science > Machine Learning arXiv:2607.05188 (cs) [Submitted on 6 Jul 2026] Title: Latent Programming Horizons in Coding Agents Authors: André Silva , Han Tu , Martin Monperrus View a PDF of the paper titled Latent Programming Horizons in Coding Agents, by Andr\'e Silva and 2 other authors View PDF HTML (experimental) Abstract: A coding agent solving a software-engineering task spends dozens of steps reasoning, editing code, and running tests, yet little is known about what the underlying language model internally represents about the program it is working on. We show that the residual streams of language models under coding agents linearly encode properties of the evolving program: a logistic-regression probe on hidden states is able to decode whether the current code parses, passes its test suite, reduces the number of failing tests, and introduces regressions, reaching AUC up to 0.83 for correctness across two models and two benchmarks. Our second finding is more surprising: these representations run ahead of the agent's own edits. Probes trained to predict the outcome of future edits (before they are materialized and written on disk) achieve performance above chance up to roughly 25 steps in advance. We call this the agent's latent programming horizon. As a proof of external validity, we show that the probes transfer across benchmarks without retraining. Our positive results open calls for more research in mechanistic interpretability of coding agents. Subjects: Machine Learning (cs.LG) ; Software Engineering (cs.SE) Cite as: arXiv:2607.05188 [cs.LG] (or arXiv:2607.05188v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2607.05188 Focus to learn more arXiv-issued DOI via DataCite Submission history From: André Silva [ view email ] [v1] Mon, 6 Jul 2026 15:08:26 UTC (653 KB) Full-text links: Access Paper: View a PDF of the paper titled Latent Programming Horizons in Coding Agents, by Andr\'e Silva and 2 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2026-07 Change to browse by: cs cs.SE References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation &times; loading... Data provided by: 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? ) 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? )