Programmers write formal specifications, and LLMs implement them, proving that each implementation matches its spec. Taken to its extreme, this makes specification languages the new programming langua...
Spec‑Harness evaluates how well large language models (LLMs) synthesize Java Modeling Language (JML) specifications by measuring behavioral adequacy across precondition and postcondition correctness and completeness. The study shows that while prompt optimization can raise verifier pass rates, many accepted specifications remain behaviorally weak, either over‑ or under‑constraining inputs and outputs. Spec‑Harness also serves as a feedback mechanism that improves the quality of specifications generated by general‑purpose coding agents and a specialized JML agent.
arXiv:2606. 26490v1 Announce Type: cross Abstract: Static verification tools can assure industrial scale software, but require significant human labor to write specifications.
arXiv:2607. 06341v1 Announce Type: cross Abstract: Formal verification offers the strongest guarantee of software correctness, but it does not scale: the proofs demanded by interactive theorem provers such as Coq require enormous expert effort.
arXiv:2602. 20064v2 Announce Type: replace-cross Abstract: Large language models are increasingly deployed as agents: they plan, call tools, read untrusted data, and act on the results.
Formal verification offers the strongest guarantee of software correctness, but it does not scale: the proofs demanded by interactive theorem provers such as Coq require enormous expert effort. Large language models (LLMs) promise to generate these proofs automatically, yet existing approaches wire a fixed, human-designed proof strategy into the system and constrain the model to follow it (retrieving premises and predicting tactics one step at a time, or splitting goals by divide-and-conquer), and still prove only a fraction of their target theorems.
arXiv:2606. 00220v1 Announce Type: cross Abstract: Formal methods provide rigorous accounts of program behavior, but practical software engineering often works through executable libraries, tests, and incremental design.
arXiv:2606. 03019v1 Announce Type: cross Abstract: Copyleft, as implemented in licenses such as the GNU General Public License, was a legal hack that used copyright to guarantee user freedom by tying the availability of source code to every act of distribution.
The paper introduces JAZ, a minimalist LLM agent framework that centers on a single primitive called “invoke”, which allows an LLM to write and execute arbitrary code, including recursive calls, while treating all inputs and interaction history as variables in the code environment. JAZ provides built‑in hooks for constraints and monitoring but relies solely on prompting, without external tools, memory systems, or file‑system access. Experiments show that JAZ “invoke” outperforms specialized external harnesses such as Letta (MemGPT) and ACE on long‑horizon recall tasks and continual self‑improvement, achieving higher accuracy at lower cost.
arXiv:2607. 13921v1 Announce Type: cross Abstract: Languages with rich static semantics, such as Rust, provide stronger guarantees for AI-generated code, but their strictness makes generation more difficult.
arXiv:2602. 09464v2 Announce Type: replace-cross Abstract: Vericoding refers to the generation of formally verified code from rigorous specifications.
arXiv:2608. 13522v1 Announce Type: cross Abstract: AI agents are increasingly used for programming, but do not provide any guarantee on the correctness of generated code.