ImProver 2: Iteratively Self-Improving LMs for Neurosymbolic Proof Optimization
ImProver 2 is a neurosymbolic framework designed for automated proof optimization in formal mathematics. It addresses challenges such as heterogeneous objectives and high training costs by utilizing a data-efficient expert-iteration pipeline. The framework has shown that smaller models can effectively restructure complex proofs, achieving competitive performance with larger systems.
- ▪ImProver 2 combines a data-efficient expert-iteration pipeline with a scaffold that exposes formal structure alongside informal abstractions.
- ▪The framework trains a 7B-parameter model that outperforms larger models within the same family and competes with mid-tier frontier models.
- ▪ImProver 2 demonstrates that small models can restructure research-level proofs effectively, establishing proof optimization as a scalable task.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2605.22885 |
| Publication time | Mon, 25 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-25T04:07:35.648Z |
| Last seen | 2026-05-25T04:07:35.648Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | jFmJXHl9bq-D |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2605.22885 (cs) [Submitted on 21 May 2026] Title:ImProver 2: Iteratively Self-Improving LMs for Neurosymbolic Proof Optimization Authors:Riyaz Ahuja, Tate Rowney, Jeremy Avigad, Sean Welleck View a PDF of the paper titled ImProver 2: Iteratively Self-Improving LMs for Neurosymbolic Proof Optimization, by Riyaz Ahuja and 3 other authors View PDF HTML (experimental) Abstract:Formal mathematics libraries are rapidly expanding, creating a growing need to refactor verified proofs for maintainability and to improve training data quality for neural provers. However, scalable proof optimization is hindered by heterogeneous and heuristically specified objectives, scarce data, and high training and inference costs.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
