Matches in SemOpenAlex for { <https://semopenalex.org/work/W4379539325> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4379539325 abstract "Auto-GPT is an autonomous agent that leverages recent advancements in adapting Large Language Models (LLMs) for decision-making tasks. While there has been a growing interest in Auto-GPT stypled agents, questions remain regarding the effectiveness and flexibility of Auto-GPT in solving real-world decision-making tasks. Its limited capability for real-world engagement and the absence of benchmarks contribute to these uncertainties. In this paper, we present a comprehensive benchmark study of Auto-GPT styled agents in decision-making tasks that simulate real-world scenarios. Our aim is to gain deeper insights into this problem and understand the adaptability of GPT-based agents. We compare the performance of popular LLMs such as GPT-4, GPT-3.5, Claude, and Vicuna in Auto-GPT styled decision-making tasks. Furthermore, we introduce the Additional Opinions algorithm, an easy and effective method that incorporates supervised/imitation-based learners into the Auto-GPT scheme. This approach enables lightweight supervised learning without requiring fine-tuning of the foundational LLMs. We demonstrate through careful baseline comparisons and ablation studies that the Additional Opinions algorithm significantly enhances performance in online decision-making benchmarks, including WebShop and ALFWorld." @default.
- W4379539325 created "2023-06-07" @default.
- W4379539325 creator A5000296482 @default.
- W4379539325 creator A5052450297 @default.
- W4379539325 creator A5079019876 @default.
- W4379539325 date "2023-06-03" @default.
- W4379539325 modified "2023-09-25" @default.
- W4379539325 title "Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions" @default.
- W4379539325 doi "https://doi.org/10.48550/arxiv.2306.02224" @default.
- W4379539325 hasPublicationYear "2023" @default.
- W4379539325 type Work @default.
- W4379539325 citedByCount "0" @default.
- W4379539325 crossrefType "posted-content" @default.
- W4379539325 hasAuthorship W4379539325A5000296482 @default.
- W4379539325 hasAuthorship W4379539325A5052450297 @default.
- W4379539325 hasAuthorship W4379539325A5079019876 @default.
- W4379539325 hasBestOaLocation W43795393251 @default.
- W4379539325 hasConcept C105795698 @default.
- W4379539325 hasConcept C119857082 @default.
- W4379539325 hasConcept C126388530 @default.
- W4379539325 hasConcept C13280743 @default.
- W4379539325 hasConcept C134306372 @default.
- W4379539325 hasConcept C154945302 @default.
- W4379539325 hasConcept C15744967 @default.
- W4379539325 hasConcept C177606310 @default.
- W4379539325 hasConcept C185798385 @default.
- W4379539325 hasConcept C18903297 @default.
- W4379539325 hasConcept C205649164 @default.
- W4379539325 hasConcept C2780598303 @default.
- W4379539325 hasConcept C33923547 @default.
- W4379539325 hasConcept C41008148 @default.
- W4379539325 hasConcept C77618280 @default.
- W4379539325 hasConcept C77805123 @default.
- W4379539325 hasConcept C86803240 @default.
- W4379539325 hasConceptScore W4379539325C105795698 @default.
- W4379539325 hasConceptScore W4379539325C119857082 @default.
- W4379539325 hasConceptScore W4379539325C126388530 @default.
- W4379539325 hasConceptScore W4379539325C13280743 @default.
- W4379539325 hasConceptScore W4379539325C134306372 @default.
- W4379539325 hasConceptScore W4379539325C154945302 @default.
- W4379539325 hasConceptScore W4379539325C15744967 @default.
- W4379539325 hasConceptScore W4379539325C177606310 @default.
- W4379539325 hasConceptScore W4379539325C185798385 @default.
- W4379539325 hasConceptScore W4379539325C18903297 @default.
- W4379539325 hasConceptScore W4379539325C205649164 @default.
- W4379539325 hasConceptScore W4379539325C2780598303 @default.
- W4379539325 hasConceptScore W4379539325C33923547 @default.
- W4379539325 hasConceptScore W4379539325C41008148 @default.
- W4379539325 hasConceptScore W4379539325C77618280 @default.
- W4379539325 hasConceptScore W4379539325C77805123 @default.
- W4379539325 hasConceptScore W4379539325C86803240 @default.
- W4379539325 hasLocation W43795393251 @default.
- W4379539325 hasOpenAccess W4379539325 @default.
- W4379539325 hasPrimaryLocation W43795393251 @default.
- W4379539325 hasRelatedWork W1911385653 @default.
- W4379539325 hasRelatedWork W1966275857 @default.
- W4379539325 hasRelatedWork W1994643058 @default.
- W4379539325 hasRelatedWork W2159871347 @default.
- W4379539325 hasRelatedWork W2250134121 @default.
- W4379539325 hasRelatedWork W2358275981 @default.
- W4379539325 hasRelatedWork W2382984733 @default.
- W4379539325 hasRelatedWork W3123829044 @default.
- W4379539325 hasRelatedWork W3146459634 @default.
- W4379539325 hasRelatedWork W4246259489 @default.
- W4379539325 isParatext "false" @default.
- W4379539325 isRetracted "false" @default.
- W4379539325 workType "article" @default.