Related papers: Pull Requests as a Training Signal for Repo-Level …

Code large language models (LLMs) have become indispensable tools for building efficient and automated coding pipelines. Existing models are typically post-trained using reinforcement learning (RL) from general-purpose LLMs using "human…

Process Reward Models (PRMs) have become essential for improving Large Language Models (LLMs) via test-time scaling, yet their effectiveness in coding remains limited due to the lack of meaningful step decompositions in code and the noise…

Large Language Model (LLM)-based agents are increasingly applied to tasks requiring structured reasoning, tool use, and environmental adaptation, such as data manipulation, multistep planning, and computer-use automation. However, despite…

We propose a new strategy for applying large pre-trained language models to novel tasks when labeled training data is limited. Rather than apply the model in a typical zero-shot or few-shot fashion, we treat the model as the basis for…

Iterative self-refinement is a popular inference-time reliability technique, but its effectiveness in code-mode tool use depends heavily on the structure of the feedback signal: unstructured critique helps inconsistently across models, and…

AI coding agents are rapidly transforming software engineering by performing tasks such as feature development, debugging, and testing. Despite their growing impact, the research community lacks a comprehensive dataset capturing how these…

To create unit tests, it may be necessary to refactor the production code, e.g. by widening access to specific methods or by decomposing classes into smaller units that are easier to test independently. We report on an extensive study to…

Sequential knowledge editing in large language models often causes catastrophic collapse of the model's general abilities, especially for parameter-modifying methods. Existing approaches mitigate this issue through heuristic constraints on…

Pre-trained Generative Language models (e.g. PLBART, CodeT5, SPT-Code) for source code yielded strong results on several tasks in the past few years, including code generation and translation. These models have adopted varying pre-training…

Reinforcement learning (RL) with unit test feedback has enhanced large language models' (LLMs) code generation, but relies on sparse rewards provided only after complete code evaluation, limiting learning efficiency and incremental…

Large Language Model (LLM) agents show great promise for complex, multi-turn tool-use tasks, but their development is often hampered by the extreme scarcity of high-quality training data. Supervised fine-tuning (SFT) on synthetic data leads…

As coding challenges become more complex, recent advancements in Large Language Models (LLMs) have led to notable successes, such as achieving a 94.6\% solve rate on the HumanEval benchmark. Concurrently, there is an increasing commercial…

We introduce TDFlow, a novel test-driven agentic workflow that frames repository-scale software engineering as a test-resolution task, specifically designed to solve human-written tests. Given a set of tests, TDFlow repeatedly proposes,…

The automatic generation of pull requests (PRs) using AI agents has become increasingly common. Although AI-generated PRs are fast and easy to create, their merge rates have been reported to be lower than those created by humans. In this…

Large Language Models (LLMs) have shown strong capabilities in code generation and comprehension, yet their application to complex software engineering tasks often suffers from low precision and limited interpretability. We present Repeton,…

Automatic Program Repair (APR) endeavors to autonomously rectify issues within specific projects, which generally encompasses three categories of tasks: bug resolution, new feature development, and feature enhancement. Despite extensive…

Register-Transfer Level (RTL) coding is an iterative, repository-scale process in which Power, Performance, and Area (PPA) emerge from interactions across many files and the downstream toolchain. While large language models (LLMs) have…

Mechanisms for continued self-improvement of language models without external supervision remain an open challenge. We propose Peer-Predictive Self-Training (PST), a label-free fine-tuning framework in which multiple language models improve…

AI coding agents have shown great progress on Python software engineering benchmarks like SWE-Bench, and for other languages like Java and C in benchmarks like Multi-SWE-Bench. However, C# -- a prominent enterprise language ranking #5 in…

The paper shows that parameter-efficient reinforcement learning (PE-RL) is a highly effective training regime to improve large language models' (LLMs) ability to answer queries on sensitive topics with a Neutral Point of View (NPOV), i.e.…