The paper argues that AI can cheaply produce plausible scientific artifacts, leading to epistemic pollution because the existing scientific infrastructure relies on high generation costs as a filter. It proposes rebalancing generation and verification costs by introducing structured "blueprints"—typed graph components that decompose claims, evidence, assumptions, and definitions—so that verification becomes cheaper, more local, and distributed. The blueprint complements traditional papers, serving as a verification interface while the paper remains the narrative interface, and a prototype demonstrates the concept.
By Jiaqi W. Ma
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:2607. 12650v1 Announce Type: cross Abstract: Tool access alone does not make LLM empirical reasoning governable: accepted outputs need not descend from attested evidence, and accepted deductions need not hold up under formal scrutiny.
By Junyu Ren
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
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
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:2610.14381v1 Announce Type: new
Abstract: Large language models are increasingly used as scientific assistants, yet we still lack reliable ways to evaluate whether they can investigate a system...
By Yiwei Chen, Amila Weerasinghe, Siddharth Biswal, Utkrisht Rajkumar, Olcay Boz, Taylor Berg-Kirkpatrick, Rose Yu
The paper argues that as AI systems increasingly generate code, the bottleneck has shifted to supervising these systems, revealing a vocabulary gap between cybernetic coordination (actions aligning with the world) and epistemic coordination (understanding that can be verified). It critiques current oversight that merely approves outputs, proposing instead that every consequential choice by an agent must include a retrievable condition explaining why it was made, enabling third‑party verification. The authors illustrate this with three delegation episodes, introduce a two‑part reconstruction test, and propose the ORRCF convention to embed such conditions in all recorded decisions.
By J\'er\'emie Lumbroso
arXiv:2610.40906v1 Announce Type: new
Abstract: Recent scientific agents build knowledge recursively by retrieving evidence, constructing an intermediate state, and judging whether that state contain...
By Lun Ai, Yu-Heng Wu, Jonathan Schaul, Leonie K\"uchenhoff, Denes Turei, Francesco Carli, Fabio Petroni, Aurelien Dugourd, Julio Saez-Rodriguez
The paper proposes a human‑in‑the‑loop framework for verifying AI‑generated research results, addressing the growing volume of AI‑produced mathematics manuscripts. It outlines a system where AI agents perform checks using specialised software, but a human researcher remains involved to audit fidelity, decide at fixed points, and attribute contributions. The authors present two automatic implementations—one for mathematics (using Wolfram Language, MATLAB, Lean) and one for statistics (Python and R)—and demonstrate the mathematical tool on a two‑claim example that required splitting an ambiguous claim into a refuted and a proved reading.
arXiv:2610.17358v1 Announce Type: cross
Abstract: Formal verification proves that a program satisfies its specification, but says nothing about whether the specification captures what the author mean...
By Martin Amster, One An, Holly Baker, Fernanda Graciolli, Simon Henniger, Nada Amin