English
Related papers

Related papers: Evaluation-driven Scaling for Scientific Discovery

200 papers

Large Language Models (LLMs) have enabled the emergence of LLM agents, systems capable of pursuing under-specified goals and adapting after deployment. Evaluating such agents is challenging because their behavior is open ended,…

Software Engineering · Computer Science 2025-11-18 Boming Xia , Qinghua Lu , Liming Zhu , Zhenchang Xing , Dehai Zhao , Hao Zhang

Logical reasoning remains a challenge for natural language processing, but it can be improved by training language models to mimic theorem provers on procedurally generated problems. Previous work used domain-specific proof generation…

Computation and Language · Computer Science 2024-06-18 Damien Sileo

Language models (LMs) perform well on standardized coding benchmarks but struggle with real-world software engineering tasks such as resolving GitHub issues in SWE-Bench, especially when model parameters are less than 100B. While smaller…

Computation and Language · Computer Science 2025-05-30 Guangtao Zeng , Maohao Shen , Delin Chen , Zhenting Qi , Subhro Das , Dan Gutfreund , David Cox , Gregory Wornell , Wei Lu , Zhang-Wei Hong , Chuang Gan

Recent advancements in Large Language Models (LLMs) have created new opportunities to enhance performance on complex reasoning tasks by leveraging test-time computation. However, existing scaling methods have key limitations: parallel…

Artificial Intelligence · Computer Science 2025-12-04 Jiefeng Chen , Jie Ren , Xinyun Chen , Chengrun Yang , Ruoxi Sun , Jinsung Yoon , Sercan Ö Arık

Large language models (LLMs) are increasingly used in scientific research and discovery, supporting tasks ranging from literature retrieval and synthesis to hypothesis generation, autonomous experimentation, and research evaluation.…

Digital Libraries · Computer Science 2026-05-13 Haoxuan Zhang , Ruochi Li , Yang Zhang , Ting Xiao , Jiangping Chen , Junhua Ding , Haihua Chen

Scaling test-time compute has driven the recent advances in the reasoning capabilities of large language models (LLMs), typically by allocating additional computation for more thorough exploration. However, increased compute often comes at…

Artificial Intelligence · Computer Science 2026-02-20 Mert Cemri , Nived Rajaraman , Rishabh Tiwari , Xiaoxuan Liu , Kurt Keutzer , Ion Stoica , Kannan Ramchandran , Ahmad Beirami , Ziteng Sun

Despite long-standing efforts in accelerating scientific discovery with AI, building AI co-scientists remains challenging due to limited high-quality data for training and evaluation. To tackle this data scarcity issue, we present AutoSDT,…

Test-Time Scaling (TTS) improves the reasoning performance of Large Language Models (LLMs) by allocating additional compute during inference. We conduct a structured survey of TTS methods and categorize them into sampling-based,…

Computation and Language · Computer Science 2025-06-06 Ho-Lam Chung , Teng-Yun Hsiao , Hsiao-Ying Huang , Chunerh Cho , Jian-Ren Lin , Zhang Ziwei , Yun-Nung Chen

Can the rapid advances in code generation, function calling, and data analysis using large language models (LLMs) help automate the search and verification of hypotheses purely from a set of provided datasets? To evaluate this question, we…

Scientific writing is an expert-domain task that demands deep domain knowledge, task-specific requirements and reasoning capabilities that leverage the domain knowledge to satisfy the task specifications. While scientific text generation…

Computation and Language · Computer Science 2026-04-20 Furkan Şahinuç , Subhabrata Dutta , Iryna Gurevych

The paper introduces a framework for the evaluation of the encoding of factual scientific knowledge, designed to streamline the manual evaluation process typically conducted by domain experts. Inferring over and extracting information from…

Computation and Language · Computer Science 2024-10-21 Magdalena Wysocka , Oskar Wysocki , Maxime Delmas , Vincent Mutel , Andre Freitas

The integration of experimental technologies with large language models (LLMs) is transforming scientific research. It positions AI as a versatile research assistant rather than a mere problem-solving tool. In the field of power systems,…

Computation and Language · Computer Science 2025-05-20 Mengshuo Jia , Zeyu Cui , Gabriela Hug

The promise of autonomous scientific discovery (ASD) hinges not only on answering questions, but also on knowing which questions to ask. Most recent works in ASD explore the use of large language models (LLMs) in goal-driven settings,…

Inference-time scaling can enhance the reasoning capabilities of large language models (LLMs) on complex problems that benefit from step-by-step problem solving. Although lengthening generated scratchpads has proven effective for…

Recent advances in multimodal large reasoning models (MLRMs) have substantially improved their ability to solve complex textual and visual tasks. However, these models tend to overthink on simple problems, producing unnecessarily lengthy…

Computation and Language · Computer Science 2025-10-10 Shuang Chen , Yue Guo , Yimeng Ye , Shijue Huang , Wenbo Hu , Haoxi Li , Manyuan Zhang , Jiayu Chen , Song Guo , Nanyun Peng

The effectiveness of large language models (LLMs) is closely tied to the design of prompts, making prompt optimization essential for enhancing their performance across a wide range of tasks. Many existing approaches to automating prompt…

Computation and Language · Computer Science 2025-04-08 Sarkar Snigdha Sarathi Das , Ryo Kamoi , Bo Pang , Yusen Zhang , Caiming Xiong , Rui Zhang

Test-time scaling is a promising new approach to language modeling that uses extra test-time compute to improve performance. Recently, OpenAI's o1 model showed this capability but did not publicly share its methodology, leading to many…

Achieving fully autonomous driving systems requires learning rational decisions in a wide span of scenarios, including safety-critical and out-of-distribution ones. However, such cases are underrepresented in real-world corpus collected by…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Haochen Tian , Tianyu Li , Haochen Liu , Jiazhi Yang , Yihang Qiu , Guang Li , Junli Wang , Yinfeng Gao , Zhang Zhang , Liang Wang , Hangjun Ye , Tieniu Tan , Long Chen , Hongyang Li

Scaling the amount of compute used to train language models has dramatically improved their capabilities. However, when it comes to inference, we often limit models to making only one attempt at a problem. Here, we explore inference compute…

Machine Learning · Computer Science 2025-01-03 Bradley Brown , Jordan Juravsky , Ryan Ehrlich , Ronald Clark , Quoc V. Le , Christopher Ré , Azalia Mirhoseini

As large language models (LLMs) are increasingly deployed to perform tasks with minimal human oversight, it is crucial that these models operate robustly. In particular, a model that can solve a given problem should not fail simply because…

Machine Learning · Computer Science 2026-05-18 Philipp Mondorf , Samuel J. Bell , Jesse Dodge , Dieuwke Hupkes