English
Related papers

Related papers: Agentic Scientific Simulation: Execution-Grounded …

200 papers

Existing LLM agent frameworks lack formal semantics: there is no principled way to determine whether an agent configuration is well-formed or will terminate. We present $\lambda_A$, a typed lambda calculus for agent composition that extends…

Programming Languages · Computer Science 2026-04-15 Qin Liu

Evaluating recommender systems remains challenging due to the gap between offline metrics and real user behavior, as well as the scarcity of interaction data. Recent work explores large language model (LLM) agents as synthetic users, yet…

Information Retrieval · Computer Science 2026-01-06 Nicolas Bougie , Gian Maria Marconi , Tony Yip , Narimasa Watanabe

Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making. While large language models (LLMs) demonstrate strong reasoning capabilities in closed-world settings, they struggle in open-ended and…

This article outlines a method for automatically generating models of dynamic decision-making that both have strong predictive power and are interpretable in human terms. This is useful for designing empirically grounded agent-based…

Machine Learning · Statistics 2016-11-17 John J. Nay , Jonathan M. Gilligan

In this work, we introduce MedAgentSim, an open-source simulated clinical environment with doctor, patient, and measurement agents designed to evaluate and enhance LLM performance in dynamic diagnostic settings. Unlike prior approaches, our…

Computation and Language · Computer Science 2025-10-02 Mohammad Almansoori , Komal Kumar , Hisham Cholakkal

Scientific Machine Learning (SciML) integrates data-driven inference with physical modeling to solve complex problems in science and engineering. However, the design of SciML architectures, loss formulations, and training strategies remains…

Artificial Intelligence · Computer Science 2026-02-17 Qile Jiang , George Karniadakis

The dominant paradigm for building LLM based agents is the Agent Loop, an iterative cycle where a single language model decides what to do next by reading an ever growing context window. This paradigm has three structural weaknesses:…

Artificial Intelligence · Computer Science 2026-04-14 Hu Wei

Building software that is correct by construction is a long-standing goal in software engineering, as it ensures reliability during design and development rather than after deployment. Formal methods realize this vision by enabling the…

Software Engineering · Computer Science 2026-05-19 Hongshu Wang , Xinyue Zuo , Yuhan Sun , Qin Li , Yamine Ait Ameur , Jin Song Dong

LLM-based agentic systems are rapidly evolving to perform complex autonomous tasks through dynamic tool invocation, stateful memory management, and multi-agent collaboration. However, this semantics-driven execution paradigm creates a…

Artificial Intelligence · Computer Science 2026-05-11 Chaofan Li , Lyuye Zhang , Jintao Zhai , Siyue Feng , Xichun Yang , Huahao Wang , Shihan Dou , Yu Ji , Yutao Hu , Yueming Wu , Yang Liu , Deqing Zou

Agentic discovery has shown that LLM-driven search can find novel algorithms, designs, and code under benchmark conditions. Translating the paradigm to multi-system data backends surfaces a harder problem: the search space is heterogeneous,…

Artificial Intelligence · Computer Science 2026-05-27 Shanshan Ye , Duo Lu

Historically, scientific discovery has been a lengthy and costly process, demanding substantial time and resources from initial conception to final results. To accelerate scientific discovery, reduce research costs, and improve research…

Human-Computer Interaction · Computer Science 2025-06-18 Samuel Schmidgall , Yusheng Su , Ze Wang , Ximeng Sun , Jialian Wu , Xiaodong Yu , Jiang Liu , Michael Moor , Zicheng Liu , Emad Barsoum

Recent progress in large language model (LLM) agents has largely focused on embedding self-improvement mechanisms inside the agent or searching over many concurrent variants. While these approaches can raise aggregate scores, they often…

Artificial Intelligence · Computer Science 2026-01-09 Di Zhang

The control of complex laboratory instrumentation often requires significant programming expertise, creating a barrier for researchers lacking computational skills. This work explores the potential of large language models (LLMs), such as…

Artificial Intelligence · Computer Science 2026-04-07 Yong Xie , Kexin He , Andres Castellanos-Gomez

Large language models (LLMs) can now synthesize non-trivial executable code from textual descriptions, raising an important question: can LLMs reliably implement agent-based models from standardized specifications in a way that supports…

Software Engineering · Computer Science 2026-05-01 Nuno Fachada , Daniel Fernandes , Carlos M. Fernandes , João P. Matos-Carvalho

There are two main barriers to using large language models (LLMs) in clinical reasoning. Firstly, while LLMs exhibit significant promise in Natural Language Processing (NLP) tasks, their performance in complex reasoning and planning falls…

Artificial Intelligence · Computer Science 2024-12-31 Shengxin Hong , Liang Xiao , Xin Zhang , Jianxia Chen

Recent work has used LLM agents to reproduce empirical social science results with access to both the data and code. We broaden this scope by asking: Can they reproduce results given only a paper's methods description and original data? We…

Artificial Intelligence · Computer Science 2026-04-27 Benjamin Kohler , David Zollikofer , Johanna Einsiedler , Alexander Hoyle , Elliott Ash

Reliable decision support in nuclear engineering requires traceable, domain-grounded knowledge retrieval, yet safety and risk analysis workflows remain hampered by fragmented documentation and hallucination when use pre-trained large…

Information Retrieval · Computer Science 2026-04-28 Zavier Ndum Ndum , Jian Tao , John Ford , Mansung Yim , Yang Liu

The advancement of data-driven materials science is currently constrained by a fundamental bottleneck: the vast majority of historical experimental data remains locked within the unstructured text and rasterized figures of legacy scientific…

Databases · Computer Science 2026-02-04 Yue Wu , Tianhao Su , Shunbo Hu , Deng Pan

We introduce CausaLab, a scalable environment for evaluating interactive causal discovery by LLM agents. Unlike prior evaluations, CausaLab evaluates both whether an agent can solve a problem using causal evidence and whether its answer is…

Artificial Intelligence · Computer Science 2026-05-29 Junlin Yang , Dylan Zhang , Xiangchen Song , Qirun Dai , Xiao Liu , Yuen Chen , Aniket Vashishtha , Jing Shi , Chenhao Tan , Hao Peng

Clinical trials are critical for advancing medical treatments but remain prohibitively expensive and time-consuming. Accurate prediction of clinical trial outcomes can significantly reduce research and development costs and accelerate drug…

Machine Learning · Computer Science 2025-06-06 Fengze Liu , Haoyu Wang , Joonhyuk Cho , Dan Roth , Andrew W. Lo
‹ Prev 1 8 9 10 Next ›