The paper proposes a human‑in‑the‑loop framework for verifying AI‑generated research results, particularly in mathematics and statistics. It outlines a system where AI agents perform checks using specialized software, a fidelity audit ensures each check addresses the claim, and humans intervene at fixed points to decide on outcomes. The framework also records contributions and attributes work to both human and AI, and the authors demonstrate two automatic implementations for mathematics and statistics, including a case study where an ambiguous claim was split into two readings, one refuted and one proved.
By Gy\"orgy Eigner, Patrik P. S\"uli, Roland Holl\'os
CausalSmith is a framework that automates theoretical research in causal inference by integrating a Lean proof assistant with a self‑improving agentic pipeline. It uses Causalean, a Lean library of over 7,000 machine‑checked declarations, and a pipeline that selects topics, proposes results, formalizes statements, constructs proofs, and audits them against informal claims. The system’s artifacts and source code are publicly available on GitHub.
By Jiyuan Tan, Vasilis Syrgkanis
arXiv:2607. 22511v1 Announce Type: cross Abstract: Automating theoretical research is constrained not only by the generation of candidate results, but also by their reliable evaluation.
By Jiyuan Tan, Vasilis Syrgkanis
arXiv:2608. 05179v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly used across the scientific research lifecycle: ideation, literature search, experiment design and execution, analysis, manuscript drafting, and review.
By Tianyu Ding, Aditya Nannapaneni, Bingfan Liu, Ling Zhang
FORALL-LEAN-AGENT is a frontend‑agnostic framework that enhances auditable reasoning in formal mathematics and software verification. It integrates isolated workspaces, Lean tools, and fresh review processes—including statement comparison, axiom audits, and independent proof checking—to bind verification evidence and reviewer decisions to the same candidate artifact, ensuring traceable acceptance. Evaluations on VeriSoftBench, PutnamBench, and the Lean Eval track show that the framework improves benchmark success rates and reduces costs while providing evidence beyond aggregate solve counts.
By Naing Oo Lwin
The paper introduces CoSLR, a Human‑AI collaborative system for systematic literature reviews that incorporates mandatory human checkpoints within a three‑phase pipeline using large language models and Retrieval‑Augmented Generation. In a survey of 63 participants, 42.9 % rated the system’s usability highly, yet 34.9 % indicated they would trust AI‑generated summaries without further human verification after brief interaction. The study highlights that effective human oversight in AI‑assisted literature reviews depends on users’ willingness to engage with the checkpoints, underscoring a calibration issue that interface design must directly address.
By MD Aidul Islam, Malik Abdul Sami, Muhammad Waseem, Zeeshan Rasheed, Kai-kristian Kemell, Zheying Zhang, Pekka Abrahamsson
arXiv:2607. 26064v1 Announce Type: cross Abstract: AI systems are becoming autonomous research agents that generate hypotheses, design experiments, and produce discoveries at scales beyond human oversight.
By Belinda Mo
arXiv:2603. 02668v2 Announce Type: replace Abstract: We present SorryDB, a dynamically-updating benchmark of open Lean tasks drawn from 78 real world formalization projects on GitHub.
By Austin Letson, Leopoldo Sarra, Auguste Poiroux, Oliver Dressler, Paul Lezeau, Dhyan Aranha, Frederick Pu, Aaron Hill, Miguel Corredera Hidalgo, Julian Berman, George Tsoukalas, Lenny Taelman
Artificial intelligence (AI) systems have ushered in a new age of proof abundance, but helping humans understand these proofs requires new attention to the differences in how AI agents and humans purs...
The paper investigates how autonomous AI agents differ from humans in proof formalization tasks. Using a method called "simulated collaboration," the authors analyze nine major Lean collaborations involving 4.7 million definitions. They find that AI agents focus more on explicitly marked gaps, avoid densely connected proof centers and complex or surprising goals, yet are attracted to surprising proof bodies, which they tend to regularize toward a baseline.
By B\'alint Gyevn\'ar, Simon DeDeo
As autonomous AI agents take on every stage of scientific inquiry, research output is expanding far beyond human review capacity. Yet scientific communication still relies on natural-language prose: a...
arXiv:2606. 05400v1 Announce Type: cross Abstract: Long-horizon autoformalization of research mathematics fails not only at hard lemmas, but at scale: statements drift, dependencies tangle, context decays, and local repairs corrupt distant work.
By Yuanhe Zhang, Yuekai Sun, Taiji Suzuki, Jason D. Lee, Fanghui Liu