English
Related papers

Related papers: Propose, Solve, Verify: Self-Play Through Formal V…

200 papers

Visual pointing, which aims to localize a target by predicting its coordinates on an image, has emerged as an important problem in the realm of vision-language models (VLMs). Despite its broad applicability, recent benchmarks show that…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Wenjie Yang , Zengfeng Huang

Large Language Models (LLMs) have demonstrated remarkable progress in complex reasoning tasks through both post-training and test-time scaling laws. While prevalent test-time scaling approaches are often realized by using external reward…

Machine Learning · Computer Science 2025-10-31 Fuxiang Zhang , Jiacheng Xu , Chaojie Wang , Ce Cui , Yang Liu , Bo An

We formally verify an algorithm for approximate policy iteration on Factored Markov Decision Processes using the interactive theorem prover Isabelle/HOL. Next, we show how the formalized algorithm can be refined to an executable, verified…

Artificial Intelligence · Computer Science 2024-06-12 Maximilian Schäffeler , Mohammad Abdulaziz

Self-play reinforcement learning trains language models on their own generated tasks, co-evolving a proposer and solver without human labels. Recent systems report strong reasoning gains, but collapse and instability are widely observed and…

Machine Learning · Computer Science 2026-05-22 Sophia Xiao Pu , Zhaotian Weng , Chengzhi Liu , Jayanth Srinivasa , Gaowen Liu , William Yang Wang , Xin Eric Wang

Many animals, and an increasing number of artificial agents, display sophisticated capabilities to perceive and manipulate objects. But human beings remain distinctive in their capacity for flexible, creative tool use -- using objects in…

Artificial Intelligence · Computer Science 2022-10-12 Kelsey R. Allen , Kevin A. Smith , Joshua B. Tenenbaum

Despite the syntactic fluency of Large Language Models (LLMs), ensuring their logical correctness in high-stakes domains remains a fundamental challenge. We present a neurosymbolic framework that combines LLMs with SMT solvers to produce…

Computation and Language · Computer Science 2026-05-05 Vikash Singh , Darion Cassel , Nathaniel Weir , Nick Feng , Sam Bayless

The formalization of existing mathematical proofs is a notoriously difficult process. Despite decades of research on automation and proof assistants, writing formal proofs remains arduous and only accessible to a few experts. While previous…

Artificial Intelligence · Computer Science 2023-02-21 Albert Q. Jiang , Sean Welleck , Jin Peng Zhou , Wenda Li , Jiacheng Liu , Mateja Jamnik , Timothée Lacroix , Yuhuai Wu , Guillaume Lample

Reinforcement Learning with Verifiable Rewards (RLVR) improves final-answer accuracy on reasoning tasks, but it does not reliably improve reasoning quality. Because outcome rewards only assess final answers, they also reward spurious…

Machine Learning · Computer Science 2026-05-19 Chenlu Ye , Zhou Yu , Ziji Zhang , Hao Chen , Narayanan Sadagopan , Jing Huang , Tong Zhang , Anurag Beniwal

Large language models (LLMs) are increasingly used for automated tutoring, but their reliability in structured symbolic domains remains unclear. We study step-level feedback for propositional logic proofs, which require precise symbolic…

While current software agents powered by large language models (LLMs) and agentic reinforcement learning (RL) can boost programmer productivity, their training data (e.g., GitHub issues and pull requests) and environments (e.g.,…

Software Engineering · Computer Science 2026-05-20 Yuxiang Wei , Zhiqing Sun , Emily McMilin , Jonas Gehring , David Zhang , Gabriel Synnaeve , Daniel Fried , Lingming Zhang , Sida Wang

In the context of multi-agent systems, the rational verification problem is concerned with checking which temporal logic properties will hold in a system when its constituent agents are assumed to behave rationally and strategically in…

Logic in Computer Science · Computer Science 2020-08-14 Julian Gutierrez , Muhammad Najib , Giuseppe Perelli , Michael Wooldridge

The reasoning capabilities of large language models (LLMs) have been significantly improved through reinforcement learning (RL). Nevertheless, LLMs still struggle to consistently verify their own reasoning traces. This raises the research…

Machine Learning · Computer Science 2025-11-20 Xiaoxuan Wang , Bo Liu , Song Jiang , Jingzhou Liu , Jingyuan Qi , Xia Chen , Baosheng He

Formally verifying properties of software code has been a highly desirable task, especially with the emergence of LLM-generated code. In the same vein, they provide an interesting avenue for the exploration of formal verification and…

Artificial Intelligence · Computer Science 2025-10-02 Balaji Rao , William Eiers , Carlo Lipizzi

Recursive self-improvement--where a model iteratively trains on its own outputs--promises sustained capability growth but faces a fundamental obstacle: recursive drift. As models train on self-generated data across multiple iterations,…

Artificial Intelligence · Computer Science 2026-03-24 Xinyu Zhang

Answer Set Programming (ASP) is a powerful declarative programming paradigm commonly used for solving challenging search and optimization problems. The modeling languages of ASP are supported by sophisticated solving algorithms (solvers)…

Logic in Computer Science · Computer Science 2022-08-08 Zach Hansen

Training language models to solve complex mathematical problems benefits from curriculum learning progressively training on simpler subproblems. However, existing decomposition methods are often heuristic, offering no guarantees that…

Artificial Intelligence · Computer Science 2026-02-10 Kaleem Ullah Qasim , Jiashu Zhang , Hao Li , Muhammad Kafeel Shaheen

Automated proof generation for formal software verification remains largely unresolved despite advances in large language models (LLMs). While LLMs perform well in NLP, vision, and code generation, formal verification still requires…

Logic in Computer Science · Computer Science 2026-04-10 Youngjoo Ahn , Sangyeop Yeo , Gijung Im , Jongmin Lee , Jinyoung Yeo , Jieung Kim

Self-play, where the algorithm learns by playing against itself without requiring any direct supervision, has become the new weapon in modern Reinforcement Learning (RL) for achieving superhuman performance in practice. However, the…

Machine Learning · Computer Science 2020-07-10 Yu Bai , Chi Jin

A safe Pareto improvement (SPI) [41] is a modification of a game that leaves all players better off with certainty. SPIs are typically proven under qualitative assumptions about the way different games are played. For example, we assume…

Computer Science and Game Theory · Computer Science 2025-11-24 Nathaniel Sauerberg , Caspar Oesterheld

To enhance the reasoning capabilities of Large Language Models (LLMs) without high costs of training, nor extensive test-time sampling, we introduce Verification-First (VF), a strategy that prompts models to verify a provided candidate…

Computation and Language · Computer Science 2026-05-26 Shiguang Wu , Quanming Yao