Related papers: Sub-method, partial behavioral reflection with Ref…
Self-evolving agents improve over time by reflecting on past failures, but existing evaluation is limited in two ways: it measures only task scores, leaving reflection quality unknown, and it relies on agents' own episode runs, offering no…
A common way of exposing functionality in contemporary systems is by providing a Web-API based on the REST API architectural guidelines. To describe REST APIs, the industry standard is currently OpenAPI-specifications. Test generation and…
Modern software systems are increasingly developed within rapid continuous integration and deployment (CI/CD) pipelines, where ensuring security prior to release presents significant technical and organizational challenges. Traditional…
The growing integration of AI tools in student design projects presents an unresolved challenge in HCI education: how should AI-generated content be cited and documented? Traditional citation frameworks -- grounded in credibility,…
Different from universal object detection, referring expression comprehension (REC) aims to locate specific objects referred to by natural language expressions. The expression provides high-level concepts of relevant visual and contextual…
Feedback is critical in education. This Innovative Practice Full Paper reports lessons learned from improving the quality of feedback in a semi-capstone software engineering course, with particular focus on how to deliver productive…
Multi-turn interactions between large language models (LLMs) and users naturally include implicit feedback signals. If an LLM responds in an unexpected way to an instruction, the user is likely to signal it by rephrasing the request,…
Lack of experience, inadequate documentation, and sub-optimal API design frequently cause developers to make mistakes when re-using third-party implementations. Such API misuses can result in unintended behavior, performance losses, or…
This report investigates the relationship between software refactoring and behavior preservation. Existing behavior preservation analyses often lack comprehensive insights into refactoring rejections and do not provide actionable solutions.…
We introduce the Principled Reasoning and Acting (PRAct) framework, a novel method for learning and enforcing action principles from trajectory data. Central to our approach is the use of text gradients from a reflection and optimization…
The source code of Function as a Service (FaaS) applications is constantly being refined. To detect if a source code change introduces a significant performance regression, the traditional benchmarking approach evaluates both the old and…
Self-reflection -- the ability of a large language model (LLM) to revisit, evaluate, and revise its own reasoning -- has recently emerged as a powerful behavior enabled by reinforcement learning with verifiable rewards (RLVR). While…
By late 20th century, the rationality wars had launched debates about the nature and norms of intuitive and reflective thinking. Those debates drew from mid-20th century ideas such as bounded rationality, which challenged more idealized…
We develop a behavioural theory of reflective parallel algorithms (RAs), i.e. synchronous parallel algorithms that can modify their own behaviour. The theory comprises a set of postulates defining the class of RAs, an abstract machine…
Software systems are increasingly making decisions on behalf of humans, raising concerns about the fairness of such decisions. Such concerns are usually attributed to flaws in algorithmic design or biased data, but we argue that they are…
Existing prompt-optimization techniques rely on local signals to update behavior, often neglecting broader and recurring patterns across tasks, leading to poor generalization; they further rely on full-prompt rewrites or unstructured…
Complex tasks involving tool integration pose significant challenges for Large Language Models (LLMs), leading to the emergence of multi-agent workflows as a promising solution. Reflection has emerged as an effective strategy for correcting…
Learning models of artificial intelligence can nowadays perform very well on a large variety of tasks. However, in practice different task environments are best handled by different learning models, rather than a single, universal,…
The field of Reinforcement Learning (RL) has garnered increasing attention for its ability of optimizing user retention in recommender systems. A primary obstacle in this optimization process is the environment non-stationarity stemming…
CONTEXT The R programming language has a huge and active community, especially in the area of statistical computing. Its interpreted nature allows for several interesting constructs, like the manipulation of functions at run-time, that…