Tulip Agent -- Enabling LLM-Based Agents to Solve Tasks Using Large Tool Libraries
We introduce tulip agent, an architecture for autonomous LLM-based agents with Create, Read, Update, and Delete access to a tool library containing a potentially large number of tools. In contrast to state-of-the-art implementations, tulip agent does not encode the descriptions of all available tool...
Saved in:
| Main Authors | , , , |
|---|---|
| Format | Journal Article |
| Language | English |
| Published |
31.07.2024
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | We introduce tulip agent, an architecture for autonomous LLM-based agents
with Create, Read, Update, and Delete access to a tool library containing a
potentially large number of tools. In contrast to state-of-the-art
implementations, tulip agent does not encode the descriptions of all available
tools in the system prompt, which counts against the model's context window, or
embed the entire prompt for retrieving suitable tools. Instead, the tulip agent
can recursively search for suitable tools in its extensible tool library,
implemented exemplarily as a vector store. The tulip agent architecture
significantly reduces inference costs, allows using even large tool libraries,
and enables the agent to adapt and extend its set of tools. We evaluate the
architecture with several ablation studies in a mathematics context and
demonstrate its generalizability with an application to robotics. A reference
implementation and the benchmark are available at
github.com/HRI-EU/tulip_agent. |
|---|---|
| AbstractList | We introduce tulip agent, an architecture for autonomous LLM-based agents
with Create, Read, Update, and Delete access to a tool library containing a
potentially large number of tools. In contrast to state-of-the-art
implementations, tulip agent does not encode the descriptions of all available
tools in the system prompt, which counts against the model's context window, or
embed the entire prompt for retrieving suitable tools. Instead, the tulip agent
can recursively search for suitable tools in its extensible tool library,
implemented exemplarily as a vector store. The tulip agent architecture
significantly reduces inference costs, allows using even large tool libraries,
and enables the agent to adapt and extend its set of tools. We evaluate the
architecture with several ablation studies in a mathematics context and
demonstrate its generalizability with an application to robotics. A reference
implementation and the benchmark are available at
github.com/HRI-EU/tulip_agent. |
| Author | Eggert, Julian Ocker, Felix Gienger, Michael Tanneberg, Daniel |
| Author_xml | – sequence: 1 givenname: Felix surname: Ocker fullname: Ocker, Felix – sequence: 2 givenname: Daniel surname: Tanneberg fullname: Tanneberg, Daniel – sequence: 3 givenname: Julian surname: Eggert fullname: Eggert, Julian – sequence: 4 givenname: Michael surname: Gienger fullname: Gienger, Michael |
| BackLink | https://doi.org/10.48550/arXiv.2407.21778$$DView paper in arXiv |
| BookMark | eNrjYmDJy89LZWCQNDTQM7EwNTXQTyyqyCzTMzIxMNczMjQ3t-BkCAopzcksUHBMT80rUdDVVXDNS0zKycxLV_Dx8dV1SixOTYHIFSuU5CsE5-eUpSqEJBZnFyuEFoNVJRalA0Xy83MUfDKTihKLMlOLeRhY0xJzilN5oTQ3g7yba4izhy7Y9viCoszcxKLKeJAr4sGuMCasAgDIKD0e |
| ContentType | Journal Article |
| Copyright | http://arxiv.org/licenses/nonexclusive-distrib/1.0 |
| Copyright_xml | – notice: http://arxiv.org/licenses/nonexclusive-distrib/1.0 |
| DBID | AKY GOX |
| DOI | 10.48550/arxiv.2407.21778 |
| DatabaseName | arXiv Computer Science arXiv.org |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: GOX name: arXiv.org url: http://arxiv.org/find sourceTypes: Open Access Repository |
| DeliveryMethod | fulltext_linktorsrc |
| ExternalDocumentID | 2407_21778 |
| GroupedDBID | AKY GOX |
| ID | FETCH-arxiv_primary_2407_217783 |
| IEDL.DBID | GOX |
| IngestDate | Fri Aug 02 18:12:52 EDT 2024 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | false |
| IsScholarly | false |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-arxiv_primary_2407_217783 |
| OpenAccessLink | https://arxiv.org/abs/2407.21778 |
| ParticipantIDs | arxiv_primary_2407_21778 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-07-31 |
| PublicationDateYYYYMMDD | 2024-07-31 |
| PublicationDate_xml | – month: 07 year: 2024 text: 2024-07-31 day: 31 |
| PublicationDecade | 2020 |
| PublicationYear | 2024 |
| Score | 3.8547044 |
| SecondaryResourceType | preprint |
| Snippet | We introduce tulip agent, an architecture for autonomous LLM-based agents
with Create, Read, Update, and Delete access to a tool library containing a... |
| SourceID | arxiv |
| SourceType | Open Access Repository |
| SubjectTerms | Computer Science - Artificial Intelligence Computer Science - Robotics |
| Title | Tulip Agent -- Enabling LLM-Based Agents to Solve Tasks Using Large Tool Libraries |
| URI | https://arxiv.org/abs/2407.21778 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwdVxLT8MwDLa2nbggEKDx9oFreLRpkx4H2phQBxIUqbcqaRppoqLT2k38fPLYBJddY8uyksP3OfZngJtSW0VjGZOQypJQyRQRhocTg1VUqaRkKrFC4dlrPP2kL3mU9wC3Whix_Jmv_X5g2d7ZcuPWkGbG-9APAjuy9fyW--akW8W18f_zMxzTHf0DickB7G_YHY78cxxCr_o-gvdsVc8XOLIiJiQEx1auZBAD03RGHg2KKG9rsWvwo6nXFWai_WrRtfMxtbPamDVNjem2tj2G68k4e5oSl0Wx8CsjCptg4RIMT2BgCvtqCJhwLfhDyWRFQ8qk4HGsNUsizcN7GcTRKQx3RTnbbTqHvcAAr_9_vIBBt1xVlwY4O3nlbu8XIMZxKg |
| link.rule.ids | 228,230,783,888 |
| linkProvider | Cornell University |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Tulip+Agent+--+Enabling+LLM-Based+Agents+to+Solve+Tasks+Using+Large+Tool+Libraries&rft.au=Ocker%2C+Felix&rft.au=Tanneberg%2C+Daniel&rft.au=Eggert%2C+Julian&rft.au=Gienger%2C+Michael&rft.date=2024-07-31&rft_id=info:doi/10.48550%2Farxiv.2407.21778&rft.externalDocID=2407_21778 |