From Errors to Proofs: Minimal-Core-Guided Repair for Neuro-Symbolic Constraint Solving

[2608.14771] From Errors to Proofs: Minimal-Core-Guided Repair for Neuro-Symbolic Constraint Solving Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Artificial Intelligence arXiv:2608.14771 (cs) [Submitted on 14 Aug 2026] Title: From Errors to Proofs: Minimal-Core-Guided Repair for Neuro-Symbolic Constraint Solving Authors: Dipankar Sarkar View a PDF of the paper titled From Errors to Proofs: Minimal-Core-Guided Repair for Neuro-Symbolic Constraint Solving, by Dipankar Sarkar View PDF HTML (experimental) Abstract: Making language models solve constraint problems reliably often means having them translate the problem into a formal specification and delegating the search to a sound solver. But the translation is itself a language-model task, and an unfaithful translation makes the solver faithfully solve the wrong problem. Existing pipelines repair only translations that crash, returning the solver's error message and falling silent when the program runs but is wrong. We replace the error message with a proof: when the generated program is unsatisfiable, we extract a minimal unsatisfiable core over the model's own constraints and hand it back the exact set that cannot hold together, a leakage-free signal that localizes the fault. On a new benchmark of 77 problems with an exact oracle, translation to Answer Set Programming is faithful on six of seven domains and fails only on aggregate coverage scheduling, which concentrates the translation tax in one diagnosable pattern. A minimal core, rather than a bare error, is what stops a weaker model from fabricating solutions to infeasible problems, cutting fabrication from 79% to 7%. A strong chain-of-thought baseline meanwhile matches the symbolic route on accuracy, so the route's value is not accuracy but certificates and its refusal to fabricate. Comments: 7 pages, 2 figures. Accepted at the IJCAI-ECAI 2026 Workshop on Logic and Symbolic Reasoning (LogiSymb), poster Subjects: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Machine Learning (cs.LG); Logic in Computer Science (cs.LO); Programming Languages (cs.PL); Symbolic Computation (cs.SC); Optimization and Control (math.OC) Cite as: arXiv:2608.14771 [cs.AI] (or arXiv:2608.14771v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2608.14771 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Dipankar Sarkar [ view email ] [v1] Fri, 14 Aug 2026 14:48:36 UTC (37 KB) Full-text links: Access Paper: View a PDF of the paper titled From Errors to Proofs: Minimal-Core-Guided Repair for Neuro-Symbolic Constraint Solving, by Dipankar Sarkar View PDF HTML (experimental) TeX Source view license Current browse context: cs.AI < prev | next > new | recent | 2026-08 Change to browse by: cs cs.CL cs.LG cs.LO cs.PL cs.SC math math.OC References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × 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? ) 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

• Solving Large-Scale Multiobjective Optimization Problems With Sparse Optimal Solutions via Unsupervised Neural Networks#19736
• Neurodesign-plus: design optimization for constrained event-level fMRI paradigms#421762
• Automatic single-isocenter multiple-target cranial stereotactic treatment plan optimization via planning system scripting.#1167200
• Neurobiology of Mathematics (Cap 6) - ko#184050
• Neurobiology of Mathematics (Cap 6) - ko#184040