English
Related papers

Related papers: Small Scale Reflection for the Working Lean User

200 papers

General-purpose Large Language Models (LLMs) have achieved remarkable success in intelligence, performing comparably to human experts on complex reasoning tasks such as coding and mathematical reasoning. However, generating formal proofs in…

We describe a method for building composable and extensible verification procedures within the Coq proof assistant. Unlike traditional methods that rely on run-time generation and checking of proofs, we use verified-correct procedures with…

Programming Languages · Computer Science 2013-05-29 Gregory Malecha , Adam Chlipala , Thomas Braibant , Patrick Hulin , Edward Z. Yang

Advanced large language models (LLMs) frequently reflect in reasoning chain-of-thoughts (CoTs), where they self-verify the correctness of current solutions and explore alternatives. However, given recent findings that LLMs detect limited…

Machine Learning · Computer Science 2025-10-15 Zhongwei Yu , Wannian Xia , Xue Yan , Bo Xu , Haifeng Zhang , Yali Du , Jun Wang

We present a novel pipeline, ReflectEvo, to demonstrate that small language models (SLMs) can enhance meta introspection through reflection learning. This process iteratively generates self-reflection for self-training, fostering a…

Artificial Intelligence · Computer Science 2025-05-23 Jiaqi Li , Xinyi Dong , Yang Liu , Zhizhuo Yang , Quansen Wang , Xiaobo Wang , SongChun Zhu , Zixia Jia , Zilong Zheng

Large Language Models (LLMs) have demonstrated remarkable reasoning abilities, yet existing test-time frameworks often rely on coarse self-verification and self-correction, limiting their effectiveness on complex tasks. In this paper, we…

Computation and Language · Computer Science 2025-11-14 Haizhou Shi , Ye Liu , Bo Pang , Zeyu Leo Liu , Hao Wang , Silvio Savarese , Caiming Xiong , Yingbo Zhou , Semih Yavuz

Large language models (LLMs) with Chain-of-Thought (CoT) reasoning have achieved strong performance across diverse tasks, including mathematics, coding, and general reasoning. A distinctive ability of these reasoning models is…

Artificial Intelligence · Computer Science 2025-12-17 Ge Yan , Chung-En Sun , Tsui-Wei , Weng

We address the problem of translating informal mathematical proofs expressed in natural language into formal proofs in Lean4 under a constrained computational budget. Our approach is grounded in two key insights. First, informal proofs tend…

Logic in Computer Science · Computer Science 2025-12-15 Ziyu Wang , Bowen Yang , Chenyi Li , Yuan Zhang , Shihao Zhou , Bin Dong , Zaiwen Wen

While large language models (LLMs) have shown great potential across various domains, their applications in robotics remain largely limited to static prompt-based behaviors and still face challenges in complex tasks under zero-shot or…

Lean is an increasingly popular proof assistant based on dependent type theory. Despite its success, it still lacks important automation features present in more seasoned proof assistants, such as the Sledgehammer tactic in Isabelle/HOL. A…

Logic in Computer Science · Computer Science 2025-05-22 Abdalrhman Mohamed , Tomaz Mascarenhas , Harun Khan , Haniel Barbosa , Andrew Reynolds , Yicheng Qian , Cesare Tinelli , Clark Barrett

We present a novel method for symbolic regression (SR), the task of searching for compact programmatic hypotheses that best explain a dataset. The problem is commonly solved using genetic algorithms; we show that we can enhance such methods…

Machine Learning · Computer Science 2024-12-11 Arya Grayeli , Atharva Sehgal , Omar Costilla-Reyes , Miles Cranmer , Swarat Chaudhuri

Refinement Reflection turns your favorite programming language into a proof assistant by reflecting the code implementing a user-defined function into the function's (output) refinement type. As a consequence, at uses of the function, the…

Programming Languages · Computer Science 2016-10-18 Niki Vazou , Ranjit Jhala

Large Language Models (LLMs) have demonstrated impressive progress in complex reasoning tasks, largely driven by the Chain-of-Thought (CoT) paradigm, which decomposes difficult problems into intermediate steps. However, CoT reasoning…

Symbolic Computation · Computer Science 2026-05-26 Rui Wang , Zeming Wei , Yihao Zhang , Xiaokun Luan

ML4PG is an extension of the Proof General interface, allowing the user to invoke machine-learning algorithms and find proof similarities in Coq/SSReect libraries. In this paper, we present three new improvements to ML4PG. First, a new…

Logic in Computer Science · Computer Science 2014-02-04 Jónathan Heras , Ekaterina Komendantskaya

We present StepFun-Prover Preview, a large language model designed for formal theorem proving through tool-integrated reasoning. Using a reinforcement learning pipeline that incorporates tool-based interactions, StepFun-Prover can achieve…

Artificial Intelligence · Computer Science 2025-08-14 Shijie Shang , Ruosi Wan , Yue Peng , Yutong Wu , Xiong-hui Chen , Jie Yan , Xiangyu Zhang

We introduce Refinement Reflection, a new framework for building SMT-based deductive verifiers. The key idea is to reflect the code implementing a user-defined function into the function's (output) refinement type. As a consequence, at uses…

Programming Languages · Computer Science 2019-07-16 Niki Vazou , Anish Tondwalkar , Vikraman Choudhury , Ryan G. Scott , Ryan R. Newton , Philip Wadler , Ranjit Jhala

Large language models (LLMs) have achieved impressive results on multi-step mathematical reasoning, yet at the cost of high computational overhead. This challenge is particularly acute for test-time scaling methods such as parallel…

Machine Learning · Computer Science 2026-03-24 Yuanlin Chu , Bo Wang , Xiang Liu , Hong Chen , Aiwei Liu , Xuming Hu

Current reasoning paradigms for LLMs include chain-of-thought, ReAct, and post-hoc self-critique. These paradigms rely on two assumptions that fail on long-horizon, multi-stage tasks. As a result, errors accumulate silently across reasoning…

Artificial Intelligence · Computer Science 2026-05-08 Fan Huang

Evaluating log summarization systems is challenging due to the lack of high-quality reference summaries and the limitations of existing metrics like ROUGE and BLEU, which depend on surface-level lexical overlap. We introduce REFLEX, a…

Computation and Language · Computer Science 2026-04-21 Priyanka Mudgal

Large Language Models (LLMs) have transformed natural language processing, yet improving their problem-solving capabilities, particularly for complex, reasoning-intensive tasks, remains a persistent challenge. This paper introduces the REAP…

Computation and Language · Computer Science 2024-09-17 Ryan Lingo , Martin Arroyo , Rajeev Chhajer

Automated theorem proving systems built on Lean 4 increasingly rely on parallel tactic search over partially specified proofs, such as those generated by Draft-Sketch-Prove (DSP) pipelines. In current systems, each search branch…

Logic in Computer Science · Computer Science 2026-05-29 Austin Shen , Yunong Shi
‹ Prev 1 2 3 10 Next ›