English
Related papers

Related papers: Thinking vs. Doing: Agents that Reason by Scaling …

200 papers

Early artificial intelligence paradigms exhibited separated cognitive functions: Neural Networks focused on "perception-representation," Reinforcement Learning on "decision-making-behavior," and Symbolic AI on "knowledge-reasoning." With…

Artificial Intelligence · Computer Science 2026-01-07 Zhi Liu , Guangzhi Wang

Current test-time scaling (TTS) techniques enhance large language model (LLM) performance by allocating additional computation at inference time, yet they remain insufficient for agentic settings, where actions directly interact with…

Computation and Language · Computer Science 2026-02-04 Xingshan Zeng , Lingzhi Wang , Weiwen Liu , Liangyou Li , Yasheng Wang , Lifeng Shang , Xin Jiang , Qun Liu

Recent advances in autonomous LLM agents demonstrate their ability to improve performance through iterative interaction with the environment. We define this paradigm as Test-Time Improvement (TTI). However, the mechanisms under how and why…

Artificial Intelligence · Computer Science 2026-02-04 Hang Yan , Xinyu Che , Fangzhi Xu , Qiushi Sun , Zichen Ding , Kanzhi Cheng , Jian Zhang , Tao Qin , Jun Liu , Qika Lin

Graphical user interface (GUI) agents autonomously complete tasks across platforms (\eg, Linux) by sequentially decomposing user instructions into action proposals that iteratively interact with visual elements in the evolving environment.…

With the growing adoption of large language model agents in persistent real-world roles, they naturally encounter continuous streams of tasks. A key limitation, however, is their failure to learn from the accumulated interaction history,…

Advanced agentic intelligence is a prerequisite for deploying Large Language Models in practical, real-world applications. Diverse real-world APIs demand precise, robust function-calling intelligence, which needs agents to develop these…

Test-time scaling has become an effective paradigm for improving the reasoning ability of large language models by allocating additional computation during inference. Recent structured approaches have further advanced this paradigm by…

Artificial Intelligence · Computer Science 2026-05-20 George Wu , Nan Jing , Qing Yi , Chuan Hao , Ming Yang , Feng Chang , Yuan Wei , Jian Yang , Ran Tao , Bryan Dai

Test-time scaling has become a standard way to improve performance and boost reliability of neural network models. However, its behavior on agentic, multi-step tasks remains less well-understood: small per-step errors can compound over long…

Artificial Intelligence · Computer Science 2026-02-13 Nicholas Lee , Lutfi Eren Erdogan , Chris Joseph John , Surya Krishnapillai , Michael W. Mahoney , Kurt Keutzer , Amir Gholami

Test-time scaling (TTS) -- the dynamic allocation of compute during inference -- is a promising direction for improving reasoning in large language models (LLMs). However, a systematic comparison of well-known TTS strategies under identical…

Computation and Language · Computer Science 2025-12-02 Aradhye Agarwal , Ayan Sengupta , Tanmoy Chakraborty

Recent advancements in software engineering agents have demonstrated promising capabilities in automating program improvements. However, their reliance on closed-source or resource-intensive models introduces significant deployment…

Software Engineering · Computer Science 2025-04-09 Yingwei Ma , Yongbin Li , Yihong Dong , Xue Jiang , Rongyu Cao , Jue Chen , Fei Huang , Binhua Li

As large language models (LLMs) increasingly tackle complex reasoning tasks, test-time scaling has become critical for enhancing capabilities. However, in agentic scenarios with frequent tool calls, the traditional generation-length-based…

Computation and Language · Computer Science 2026-01-26 Yichuan Ma , Linyang Li , Yongkang chen , Peiji Li , Xiaozhe Li , Qipeng Guo , Dahua Lin , Kai Chen

LLM-based agents can autonomously accomplish complex tasks across various domains. However, to further cultivate capabilities such as adaptive behavior and long-term decision-making, training on static datasets built from human-level…

Machine Learning · Computer Science 2025-12-24 Yuchen Huang , Sijia Li , Minghao Liu , Wei Liu , Shijue Huang , Zhiyuan Fan , Hou Pong Chan , Yi R. Fung

Test-time scaling (TTS) enhances the performance of large language models (LLMs) by allocating additional compute resources during inference. However, existing research primarily investigates TTS in single-stage tasks; while many real-world…

Artificial Intelligence · Computer Science 2025-10-23 Fali Wang , Hui Liu , Zhenwei Dai , Jingying Zeng , Zhiwei Zhang , Zongyu Wu , Chen Luo , Zhen Li , Xianfeng Tang , Qi He , Suhang Wang

Scaling test time compute has shown remarkable success in improving the reasoning abilities of large language models (LLMs). In this work, we conduct the first systematic exploration of applying test-time scaling methods to language agents…

Web agents, which couple language models with browsing and tool-use capabilities, show promise as open web assistants. Yet progress is increasingly limited by the lack of scalable, process-level supervision. Existing benchmarks are largely…

Artificial Intelligence · Computer Science 2026-05-29 Tenghao Huang , Kung-Hsiang Huang , Prafulla Kumar Choubey , Yilun Zhou , Muhao Chen , Jonathan May , Chien-Sheng Wu

Current evaluations of agents remain centered around one-shot task completion, failing to account for the inherently iterative and collaborative nature of many real-world problems, where human goals are often underspecified and evolve. We…

Recent advancements in agentic test-time scaling allow models to gather environmental feedback before committing to final actions. A key limitation of existing methods is that they typically employ undifferentiated exploration strategies,…

Artificial Intelligence · Computer Science 2026-05-13 Xingyuan Hua , Sheng Yue , Ju Ren

Reasoning reinforcement learning (RL) has recently revealed a new scaling effect: test-time scaling. Thinking models such as R1 and o1 improve their reasoning accuracy at test time as the length of the reasoning context increases. However,…

Machine Learning · Computer Science 2025-11-24 Chao Yu , Qixin Tan , Jiaxuan Gao , Shi Yu , Hong Lu , Xinting Yang , Zelai Xu , Yu Wang , Yi Wu , Eugene Vinitsky

Test-Time Learning (TTL) enables language agents to iteratively refine their performance through repeated interactions with the environment at inference time. At the core of TTL is an adaptation policy that updates the actor policy based on…

Machine Learning · Computer Science 2026-04-03 Zhanzhi Lou , Hui Chen , Yibo Li , Qian Wang , Bryan Hooi

Scaling test-time computation improves performance across different tasks on large language models (LLMs), which has also been extended to tool-augmented agents. For these agents, scaling involves not only "thinking" in tokens but also…

‹ Prev 1 2 3 10 Next ›