Related papers: BoostAPR: Boosting Automated Program Repair via Ex…
Repository-level code editing requires models to understand complex dependencies and execute precise multi-file modifications across a large codebase. While recent gains on SWE-bench rely heavily on complex agent scaffolding, it remains…
Process reward models (PRMs) have proven effective for test-time scaling of Large Language Models (LLMs) on challenging reasoning tasks. However, reward hacking issues with PRMs limit their successful application in reinforcement…
Providing feedback on programming assignments is a tedious task for the instructor, and even impossible in large Massive Open Online Courses with thousands of students. Previous research has suggested that program repair techniques can be…
Multi-step tool orchestration remains challenging for LLMs, as state-of-the-art models frequently fail on full sequence execution due to parameter errors. Training for these workflows faces two obstacles: the lack of environments supporting…
Detecting and fixing bugs are two of the most important yet frustrating parts of the software development cycle. Existing bug detection tools are based mainly on static analyzers, which rely on mathematical logic and symbolic reasoning…
Agent-repair leaderboards reorder under evaluator reconfiguration, and a measurable share of the reordering is produced by methods that consult evaluator-derived signal during internal selection of candidate repairs. We document this…
Reinforcement learning for LLMs is vulnerable to reward hacking, where models exploit shortcuts to maximize reward without solving the intended task. We systematically study this phenomenon in coding tasks using an environment-manipulation…
A typical approach developers follow to influence an LLM's behavior in an application is through careful manipulation of the prompt, such as by adding or modifying instructions. However, merely adding more instructions provides little…
Vision-Language-Action systems follow instructions to execute multi-step tasks in multimodal environments. Recent VLA approaches typically rely on post-hoc correction mechanisms or operate under fixed task decompositions and alignment…
Recent machine learning papers often report 1-2 percentage point improvements from a single run on a benchmark. These gains are highly sensitive to random seeds, data ordering, and implementation details, yet are rarely accompanied by…
Tool-integrated agents that interleave reasoning with API calls are promising for complex tasks, yet aligning them for high-stakes, domain-specific deployment remains challenging: existing reinforcement learning approaches rely on coarse…
How should two language models interact to produce better code than either can alone? The conventional approach -- a reasoning model plans, a code specialist implements -- seems natural but fails: on HumanEval+, plan-then-code degrades…
Retrieval-augmented agents can query external evidence, yet their reliability in multi-step reasoning remains limited: noisy retrieval may derail multi-hop question answering, while outcome-only reinforcement learning provides credit…
Retrieving the correct set of files from a large codebase is a crucial step in Automated Program Repair (APR). High recall is necessary to ensure that the relevant files are included, but simply increasing the number of retrieved files…
Automatic program repair (APR) techniques have the potential to reduce manual efforts in uncovering and repairing program defects during the code review (CR) process. However, the limited accuracy and considerable time costs associated with…
Tabular language models can generate synthetic tables by modeling rows as token sequences, but they are typically trained once with supervised fine-tuning and then used as static synthesizers. This is limiting because next-token likelihood…
Automated Program Repair (APR) has garnered significant attention due to its potential to streamline the bug repair process for human developers. Recently, LLM-based APR methods have shown promise in repairing real-world bugs. However,…
Reinforcement Learning from Verifiable Rewards (RLVR) has driven recent progress in code large language models by leveraging execution-based feedback from unit tests, but its scalability is fundamentally constrained by the availability and…
Automated program repair (APR) has great potential to reduce the effort and time-consumption in software maintenance and becomes a hot topic in software engineering recently with many approaches being proposed. Multi-location program repair…
Self-paced reinforcement learning (RL) aims to improve the data efficiency of learning by automatically creating sequences, namely curricula, of probability distributions over contexts. However, existing techniques for self-paced RL fail in…