paper-with-me

홈 › Papers

Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interface

2024-09-30 · Wenyue Hua, Mengting Wan, Shashank Vadrevu, Ryan Nadel, Yongfeng Zhang, Chi Wang

Agents, as user-centric tools, are increasingly deployed for human task delegation, assisting with a broad spectrum of requests by generating thoughts, engaging with user proxies, and producing action plans. However, agents based on large language models (LLMs) often face substantial planning latency due to two primary factors: the efficiency limitations of the underlying LLMs due to their large size and high demand, and the structural complexity of the agents due to the extensive generation of intermediate thoughts to produce the final output. Given that inefficiency in service provision can undermine the value of automation for users, this paper presents a human-centered efficient agent planning method -- Interactive Speculative Planning -- aiming at enhancing the efficiency of agent planning through both system design and human-AI interaction. Our approach advocates for the co-design of the agent system and user interface, underscoring the importance of an agent system that can fluidly manage user interactions and interruptions. By integrating human interruptions as a fundamental component of the system, we not only make it more user-centric but also expedite the entire process by leveraging human-in-the-loop interactions to provide accurate intermediate steps. Code and data will be released.

📄 PDF Abstract BibTeX arXiv:2410.00079

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Golden Queue Managers 설명 없음

Similar Papers 제목 키워드 기반

Dynamic Speculative Agent Planning

2025-09-02 · Yilin Guan, Qingfeng Lan, Sun Fei, Dujian Ding 외 arxiv

Despite their remarkable success in complex tasks propelling widespread adoption, large language-model-based agents still face critical deployment challenges due to prohibitive latency and inference costs. While recent w…

Reinforcement Learning

What Limits Agentic Systems Efficiency?

2025-10-18 · Song Bian, Minghao Yan, Anand Jayarajan, Gennady Pekhimenko 외 arxiv

Large Language Models (LLMs), such as OpenAI-o1 and DeepSeek-R1, have demonstrated strong reasoning capabilities. To further enhance LLM capabilities, recent agentic systems, such as Deep Research, incorporate web intera…

MPO: Boosting LLM Agents with Meta Plan Optimization

2025-03-04 · Weimin Xiong, YiFan Song, Qingxiu Dong, Bingchan Zhao 외

Recent advancements in large language models (LLMs) have enabled LLM-based agents to successfully tackle interactive planning tasks. However, despite their successes, existing approaches often suffer from planning halluc…

Speculative Actions: A Lossless Framework for Faster Agentic Systems

2025-10-05 · Naimeng Ye, Arnav Ahuja, Georgios Liargkovas, Yunan Lu 외 arxiv

AI agents are increasingly deployed in complex, interactive environments, yet their runtime remains a major bottleneck for training, evaluation, and real-world use. Typical agent behavior unfolds sequentially, with each …

SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning

2026-03-24 · Haoyu Huang, Jinfa Huang, Zhongwei Wan, Xiawu Zheng 외 arxiv

Agentic multimodal large language models (MLLMs) (e.g., OpenAI o3 and Gemini Agentic Vision) achieve remarkable reasoning capabilities through iterative visual tool invocation. However, the cascaded perception, reasoning…