Related papers: LaForge: Always-Correct and Fast Incremental Build…
Automated code generation remains a persistent challenge in software engineering, as conventional multi-agent frameworks are often constrained by static planning, isolated execution, high computational overhead, and limited adaptability to…
The high cost of agentic workflows in formal mathematics hinders large-scale data synthesis, exacerbating the scarcity of open-source corpora. To address this, we introduce \textbf{TheoremForge}, a cost-effective formal data synthesis…
Frequent toolchain updates and growing ISA diversity have made system-level software package repair increasingly important. Diagnosing and repairing build failures remains challenging because failures involve heterogeneous evidence,…
Security analysts routinely query system logs to detect threats and investigate incidents, but each log source uses its own semi-structured format: logs are cheap to produce, but expensive to use. The standard approach, building per-source…
Recently, a diverse set of decoding and reranking procedures have been shown effective for LLM-based code generation. However, a comprehensive framework that links and experimentally compares these methods is missing. We address this by…
Large Language Models (LLMs) are showing remarkable performance in generating source code, yet the generated code often has issues like compilation errors or incorrect code. Researchers and developers often face wasted effort in…
Scientific and engineering verticals often suffer from data scarcity and strict executability requirements: models must generate not only fluent text, but also syntactically valid, tool-compilable scripts. We present a schema-first…
Formal specification generation has recently drawn attention in software engineering as a way to improve program correctness without requiring manual annotations. Large Language Models (LLMs) have shown promise in this area, but early…
Large Language Models (LLMs) can generate code but often introduce security vulnerabilities, logical inconsistencies, and compilation errors. Prior work demonstrates that LLMs benefit substantially from structured feedback, static analysis,…
Efficient fine-tuning is vital for adapting large language models (LLMs) to downstream tasks. However, it requires non-trivial efforts to implement these methods on different models. We present LlamaFactory, a unified framework that…
Large language models can generate plausible code, but remain brittle for formal verification in proof assistants such as Lean. A central scalability challenge is that verified synthesis requires consistent artifacts across several coupled…
Automated code completion, aiming at generating subsequent tokens from unfinished code, has been significantly benefited from recent progress in pre-trained Large Language Models (LLMs). However, these models often suffer from coherence…
Experience with lightweight formal methods suggests that programmers are willing to write specification if it brings tangible benefits to their usual development activities. This paper considers stronger specifications and studies whether…
The latest paradigm shift in software development brings in the innovation and automation afforded by Large Language Models (LLMs), showcased by Generative Pre-trained Transformer (GPT), which has shown remarkable capacity to generate code…
Although it is possible to increase confidence in Free and Open Source Software (FOSS) by reviewing its source code, trusting code is not the same as trusting its executable counterparts. These are typically built and distributed by…
The release note is an essential software artifact of open-source software that documents crucial information about changes, such as new features and bug fixes. With the help of release notes, both developers and users could have a general…
Composing language models (LMs) into multi-step language programs and automatically optimizing their modular prompts is now a mainstream paradigm for building AI systems, but the tradeoffs in this space have only scarcely been studied…
Interactive proof assistants are computer programs carefully constructed to check a human-designed proof of a mathematical claim with high confidence in the implementation. However, this only validates truth of a formal claim, which may…
Writing declarative models has numerous benefits, ranging from automated reasoning and correction of design-level properties before systems are built, to automated testing and debugging of their implementations after they are built. Alloy…
Formal software specification is known to enable early error detection and explicit invariants, yet it has seen limited industrial adoption due to its high notation overhead and the expertise required to use traditional formal languages.…