10 papers
Danus: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory
Jihao Liu, Guoxiong Gao, Zeming Sun +8
Recent LLM-based mathematical reasoning agents have begun to tackle research-level problems and, in several cases, have contributed to the resolution of open problems. However, sca…
Automated Conjecture Resolution with Formal Verification
Haocheng Ju, Guoxiong Gao, Jiedong Jiang +13
Recent advances in large language models have significantly improved their ability to perform mathematical reasoning, extending from elementary problem solving to increasingly capa…
On some open problems in commutative algebra resolved by Rethlas
Jiedong Jiang, Yixiao Li, Zeming Sun +3
We report on a collection of open problems in commutative algebra and related areas that have been resolved (proved or disproved) using the Rethlas natural-language automated reaso…
Optimal bend-and-break for foliations
Jihao Liu, Zeming Sun, Jiedong Jiang
We show that for every foliation of rank on a normal projective variety, the optimal constant in the bend-and-break inequality for tangent rational curves is $r+1…
LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Proving
Guoxiong Gao, Zeming Sun, Jiedong Jiang +5
Proving theorems in Lean 4 often requires identifying a scattered set of library lemmas whose joint use enables a concise proof -- a task we call global premise retrieval. Existing…
From Atoms to Trees: Building a Structured Feature Forest with Hierarchical Sparse Autoencoders
Yifan Luo, Yang Zhan, Jiedong Jiang +4
Sparse autoencoders (SAEs) have proven effective for extracting monosemantic features from large language models (LLMs), yet these features are typically identified in isolation. H…
FATE: A Formal Benchmark Series for Frontier Algebra of Multiple Difficulty Levels
Jiedong Jiang, Wanyi He, Yuefeng Wang +8
Recent advances in large language models (LLMs) have demonstrated impressive capabilities in formal theorem proving, particularly on contest-based mathematical benchmarks like the…
REAL-Prover: Retrieval Augmented Lean Prover for Mathematical Reasoning
Ziju Shen, Naohao Huang, Fanyi Yang +11
Nowadays, formal theorem provers have made monumental progress on high-school and competition-level mathematics, but few of them generalize to more advanced mathematics. In this pa…
Herald: A Natural Language Annotated Lean 4 Dataset
Guoxiong Gao, Yutong Wang, Jiedong Jiang +4
Verifiable formal languages like Lean have profoundly impacted mathematical reasoning, particularly through the use of large language models (LLMs) for automated reasoning. A signi…
A Semantic Search Engine for Mathlib4
Guoxiong Gao, Haocheng Ju, Jiedong Jiang +2
The interactive theorem prover Lean enables the verification of formal mathematical proofs and is backed by an expanding community. Central to this ecosystem is its mathematical li…