Related papers: Procedural Refinement by LLM-driven Algorithmic De…

Iterative refinement has been a promising paradigm to enable large language models (LLMs) to resolve difficult reasoning and problem-solving tasks. One of the key challenges, however, is how to effectively search through the enormous search…

The OpenAI o1-series models have demonstrated that leveraging long-form Chain of Thought (CoT) can substantially enhance performance. However, the recursive thinking capabilities of Large Language Models (LLMs) remain limited, particularly…

Automated Program Repair (APR) has benefited from the code understanding and generation capabilities of Large Language Models (LLMs). Existing feedback-based APR methods iteratively refine candidate patches using test execution feedback and…

Automated Program Repair (APR) is essential for ensuring software reliability and quality while enhancing efficiency and reducing developers' workload. Although rule-based and learning-based APR methods have demonstrated their…

The gap between the trepidation of program reliability and the expense of repairs underscores the indispensability of Automated Program Repair (APR). APR is instrumental in transforming vulnerable programs into more robust ones, bolstering…

Large Language Models (LLMs) have recently shown strong potential in automatic program repair (APR), especially in repository-level settings where the goal is to generate patches based on natural language issue descriptions, large…

Scaling inference-time computation has substantially improved the reasoning capabilities of language models. However, existing methods have significant limitations: serialized chain-of-thought approaches generate overly long outputs,…

Program refinement involves correctness-preserving transformations from formal high-level specification statements into executable programs. Traditional verification tool support for program refinement is highly interactive and lacks…

Large Language Models (LLMs) have demonstrated remarkable performance on various quantitative reasoning and knowledge benchmarks. However, many of these benchmarks are losing utility as LLMs get increasingly high scores, despite not yet…

This work compares large language models (LLMs) and neuro-symbolic approaches in solving Raven's progressive matrices (RPM), a visual abstract reasoning test that involves the understanding of mathematical rules such as progression or…

Abstract reasoning ability reflects the intelligence and generalization capacity of LLMs to extract and apply abstract rules. However, accurately measuring this ability remains challenging: existing benchmarks either rely on expensive…

Scientific discoveries must be communicated clearly to realize their full potential. Without effective communication, even the most groundbreaking findings risk being overlooked or misunderstood. The primary way scientists communicate their…

Large Language Models (LLMs) increasingly rely on external tools such as search engines to solve complex agentic tasks that require reasoning and external knowledge retrieval. Recently, reinforcement learning with verifiable rewards (RLVR)…

Modern Automatic Speech Recognition (ASR) systems can achieve high performance in terms of recognition accuracy. However, a perfectly accurate transcript still can be challenging to read due to grammatical errors, disfluency, and other…

The abductive natural language inference task ($\alpha$NLI) is proposed to evaluate the abductive reasoning ability of a learning system. In the $\alpha$NLI task, two observations are given and the most plausible hypothesis is asked to pick…

The Abstraction and Reasoning Corpus (ARC-AGI) poses a significant challenge for large language models (LLMs), exposing limitations in their abstract reasoning abilities. In this work, we leverage task-specific data augmentations throughout…

Automated program repair (APR) aims to automatically repair program errors without human intervention, and recent years have witnessed a growing interest on this research topic. While much progress has been made and techniques originating…

Formal verification via theorem proving enables the expressive specification and rigorous proof of software correctness, but it is difficult to scale due to the significant manual effort and expertise required. While Large Language Models…

Automated Program Repair (APR) has advanced rapidly with Large Language Models (LLMs), but most existing methods remain computationally expensive, and focused on a small set of languages. Ruby, despite its widespread use in web development…

Automatic program repair (APR) aims to reduce the manual efforts required to identify and fix errors in source code. Before the rise of LLM-based agents, a common strategy was to increase the number of generated patches, sometimes to the…