PAFFA: Premeditated Actions For Fast Agents

Wedi'i Gadw mewn:
Manylion Llyfryddiaeth
Cyhoeddwyd yn:arXiv.org (Dec 10, 2024), p. n/a
Prif Awdur: Shambhavi Krishna
Awduron Eraill: Chen, Zheng, Kumar, Vaibhav, Huang, Xiaojiang, Li, Yingjie, Yang, Fan, Li, Xiang
Cyhoeddwyd:
Cornell University Library, arXiv.org
Pynciau:
Mynediad Ar-lein:Citation/Abstract
Full text outside of ProQuest
Tagiau: Ychwanegu Tag
Dim Tagiau, Byddwch y cyntaf i dagio'r cofnod hwn!

MARC

LEADER 00000nab a2200000uu 4500
001 3143450801
003 UK-CbPIL
022 |a 2331-8422 
035 |a 3143450801 
045 0 |b d20241210 
100 1 |a Shambhavi Krishna 
245 1 |a PAFFA: Premeditated Actions For Fast Agents 
260 |b Cornell University Library, arXiv.org  |c Dec 10, 2024 
513 |a Working Paper 
520 3 |a Modern AI assistants have made significant progress in natural language understanding and API/tool integration, with emerging efforts to incorporate diverse interfaces (such as Web interfaces) for enhanced scalability and functionality. However, current approaches that heavily rely on repeated LLM-driven HTML parsing are computationally expensive and error-prone, particularly when handling dynamic web interfaces and multi-step tasks. To overcome these challenges, we introduce PAFFA (Premeditated Actions For Fast Agents), a framework designed to enhance web interaction capabilities through an Action API Library of reusable, verified browser interaction functions. By pre-computing interaction patterns and employing two core methodologies - "Dist-Map" for task-agnostic element distillation and "Unravel" for incremental page-wise exploration - PAFFA reduces inference calls by 87% while maintaining robust performance even as website structures evolve. This framework accelerates multi-page task execution and offers a scalable solution to advance autonomous web agent research. 
653 |a Application programming interface 
700 1 |a Chen, Zheng 
700 1 |a Kumar, Vaibhav 
700 1 |a Huang, Xiaojiang 
700 1 |a Li, Yingjie 
700 1 |a Yang, Fan 
700 1 |a Li, Xiang 
773 0 |t arXiv.org  |g (Dec 10, 2024), p. n/a 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3143450801/abstract/embedded/ZKJTFFSVAI7CB62C?source=fedsrch 
856 4 0 |3 Full text outside of ProQuest  |u http://arxiv.org/abs/2412.07958