PAFFA: Premeditated Actions For Fast Agents
Wedi'i Gadw mewn:
| Cyhoeddwyd yn: | arXiv.org (Dec 10, 2024), p. n/a |
|---|---|
| Prif Awdur: | |
| Awduron Eraill: | , , , , , |
| Cyhoeddwyd: |
Cornell University Library, arXiv.org
|
| Pynciau: | |
| Mynediad Ar-lein: | Citation/Abstract Full text outside of ProQuest |
| Tagiau: |
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 |