Paper

ImProver 2: Iteratively Self-Improving LMs for Neurosymbolic Proof Optimization

Unreadunread

AI summary

arXiv:2605. 22885v1 Announce Type: new 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.

Reading status

Priority

About this paper

Authors: Riyaz Ahuja, Tate Rowney, Jeremy Avigad, Sean Welleck
Released: 2026-05-25 (2mo ago)
Topic: Related to current project
Relation to my work: Read next because ImProver 2: Iteratively Self-Improving LMs for Neurosymbolic Proof Optimization overlaps with clean result "The marker is a representational handle, not a behavioural one — sharing it between a villain persona and the assistant transfers no misalignment (HIGH confidence)", experiment "Factor screen for marker implantation + leakage (2^5: system-prompt length, answer-format length, persona-presence, on-policy, marker-only-loss)", experiment "#351 follow-up: broader-vocab position-0 sweep at T=1.0 + position-1 suffix isolation". Matching terms: line, rate, factor, model. Source: arxiv cs.AI (Artificial Intelligence).
arXiv: 2605.22885

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to ImProver 2: Iteratively Self-Improving LMs for Neurosymbolic Proof Optimization. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.