Results 311 to 320 of about 9,013,912 (355)

R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model

arXiv.org
Recently DeepSeek R1 demonstrated how reinforcement learning with simple rule-based incentives can enable autonomous development of complex reasoning in large language models, characterized by the"aha moment", in which the model manifest self-reflection ...
Hengguang Zhou, Xirui Li, Ruochen Wang, Minhao Cheng, Tianyi Zhou, Cho-Jui Hsieh   +5 more
semanticscholar   +1 more source

Model-Based Reasoning in SSF ECLSS

SAE Technical Paper Series, 1992
<div class="htmlview paragraph">The interacting processes and reconfigurable subsystems of the Space Station Freedom Environmental Control and Life Support System (ECLSS) present a tremendous technical challenge to Freedom's crew and ground support. E<span class="small-caps">CLSS</span> operation and problem analysis is time-consuming
J. Kellie Miller, George P. W. Williams
openaire   +1 more source

Scaling Large-Language-Model-based Multi-Agent Collaboration

International Conference on Learning Representations
Recent breakthroughs in large language model-driven autonomous agents have revealed that multi-agent collaboration often surpasses each individual through collective reasoning.
Cheng Qian, Zihao Xie, Yifei Wang, Wei Liu, Yufan Dang, Zhuoyun Du, Weize Chen, Cheng Yang, Zhiyuan Liu, Maosong Sun   +9 more
semanticscholar   +1 more source

A Survey on Large Language Model-Based Game Agents

arXiv.org
Game environments provide rich, controllable settings that stimulate many aspects of real-world complexity. As such, game agents offer a valuable testbed for exploring capabilities relevant to Artificial General Intelligence.
Sihao Hu, Tiansheng Huang, Fatih Ilhan, S. Tekin, Gaowen Liu, R. Kompella, Ling Liu   +6 more
semanticscholar   +1 more source

AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning

arXiv.org
Recent advancements in Vision-Language-Action (VLA) models have shown promise for end-to-end autonomous driving by leveraging world knowledge and reasoning capabilities. However, current VLA models often struggle with physically infeasible action outputs,
Zewei Zhou, Tianhui Cai, Seth Z. Zhao, Yun Zhang, Zhiyu Huang, Bolei Zhou, Jiaqi Ma   +6 more
semanticscholar   +1 more source

Design Patterns for Model-Based Reasoning

2017
The aspects of model-based reasoning serve as the Focal knowledge, skills and abilities (KSAs) of the design patterns. They highlight distinct aspects of model-based reasoning in a way that supports either focused tasks (building on one or a few design patterns) or more extensive investigations (building jointly on several design patterns).
Robert J. Mislevy, Geneva Haertel, Michelle Riconscente, Daisy Wise Rutstein, Cindy Ziker   +4 more
openaire   +1 more source

GuardReasoner: Towards Reasoning-based LLM Safeguards

arXiv.org
As LLMs increasingly impact safety-critical applications, ensuring their safety using guardrails remains a key challenge. This paper proposes GuardReasoner, a new safeguard for LLMs, by guiding the guard model to learn to reason.
Yue Liu, Hongcheng Gao, Shengfang Zhai, Jun Xia, Zhengyu Hu, Tianyi Wu, Zhiwei Xue, Yulin Chen, Kenji Kawaguchi, Jiaheng Zhang, Bryan Hooi   +10 more
semanticscholar   +1 more source

Model-Based Reasoning in the Social Sciences

2017
Social scientists use different types of model to reason about social objects and to study social phenomena. In this chapter, I provide an overview of various forms of model-based reasoning in social research, especially quantitative and qualitative.
openaire   +3 more sources

Model-based reasoning for fault isolation

[1988] Proceedings. The Fourth Conference on Artificial Intelligence Applications, 2003
The author attempts to explore the promise or limitations of a model-based reasoning approach for a system of practical size and complexity. Specifically, a target system was chosen which contained the order of a hundred components and featured complex feedback looping. A prototype fault isolation system has been developed for the system.
openaire   +1 more source

Constraining model-based reasoning using contexts

Proceedings IEEE/WIC International Conference on Web Intelligence (WI 2003), 2004
Web-based customer service has become a norm of business practice with increasing emphasis on modeling customer needs and providing them with targeted or personalized service solutions in a timely fashion. Almost all the commercial Web service systems adopt some kind of simple customer segmentation models and shallow pattern matching or rule-based ...
L. Gong, D. Riecken
openaire   +1 more source