arXiv Machine Learning July 28, 2026 By Evan Wang, Simon Chess, Sophie Szeto, Theodore Meek

Learned Interventions in Lean 4 grind

Read the original on arXiv Machine Learning →

arXiv:2607. 22972v1 Announce Type: new Abstract: Lean~4's \grind{} tactic combines congruence closure, \ematch{}ing, and case-splitting into a single automated solver, and like any such solver, it relies on hand-tuned heuristics to decide what to instantiate and where to case-split.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 12

Pythagoras-Prover: Advancing Efficient Formal Proving via Augmented Lean Formalisation

arXiv:2606. 12594v1 Announce Type: new Abstract: Modern Lean theorem provers achieve strong performance only with substantial training and inference compute, driven in part by scarce verified proof data and the long reasoning traces of formal proof search, making both supervised fine-tuning (SFT) and sampling expensive.

By Joshua Ong Jun Leang, Zheng Zhao, Mihaela C\u{a}t\u{a}lina Stoian, Qiyuan Xu, Haonan Li, Wenda Li, Shay B. Cohen, Eleonora Giunchiglia

diffusion fine-tuning efficiency benchmarks

arXiv AI

Jul 1

When Does Learning to Stop Help? A Cost-Aware Study of Early Exits in Reasoning Models

arXiv:2606. 30852v1 Announce Type: new Abstract: Reasoning models spend different amounts of useful computation across instances, but it remains unclear when a learned stopping rule improves over simple confidence or convergence thresholds.

By Zhe Dong (University of Maine at Presque Isle), Fang Qin (Stanford University), Manish Shah (Independent Researcher)

llms benchmarks

arXiv AI

Jul 21

Self-Modifying Lean Proof Agents with Verifier-Grounded Benchmark Coevolution

arXiv:2607. 17352v1 Announce Type: new Abstract: Designing effective Lean proof agents is a central challenge in formal mathematical reasoning.

By Yuqing Li, Zeguan Wu, Yu Gan, Junyu Liu

agents benchmarks

arXiv AI

Jun 19

Think Again or Think Longer? Selective Verification for Budget-Aware Reasoning

arXiv:2606. 19808v1 Announce Type: new Abstract: Test-time reasoning is increasingly used as a serving-time control knob, but extra reasoning is not uniformly valuable: it can repair failed attempts, waste compute on already-correct answers, or introduce harmful answer changes.

By Sajib Acharjee Dip, Dawei Zhou, Liqing Zhang

arXiv AI

1d ago

Admission Without Answers: Label-Free Certification and Experience Learning for LLM-Based Optimization Modeling

arXiv:2608. 15565v1 Announce Type: new Abstract: Experience-learning agents for optimization modeling improve by storing verified skills, but existing learners admit knowledge by checking against known answers, which real ticket streams do not provide.

By Junbo Jacob Lian, Huiling Chen, Hanzhang Qin, Chung-Piaw Teo

llms agents benchmarks

arXiv AI

Aug 10

The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflows

arXiv:2608. 06714v1 Announce Type: new Abstract: Recent systems for optimizing prompts, programs, and ML workflows typically rely on explicit outer-loop controllers such as evolutionary search, bandits, or textual-gradient methods.

By Junbo Li, Boyi Liu, Canwen Xu, Yite Wang, Yuxiong He, Zhangyang Wang, Qiang Liu, Zhewei Yao

agents

Related stories

Pythagoras-Prover: Advancing Efficient Formal Proving via Augmented Lean Formalisation

When Does Learning to Stop Help? A Cost-Aware Study of Early Exits in Reasoning Models

Self-Modifying Lean Proof Agents with Verifier-Grounded Benchmark Coevolution

Think Again or Think Longer? Selective Verification for Budget-Aware Reasoning

Admission Without Answers: Label-Free Certification and Experience Learning for LLM-Based Optimization Modeling

The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflows