Web agents based on large language models (LLMs) rely on observations of web pages -- commonly represented as HTML -- as the basis for identifying available actions and planning subsequent steps. Prior work has treated the verbosity of HTML as an obstacle to performance and adopted observation reduction as a standard practice. We revisit this trend and demonstrate that the optimal observation representation depends on model capability and thinking token budget: (1) compact observations (accessibility trees) are preferable for lower-capability models, while detailed observations (HTML) are advantageous for higher-capability models; moreover, increasing thinking tokens further amplifies the benefit of HTML. (2) Our error analysis suggests that higher-capability models exploit layout information in HTML for better action grounding, while lower-capability models suffer from increased hallucination under longer inputs. We also find that incorporating observation history improves performance across most models and settings, and a diff-based representation offers a token-efficient alternative. Based on these findings, we suggest practical guidelines: adaptively select observation representations based on model capability and thinking token budget, and incorporate observation history using diff-based representations.
StreamingThinker: Large Language Models Can Think While Reading
Shanghai Jiao Tong University(上海交通大学);Eastern Institute of Technology, Ningbo(宁波东部技术研究院);Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative, Institute of Digital Twin(宁波空间智能与数字衍生关键实验室,数字孪生研究院);Hong Kong Polytechnic University(香港理工大学);Munich Center for Machine Learning, LMU(慕尼黑机器学习中心,莱茵-慕尼黑大学)
PRefLexOR: Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning and Agentic Thinking
Center for Computational Science and Engineering(计算科学与工程中心);Schmarzman College of Computing(施马茨曼计算学院);Laboratory for Atomistic and Molecular Mechanics (LAMM)(原子与分子力学实验室);Massachusetts Institute of Technology(麻省理工学院)
Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space
University of California, Santa Barbara(加州大学圣芭芭拉分校);University of California, Santa Cruz(加州大学圣克ruz分校);University of California, Los Angeles(加州大学洛杉矶分校);Purdue University(普渡大学);LMSYS Org(LMSYS组织);Microsoft(微软)
Entertain, then Cancel: How Thinking Makes Reasoning Models Read Some and Or Literally
The Hong Kong University of Science and Technology(香港科技大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Peking University(北京大学)
Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs
Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);Tübingen AI Center(图宾根人工智能中心);ETH Zurich(苏黎世联邦理工学院);University Hospital Tübingen(图宾根大学医院);University of Tübingen(图宾根大学);ELLIS Institute Tübingen(图宾根ELLIS研究所)