paper-with-me

Papers

ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level Combinatorics

2026-06-09 · Shunkai Zhang, Haoran Zhang, Yun Luo, Qianjia Cheng, Haodi Lei, Yizhuo Li, Runzhe Zhan, Zhilin Wang, Bangjie Xu, Yucheng Su, Xinmiao Han, Xiaoye Qu, Dongrui Liu, Zhouchen Lin, Yu Qiao, Ning Ding, Yafu Li, Yu Cheng arxiv

Combinatorics is central to Olympiad-level mathematical problem solving, requiring deep discrete reasoning, creative constructions, and rigorous structural insight. Recent evidence suggests that even today's strongest frontier models remain uneven on Olympiad combinatorics, revealing a gap in creative mathematical reasoning. We introduce ComBench, an Olympiad-level combinatorics benchmark for evaluating and diagnosing the combinatorial reasoning capabilities of large language models. ComBench contains 100 human-annotated competition-level problems organized around two complementary settings: analysis-centric problems, which primarily require rigorous mathematical arguments, and construction-centric problems, which require explicit constructions in addition to correctness justifications. The evaluation protocol combines rubric-guided proof grading with deterministic construction verification, exposing cases where proof quality and construction validity diverge. Experiments on frontier open- and closed-source models show that ComBench is far from saturated: the strongest model reaches 65.4% overall Avg. and 75.3% overall Best@4. We further find that Rigorous Proof Reasoning and Constructive Realization are distinct capabilities: Kimi-K2.6 trails GPT-5.5 on analysis-centric proof grading but surpasses it on construction-centric Best@4, while Existence and Construction problems remain consistently hardest across representative frontier models.

📄 PDF Abstract BibTeX arXiv:2606.10479

Code (0)

등록된 구현이 없습니다.

Tasks

Mathematical Reasoning

Similar Papers 제목 키워드 기반

EcomBench: Towards Holistic Evaluation of Foundation Agents in E-commerce

2025-12-09 · Rui Min, Zile Qiao, Ze Xu, Jiawen Zhai 외 arxiv

Foundation agents have rapidly advanced in their ability to reason and interact with real environments, making the evaluation of their core capabilities increasingly important. While many benchmarks have been developed t…

Information Retrieval

ComBench: A Repo-level Real-world Benchmark for Compilation Error Repair

2026-03-28 · Jia Li, Zeyang Zhuang, Zhuangbin Chen, Yuxin Su 외 arxiv

Compilation errors pose pervasive and critical challenges in software development, significantly hindering productivity. Therefore, Automated Compilation Error Repair (ACER) techniques are proposed to mitigate these issu…

Enumerate-Conjecture-Prove: Formally Solving Answer-Construction Problems in Math Competitions

2025-05-24 · Jialiang Sun, Yuzhi Tang, Ao Li, Chris J. Maddison 외

Mathematical reasoning lies at the heart of artificial intelligence, underpinning applications in education, program verification, and research-level mathematical discovery. Mathematical competitions, in particular, pres…

Automated Theorem ProvingMathMathematical Reasoning

Advocate for Complete Benchmarks for Formal Reasoning with Formal/Informal Statements and Formal/Informal Proofs

2025-07-07 · Roozbeh Yousefzadeh, Xuenan Cao arxiv

This position paper provides a critical but constructive discussion of current practices in benchmarking and evaluative practices in the field of formal reasoning and automated theorem proving. We take the position that …

Automated Theorem Proving

Proof or Bluff? Evaluating LLMs on 2025 USA Math Olympiad

2025-03-27 · Ivo Petrov, Jasper Dekoninck, Lyuben Baltadzhiev, Maria Drencheva 외

Recent math benchmarks for large language models (LLMs) such as MathArena indicate that state-of-the-art reasoning models achieve impressive performance on mathematical competitions like AIME, with the leading model, Gem…

MathMathematical Reasoning