Related papers: Debugging the Debuggers: Failure-Anchored Structur…

Generative search engines and deep research LLM agents promise trustworthy, source-grounded synthesis, yet users regularly encounter overconfidence, weak sourcing, and confusing citation practices. We introduce DeepTRACE, a novel…

Test-based automated program repair has been a prolific field of research in software engineering in the last decade. Many approaches have indeed been proposed, which leverage test suites as a weak, but affordable, approximation to program…

This paper presents the tracking approach for deriving detectably recoverable (and thus also durable) implementations of many widely-used concurrent data structures. Such data structures, satisfying detectable recovery, are appealing for…

Even competent programmers make mistakes. Automatic verification can detect errors, but leaves the frustrating task of finding the erroneous line of code to the user. This paper presents an automatic approach for identifying potential error…

Trace alignment algorithms have been used in process mining for discovering the consensus treatment procedures and process deviations. Different alignment algorithms, however, may produce very different results. No widely-adopted method…

Autonomous GUI agents based on vision-language models (VLMs) often assume deterministic environment responses, generating actions without verifying whether previous operations succeeded. In real-world settings with network latency,…

This paper suggests that by operationalizing the concept of commitment in the shape of a model, a new insight is provided in improving software processes - a more human centered approach as opposed to various technical approaches available.…

As production code evolves, the test suite must co-evolve to remain effective. Existing benchmarks for test evolution operate at method-level granularity with pre-paired inputs, bypassing the task of locating affected tests from the full…

Background: Large language models are typically evaluated as models, benchmarks, or short conversational episodes. Less is known about what happens when an agent is embedded persistently in a real academic research environment with durable…

Code debugging is a vital stage of software development, essential for ensuring the reliability and performance of Large Language Models (LLMs) in the code generation task. Human debugging typically follows a multi-stage process, which…

In several software development scenarios, it is desirable to detect runtime errors and exceptions in code snippets without actual execution. A typical example is to detect runtime exceptions in online code snippets before integrating them…

Unit tests are critical in the hardware design lifecycle to ensure that component design modules are functionally correct and conform to the specification before they are integrated at the system level. Thus developing unit tests targeting…

In recent years, more vulnerabilities have been discovered every day, while manual vulnerability repair requires specialized knowledge and is time-consuming. As a result, many detected or even published vulnerabilities remain unpatched,…

Large Language Model (LLM) agents are increasingly deployed for complex, multi-step software engineering (SWE) tasks. However, their trajectories often contain costly inefficiencies, such as redundant exploration, looping, and failure to…

Existing datasets for coding agents evaluate performance on isolated, single pull request (PR) tasks in a stateless manner, failing to capture the reality of real-world software development where code changes accumulate, technical debt…

Software Engineering (SE) agents have shown promising abilities in supporting various SE tasks. Current SE agents remain fundamentally reactive, making decisions mainly based on conversation history and the most recent response. However,…

Serverless computing is an emerging cloud paradigm with serverless functions at its core. While serverless environments enable software developers to focus on developing applications without the need to actively manage the underlying…

While reinforcement learning (RL) enhances their ability to plan and reason across retrieval steps, we identify a critical failure mode in this setting: Tool-Call Hacking. Unlike execution-based tools (e.g., code or math), whose effects are…

Reliable evaluation of protein structure predictions remains challenging, as metrics like pLDDT capture energetic stability but often miss subtle errors such as atomic clashes or conformational traps reflecting topological frustration…

We introduce AvalancheBench, a benchmark for evaluating enterprise data agents through \emph{latent world recovery}. AvalancheBench improves on existing benchmarks in three ways. First, it evaluates analytical understanding rather than…