cs.AISep 29, 2026

Can an AI Agent Rediscover a Blaschke-Curve Invariant?

Authors: Yunus E. Zeytuncu

Organizations: University of Michigan-Dearborn

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

We study generalized Blaschke curves as a controlled environment for AI-assisted mathematical rediscovery. For one fixed degree-four Blaschke product, an agent receives numerical coordinates of the six pair-lines determined by each of 80 boundary configurations. The target theorem is withheld from the task instructions. The saved research log reports rejected geometric hypotheses and a homogeneous cubic fitted to polygon sides. Its frozen coefficients predict 480 lines from 80 unseen parameter values, with a recorded RMS scale-free residual of 8.88×10−178.88\times10^{-17}. Discovery-set diagonals provide an out-of-fit consistency check, not a fully held-out test. A separate one-configuration run reports insufficient evidence for invariance. A post-review deterministic degree-search baseline also recovers the cubic, so the experiment does not establish an advantage over polynomial fitting. We present this single-instance case study as a protocol for separating conjecture, numerical validation, and proof, with explicit limitations concerning agent metadata, prior knowledge, and reproducibility.

Figures & tables

Figure 1: The 480 stored discovery lines from exactly 80 values of λ\lambda . Blue lines are sides and red lines are diagonals; black points are the zeros of BB . This post-review visualization uses the experimental discovery CSV, not an additional sampling grid. No envelope figure was supplied in the original discovery task.
ProcedureEvaluation RMSEvaluation maximum
Frozen agent cubic (archived report)8.88×10−178.88\times 10^{-17}3.18×10−163.18\times 10^{-16}
Deterministic degree search (new control)1.24×10−151.24\times 10^{-15}3.18×10−153.18\times 10^{-15}
Table 1: Original agent outcome and post-review deterministic comparison. Both polynomials use coefficient −1-1 for w3w^{3} and residual ( 3 ). Roundoff-level differences are not evidence of superior discovery performance.
Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

RunPhaseElapsed secondsOutput tokens
Full dataDiscovery143.16,219
Full dataEvaluation43.32,129
Sparse dataDiscovery122.75,209
Sparse dataEvaluation100.84,815
Appendix
Table 2: Recovered original-run accounting. Elapsed times span recorded task start to completion. Output-token counts are the harness-reported field, not a prespecified budget or a cost estimate.
DegreeNumber of monomialsNumerical nullityσmin⁡/σmax⁡\sigma_{\min}/\sigma_{\max}
1309.46×10−19.46\times 10^{-1}
2608.71×10−38.71\times 10^{-3}
31012.75×10−162.75\times 10^{-16}
41531.37×10−161.37\times 10^{-16}
52168.17×10−178.17\times 10^{-17}
Appendix
Table 3: Numerical degree search on the 320 discovery side rows.
ConfigurationsUnique side rowsCubic nullityEvaluation RMS
146Not uniquely identified
282Not uniquely identified
52012.00×10−152.00\times 10^{-15}
104012.22×10−152.22\times 10^{-15}
208012.00×10−152.00\times 10^{-15}
4016017.78×10−167.78\times 10^{-16}
Appendix
Table 4: Post-review deterministic controls, not additional agent ablations. Residuals here use unit Euclidean coefficient norm, unlike Table 1 .

Explore similar work

CardsList
Aug 24, 2026cs.AI

Autonomous Mathematical Discovery in an Open-World Multi-Agent Environment

We study autonomous mathematical discovery in the Station, an open-world multi-agent environment in which AI agents from different model families pursue a shared research goal without a central coordinator or scripted pipeline. Agents choose their own research directions, conduct experiments, collaborate and publish papers. These papers accumulate into a shared body of knowledge that later agents can read, cite and extend. We evaluated the Station on 12 mathematical construction problems from the AlphaEvolve study and two additional case studies. Five of the 12 problems yielded results novel relative to the prior literature: a new infinite family of finite field Kakeya sets, new exact 604-point kissing configurations in eleven dimensions, improved bounds for the discretized Kakeya needle and sign uncertainty problems, and a substantially improved lower bound for Erdős's minimum overlap problem. Agents also discovered novel infinite families for Book Ramsey numbers. Their research extended beyond searching for high-scoring constructions: agents developed explanations of their findings and proved theorems outside the assigned tasks. These explanations guided further discoveries and were preserved in the agents' papers, making the underlying insights easier for external researchers to understand and build upon. All presented discoveries are supported by exact constructions or proofs formally verified in Lean. We release the source code, full agent dialogues, papers and verification code, providing a transparent record of how these discoveries emerged.

Stephen Chung, Wenyu Du, William J. Wesley

DualverseAI · University of Cambridge · University of Hong Kong +1

Multi-Agent PlanningOpen-WorldAlphaevolveEnvironment
AskPDF
Aug 11, 2026cs.AI

Long-Horizon AI Research for Grothendieck Constant: A Case Study in Human-AI Mathematical Collaboration

AI agents are increasingly used in mathematics research, but it is often unclear how to use them effectively. Towards this, we present an extensive case study of how AI was used to improve bounds on the Grothendieck constant KGK_G, which captures the hardness between combinatorial problems and their continuous relaxations. Specifically, while the precise value of KGK_G is not known, we recently tightened the best known bounds to 6π11  ≤  KG  ≤  π2log⁡(1+2)−10−4.\frac{6π}{11} \;\le\; K_G \;\le\; \fracπ{2\log(1+\sqrt2)} - 10^{-4}. Crucially, these improvements were achieved using an AI research system that could arrive at insights deemed novel by domain experts. We give a detailed discussion of our experience using AI for mathematics research, particularly touching upon its strengths and weaknesses, as well as our experience with creating ideal conditions for AI to arrive at breakthrough insights.

Alan Li, Rahul Saha, Anton Xue +4

Artificial Intelligence ResearchHilbert SeriesCombinationsCase StudyHardLong-Horizon Agents
AskPDF
Sep 30, 2026hep-th

How AI Agents Discover Scientific Equations: From Hydrotope Rediscovery to New Water-Wave Amplitudes

We study how AI agents discover and validate scientific formulas using a controlled case study of the hydrotope, a recently discovered geometric formula that combines the different polynomial pieces of nonlinear surface-wave scattering into one global expression. This problem is deceptively difficult: simple formulas can hold within individual frequency regions, but the global result must identify their boundaries and combine exponentially many potentially active terms. We reconstruct how the formula was originally discovered through human--agent collaboration and analyze 18 single-prompt rediscovery runs under no hint and two forms of human guidance: a false hint representing an incorrect prior and a true hint representing domain-informed insight. Only four recover the formula across all kinematic chambers (i.e., regions in which a single polynomial form applies), while most unsuccessful runs find correct chamber polynomials but fail to combine them or test their full domain. Conventional and LLM-assisted symbolic regression and standard machine-learning regressors likewise fail to recover the global formula in our experiments. Guided by these failure modes, we test a PI++two-student workflow in which a coordinating lead agent assigns complementary analytic and numerical tasks to two research agents and independently evaluates their results. The PI++two-student team successfully rediscovers the complete hydrotope formula, while the same workflow applied to the harder three negative wavenumber problem discovers a new independent verified analytic expression for the six-point amplitude A6A_6.

Zihan Zhou, Digvijay Wadekar, Matias Zaldarriaga

Department of Physics, Princeton University, Princeton, NJ 08540, USA · Center for Gravitational Physics, University of Texas at Austin, Austin, TX 78712, USA · School of Natural Sciences, Institute for Advanced Study, 1 Einstein Drive, Princeton, NJ 08540, USA

Agentic DiscoveryScientific DiscoveryArtificial Intelligence AgentsSymbolic Regression
AskPDF