AutoACSL is a framework that uses Code Property Graphs and large language models to generate formal specifications for C programs with improved success ratio and full proof ratio.

This paper proposes using large language models (LLMs) to generate and compositionally verify software implementations directly from natural language specifications, showing promising preliminary resu…

A LLM powered system is presented for generating formally verified code for structured data translation between JSON schema of a pulse oximeter and FHIR format in Medical IoT.

Proposed method, KBSpec, uses external and internal knowledge to improve formal specification generation by LLMs, increasing verification pass rates and producing more high-completeness specifications…

pcbGPT is a grounded system that automatically generates editable KiCad PCB schematics from natural language requirements, achieving high accuracy on complex embedded design tasks.

The paper introduces DOMINO, a novel inductive framework that synthesizes domain-specific data for LLMs using only reference examples, significantly improving performance on challenging, implicitly de…

The paper introduces StreamSynth, a sequential setting for synthetic data generation, and proposes SynLearner, a framework that enables LLMs to improve synthesis performance by accumulating and transf…

This paper presents a framework for learning minimal Linear Temporal Logic (LTL) formulas from uncertain system demonstrations, reducing the problem to Pseudo-Boolean Optimization.

SEMBridge is a tagless-final framework that allows a single executable object program to generate multiple program semantics, including weakest-precondition and bounded-checking interpretations, ensur…

This paper introduces decode-time grammars to ensure grammatical and semantic correctness of code generated by large language models, particularly for low-resource programming surfaces.

Introduce Parallel-Synthesis, a framework enabling a synthesizer to directly consume parallel agent branches' KV caches, improving efficiency and performance.

The paper introduces ProofLoop, a novel ReAct agent that uses a solver-in-the-loop approach to automatically generate and formally verify SystemVerilog Assertions (SVA) from natural language specifica…

The paper introduces FVSpec, a large-scale benchmark that translates thousands of real-world Python property-based tests into formal Lean 4 specifications to evaluate AI models for formal software ver…

The paper proposes a flexible meta-programming framework to declaratively operationalize and explore varied temporal logics, such as TEL, MEL, and DEL, within standard Answer Set Programming systems.

The paper proposes integrating dependent pattern matching into the unification process in dependently typed languages to synthesize functions defined by case analysis, addressing the limitation of exi…

The paper introduces TRAILS~, a novel method that improves code correctness validation by grounding LLM reasoning in concrete (input, output) pairs derived from specifications, achieving state-of-the-…

This paper develops distributive laws for parallel composition in a rely/guarantee style theory for reasoning about concurrent programs.

The paper proposes projectional decoding, a novel framework that integrates a partial graph model alongside text generation to ensure the semantic validity of LLM-generated software artifacts.