相关论文: How Can I Do That with ACL2? Recent Enhancements t…

This paper presents Efficient SMT-Based Context-Bounded Model Checker (ESBMC) v7.6, an extended version based on previous work on ESBMC v7.3 by K. Song et al. The v7.3 introduced a new Clang-based C++ front-end to address the challenges…

The emergence of Large Language Models (LLMs) has revealed a growing need for human-AI collaboration, especially in creative decision-making scenarios where trust and reliance are paramount. Through human studies and model evaluations on…

This volume collects the extended versions of selected papers originally presented at the two ACM SIGPLAN workshops: ML Family Workshop 2014 and OCaml 2014. Both were affiliated with ICFP 2014 and took place on two consecutive days, on…

Applications such as Google Docs, Office 365, and Dropbox show a growing trend towards incorporating multi-user live collaboration functionality into web applications. These collaborative applications share a need to efficiently express…

This volume contains a selection of papers presented at the 16th International Workshop on the ACL2 Theorem Prover and its Applications (ACL2-2020). The workshops are the premier technical forum for presenting research and experiences…

Prior studies investigating the internal workings of LLMs have uncovered sparse subnetworks, often referred to as circuits, that are responsible for performing specific tasks. Additionally, it has been shown that model performance…

Collaborations among various entities, such as companies, research labs, AI agents, and edge devices, have become increasingly crucial for achieving machine learning tasks that cannot be accomplished by a single entity alone. This is likely…

In this proceeding contribution we discuss the status and progress towards a modernised and extended International Lattice Data Grid (ILDG), which has seen major developments, updates, and upgrades over the last year. In particular,…

This paper describes a tool suite for the ACL2 programming language which incorporates certain ideas from the Hindley-Milner paradigm of functional programming (as exemplified in popular languages like ML and Haskell), including a "typed"…

Even though the ACL2 logic is first order, the ACL2 system offers several mechanisms providing users with some operations akin to higher order logic ones. In this paper, we propose a macro, named instance-of-defspec, to ease the reuse of…

Research on using Large Language Models (LLMs) in system development is expanding, especially in automated code and test generation. While E2E testing is vital for ensuring application quality, most test generation research has focused on…

Recent improvements of the LEO-II theorem prover are presented. These improvements include a revised ATP interface, new translations into first-order logic, rule support for the axiom of choice, detection of defined equality, and more…

Witness functions have recently been introduced in cryptographic protocols' literature as a new powerful way to prove protocol correctness with respect to secrecy. In this paper, we extend them to the property of authentication. We show how…

CMMI and Agile can work together. Over 80% of CMMI appraisals in 2018 were conducted at agile organizations, even though pre-2018 CMMI versions do not provide guidelines for agile contexts. A number of experience reports and research…

As large language model (LLM) assistants become increasingly integrated into enterprise workflows, their ability to generate accurate, semantically aligned, and executable outputs is critical. However, current conversational business…

In many applications of machine learning (ML), updates are performed with the goal of enhancing model performance. However, current practices for updating models rely solely on isolated, aggregate performance analyses, overlooking important…

SASyLF was released in 2008 and used as a proof assistant in courses at several universities. It proved itself useful and has continued to be used, and each iteration of use has encouraged further development: fixing bugs and adding…

AI agents are increasingly used to solve real-world tasks by reasoning over multi-turn user interactions and invoking external tools. However, applying reinforcement learning to such settings remains difficult: realistic objectives often…

Modular AI systems can be developed using LLM-prompts-based modules to minimize deployment time even for complex tasks. However, these systems do not always perform well and improving them using the data traces collected from a deployment…

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…