相关论文: Combining Mechanical and Agentic Specification Inf…

The Move Prover (MVP) is a formal verifier for smart contracts written in the Move programming language. Recently, Move on Aptos was extended with higher-order functions: imperative functions as first-class values that can be passed around,…

Auto-active program verification rests on the ability to effectively the translation from annotated programs into verification conditions that are then discharged by automated theorem provers in the background. Characteristic such tools,…

Large language models (LLMs) have demonstrated remarkable capabilities across diverse tasks, but optimizing LLM-based agentic systems remains challenging due to the vast search space of agent configurations, prompting strategies, and…

Specification synthesis, the task of automatically inferring formal specifications from program implementations and natural language, is important for refactoring, transpilation, optimization, and verification, yet remains an open challenge…

Agentic theorem provers combine a reasoning model, retrieval, search, and a proof assistant verifier, yet it remains unclear which components actually improve finite-budget proof success and why they help on real mathematical workloads. We…

Modern software relies on libraries and uses them via application programming interfaces (APIs). Correct API usage as well as many software engineering tasks are enabled when APIs have formal specifications. In this work, we analyze the…

Parameter identification for mechanistic Ordinary Differential Equation (ODE) models underpins prediction and control in several applications, yet remains a manual and labor-intensive process: datasets are noisy and partial, models can be…

Autoresearch offers a flexible paradigm for automating scientific tasks, in which an AI agent proposes, implements, evaluates, and refines candidate solutions against a quantitative objective. Here, we use composition-based…

Logical specifications are widely used to represent software systems and their desired properties. Under system degradation or environmental changes, commonly seen in complex real-world robotic systems, these properties may no longer hold…

AI agents have shown initial promise in automating mathematical theorem proving in proof assistants such as Lean. The same proof assistants can be used to verify the correctness of code by pairing code with specifications and proofs that…

The predictive processing (PP) hypothesizes that the predictive inference of our sensorimotor system is encoded implicitly in the regularities between perception and action. We propose a neural architecture in which such regularities of…

Agentic language model (LM) systems power modern applications like "Deep Research" and "Claude Code," and leverage multi-LM architectures to overcome context limitations. Beneath their apparent diversity lies a recurring pattern: smaller…

In this paper we use pre existing language support for type modifiers and object capabilities to enable a system for sound runtime verification of invariants. Our system guarantees that class invariants hold for all objects involved in…

Can a committee of weak reasoning-model calls reach the performance of much stronger models? We study verifier-backed committee search as inference-time boosting for reasoning language models. The mechanism is not simply that ``more agents…

Language models (LMs) are becoming increasingly dependent on external tools. LM-based agentic frameworks frequently interact with their environment via such tools to search files, run code, call APIs, etc. Further, modern reasoning-based…

Agentic systems have recently emerged as state-of-the-art approaches for automated theorem proving in formal mathematics. To assess how far these capabilities extend to program verification, we evaluate Claude Code in an agentic proving…

In functional programming, datatypes a la carte provide a convenient modular representation of recursive datatypes, based on their initial algebra semantics. Unfortunately it is highly challenging to implement this technique in proof…

AI coding agents spend a substantial fraction of their tool calls on undirected codebase exploration. We investigate whether providing agents with formal architecture descriptors can reduce this navigational overhead. We present three…

Text-to-image generative models have achieved remarkable visual quality but still struggle with compositionality$-$accurately capturing object relationships, attribute bindings, and fine-grained details in prompts. A key limitation is that…

Rely-guarantee (RG) logic uses thread interference specifications (relies and guarantees) to reason about the correctness of multithreaded software. Unfortunately, RG logic requires each function postcondition to be "stabilized" or…