Related papers: SPEAR: Code-Augmented Agentic Prompt Optimization

Approximate Message Passing (AMP) has been shown to be a superior method for inference problems, such as the recovery of signals from sets of noisy, lower-dimensionality measurements, both in terms of reconstruction accuracy and in…

Recent research has highlighted the potential of LLM applications, like ChatGPT, for performing label annotation on social computing text. However, it is already well known that performance hinges on the quality of the input prompts. To…

We present a systematic empirical study of prompt engineering for formal mathematical reasoning in the context of the SAIR Equational Theories Stage 1 competition. The task requires deciding whether one equational law implies another over…

Language models of code have demonstrated state-of-the-art performance across various software engineering and source code analysis tasks. However, their demanding computational resource requirements and consequential environmental…

With the advancement of Agentic AI, researchers are increasingly leveraging autonomous agents to address challenges in software engineering (SE). However, the large language models (LLMs) that underpin these agents often function as black…

Training Large Language Models (LLMs) for reasoning tasks is increasingly driven by Reinforcement Learning with Verifiable Rewards (RLVR), where Proximal Policy Optimization (PPO) provides a principled framework for stable policy updates.…

Information Retrieval (IR) evaluation involves far more complexity than merely presenting performance measures in a table. Researchers often need to compare multiple models across various dimensions, such as the Precision-Recall trade-off…

Developing effective test cases capable of thoroughly exercising large-scale software systems is inherently difficult, especially if such systems have voluminous, complex, and deeply nested source codes. In this work, we present a novel…

Automated Program Repair (APR) is a task to automatically generate patches for the buggy code. However, most research focuses on generating correct patches while ignoring the consistency between the fixed code and the original buggy code.…

Compilers are crucial in optimizing programs and accelerating their execution. However, optimizing programs automatically using compilers is not trivial. Recent work has attempted to use reinforcement learning (RL) to solve this problem. It…

Preference-based reinforcement learning (PbRL) has shown impressive capabilities in training agents without reward engineering. However, a notable limitation of PbRL is its dependency on substantial human feedback. This dependency stems…

Prescriptive Process Monitoring (PresPM) recommends interventions during business processes to optimize key performance indicators (KPIs). In realistic settings, interventions are rarely isolated: organizations need to align sequences of…

The arrival of large language models (LLMs) capable of multi-step reasoning, tool use, and long-horizon planning has produced a qualitative shift in software engineering. Where earlier code-completion tools such as GitHub Copilot operated…

Adaptive prompt and program search makes LLM evaluation selection-sensitive. Once benchmark items are reused inside tuning, the observed winner's score need not estimate the fresh-data performance of the full tune-then-deploy procedure. We…

Large language models can now generate substantial code and draft research text, but research-software projects require more than either artifact alone. The mathematical thesis, executable system, benchmark surface, and public claims must…

Highly effective, task-specific prompts are often heavily engineered by experts to integrate detailed instructions and domain insights based on a deep understanding of both instincts of large language models (LLMs) and the intricacies of…

Automated Scoring (AS), the natural language processing task of scoring essays and speeches in an educational testing setting, is growing in popularity and being deployed across contexts from government examinations to companies providing…

We propose SPARC, a lightweight continual learning framework for large language models (LLMs) that enables efficient task adaptation through prompt tuning in a lower-dimensional space. By leveraging principal component analysis (PCA), we…

We present adaptive sequential SAA (sample average approximation) algorithms to solve large-scale two-stage stochastic linear programs. The iterative algorithm framework we propose is organized into \emph{outer} and \emph{inner} iterations…

Large Language Models (LLMs) empowered with Tool-Integrated Reasoning (TIR) can iteratively plan, call external tools, and integrate returned information to solve complex, long-horizon reasoning tasks. Agentic Reinforcement Learning…