English
Related papers

Related papers: RubricRefine: Improving Tool-Use Agent Reliability…

200 papers

Execution-based feedback like unit testing is widely used in the development of coding agents through test-time scaling (TTS) and reinforcement learning (RL). This paradigm requires scalable and reliable collection of unit test cases to…

Computation and Language · Computer Science 2025-12-29 KaShun Shum , Binyuan Hui , Jiawei Chen , Lei Zhang , X. W. , Jiaxi Yang , Yuzhen Huang , Junyang Lin , Junxian He

Rhetorical Role Labeling (RRL) assigns a functional role to each sentence in a document and is widely used in legal, medical, and scientific domains. While language models (LMs) achieve strong average performance, they remain unreliable on…

Computation and Language · Computer Science 2026-05-19 Anas Belfathi , Nicolas Hernandez , Laura Monceaux , Warren Bonnard , Richard Dufour

Large Reasoning Models (LRMs) achieve strong performance by generating long reasoning traces with reflection. Through a large-scale empirical analysis, we find that a substantial fraction of reflective steps consist of self-verification…

Computation and Language · Computer Science 2026-02-04 Quanyu Long , Kai Jie Jiang , Jianda Chen , Xu Guo , Leilei Gan , Wenya Wang

Large language models have demonstrated impressive reasoning capabilities but are inherently limited by their knowledge reservoir. Retrieval-augmented reasoning mitigates this limitation by allowing LLMs to query external resources, but…

Computation and Language · Computer Science 2025-09-22 Yaorui Shi , Sihang Li , Chang Wu , Zhiyuan Liu , Junfeng Fang , Hengxing Cai , An Zhang , Xiang Wang

Tool-integrated visual reasoning (TiVR) has demonstrated great potential in enhancing multimodal problem-solving. However, existing TiVR paradigms mainly focus on integrating various visual tools through reinforcement learning, while…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Yuji Wang , Wenlong Liu , Jingxuan Niu , Haoji Zhang , Yansong Tang

Tool-augmented LLM agents tend to call tools indiscriminately, even when the model can answer directly. Each unnecessary call wastes API fees and latency, yet no existing benchmark systematically studies when a tool call is actually needed.…

Computation and Language · Computer Science 2026-05-22 Chung-En Sun , Linbo Liu , Ge Yan , Zimo Wang , Tsui-Wei Weng

Although peer code review is widely adopted in both commercial and open source development, existing studies suggest that such code reviews often contain a significant amount of non-useful review comments. Unfortunately, to date, no tools…

Software Engineering · Computer Science 2018-07-13 Mohammad Masudur Rahman , Chanchal K. Roy , Raula G. Kula

LLM-based automated scoring approaches near-human performance, but scaling to new tasks remains bottlenecked by the per-item human configuration of upstream stages such as rubric construction. Human experts bypass this bottleneck through…

Computation and Language · Computer Science 2026-05-29 Yun Wang , Xin Xia , Xuansheng Wu , Xiaoming Zhai , Ninghao Liu

Recent reasoning-focused language models such as DeepSeek R1 and OpenAI o1 have demonstrated strong performance on structured reasoning benchmarks including GSM8K, MATH, and multi-hop question answering tasks. However, their performance…

Computation and Language · Computer Science 2026-03-31 Rahul Soni

Advancements in deep learning have significantly improved model performance across tasks involving code, text, and image processing. However, these models still exhibit notable mispredictions in real-world applications, even when trained on…

Software Engineering · Computer Science 2025-06-25 Ravishka Rathnasuriya

Evaluation and alignment pipelines for large language models increasingly rely on LLM-based judges, whose behavior is guided by natural-language rubrics and validated on benchmarks. We identify a previously under-recognized vulnerability in…

Cryptography and Security · Computer Science 2026-02-17 Ruomeng Ding , Yifei Pang , He Sun , Yizhong Wang , Zhiwei Steven Wu , Zhun Deng

Evaluating conversational systems in multi-turn settings remains a fundamental challenge. Conventional pipelines typically rely on manually defined rubrics and fixed conversational context$-$a static approach that limits coverage and fails…

Computation and Language · Computer Science 2026-01-21 Yunzhe Li , Richie Yueqi Feng , Tianxin Wei , Chin-Chia Hsu

We examine robust output feedback control of discrete-time nonlinear systems with bounded uncertainties affecting the dynamics and measurements. Specifically, we demonstrate how to construct semi-infinite programs that produce gains to…

Systems and Control · Electrical Eng. & Systems 2024-09-16 Jad Wehbeh , Eric C. Kerrigan

Uncertainty calibration is essential for the safe deployment of large language models (LLMs), particularly when users rely on verbalized confidence estimates. While prior work has focused on classifiers or short-form generation, confidence…

Computation and Language · Computer Science 2025-06-05 Chaeyun Jang , Moonseok Choi , Yegon Kim , Hyungi Lee , Juho Lee

Pre-trained code language models have achieved promising performance in code generation and improved the programming efficiency of human developers. However, their self-refinement capability is typically overlooked by the existing…

Software Engineering · Computer Science 2024-03-28 Yangruibo Ding , Marcus J. Min , Gail Kaiser , Baishakhi Ray

Peak performance metrics published by vendors often do not correspond to what can be achieved in practice. It is therefore of great interest to do extensive benchmarking on core applications and library routines. Since DGEMM is one of the…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-03-19 Jacob Odgård Tørring , Jan Christian Meyer , Anne C. Elster

Various techniques have been proposed to improve large language models (LLMs) adherence to formatting and instruction constraints. One of the most effective approaches involves utilizing high-quality data generated by powerful models.…

Computation and Language · Computer Science 2025-07-09 Sihyun Park

Tool-augmented large language models (LLMs) are usually trained with supervised imitation or coarse-grained reinforcement learning that optimizes single tool calls. Current self-reflection practices rely on heuristic prompts or one-way…

Computer Vision and Pattern Recognition · Computer Science 2026-04-16 Junhao Su , Yuanliang Wan , Junwei Yang , Hengyu Shi , Tianyang Han , Junfeng Luo , Yurui Qiu

Control flow in unstructured programs can be complex and dynamic, which makes static analysis difficult. Yet, automated reasoning about unstructured control flow is important when certifying properties of binary (machine) code in…

Programming Languages · Computer Science 2026-01-15 Andreas Lindner , Karl Palmskog , Scott Constable , Mads Dam , Roberto Guanciale , Hamed Nemati

Models such as finite state automata are widely used to abstract the behavior of software systems by capturing the sequences of events observable during their execution. Nevertheless, models rarely exist in practice and, when they do, get…

Software Engineering · Computer Science 2024-08-20 Donato Clun , Donghwan Shin , Antonio Filieri , Domenico Bianculli
‹ Prev 1 8 9 10 Next ›