Formally Specifying the High-Level Behavior of LLM-Based Agents
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914650424082432 |
|---|---|
| author | Crouse, Maxwell Abdelaziz, Ibrahim Astudillo, Ramon Basu, Kinjal Dan, Soham Kumaravel, Sadhana Fokoue, Achille Kapanipathi, Pavan Roukos, Salim Lastras, Luis |
| author_facet | Crouse, Maxwell Abdelaziz, Ibrahim Astudillo, Ramon Basu, Kinjal Dan, Soham Kumaravel, Sadhana Fokoue, Achille Kapanipathi, Pavan Roukos, Salim Lastras, Luis |
| contents | Autonomous, goal-driven agents powered by LLMs have recently emerged as promising tools for solving challenging problems without the need for task-specific finetuned models that can be expensive to procure. Currently, the design and implementation of such agents is ad hoc, as the wide variety of tasks that LLM-based agents may be applied to naturally means there can be no one-size-fits-all approach to agent design. In this work we aim to alleviate the difficulty of designing and implementing new agents by proposing a minimalistic generation framework that simplifies the process of building agents. The framework we introduce allows the user to define desired agent behaviors in a high-level, declarative specification that is then used to construct a decoding monitor which guarantees the LLM will produce an output exhibiting the desired behavior. Our declarative approach, in which the behavior is described without concern for how it should be implemented or enforced, enables rapid design, implementation, and experimentation with different LLM-based agents. We demonstrate how the proposed framework can be used to implement recent LLM-based agents (e.g., ReACT), and show how the flexibility of our approach can be leveraged to define a new agent with more complex behavior, the Plan-Act-Summarize-Solve (PASS) agent. Lastly, we demonstrate that our method outperforms other agents on multiple popular reasoning-centric question-answering benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_08535 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Formally Specifying the High-Level Behavior of LLM-Based Agents Crouse, Maxwell Abdelaziz, Ibrahim Astudillo, Ramon Basu, Kinjal Dan, Soham Kumaravel, Sadhana Fokoue, Achille Kapanipathi, Pavan Roukos, Salim Lastras, Luis Artificial Intelligence Computation and Language Autonomous, goal-driven agents powered by LLMs have recently emerged as promising tools for solving challenging problems without the need for task-specific finetuned models that can be expensive to procure. Currently, the design and implementation of such agents is ad hoc, as the wide variety of tasks that LLM-based agents may be applied to naturally means there can be no one-size-fits-all approach to agent design. In this work we aim to alleviate the difficulty of designing and implementing new agents by proposing a minimalistic generation framework that simplifies the process of building agents. The framework we introduce allows the user to define desired agent behaviors in a high-level, declarative specification that is then used to construct a decoding monitor which guarantees the LLM will produce an output exhibiting the desired behavior. Our declarative approach, in which the behavior is described without concern for how it should be implemented or enforced, enables rapid design, implementation, and experimentation with different LLM-based agents. We demonstrate how the proposed framework can be used to implement recent LLM-based agents (e.g., ReACT), and show how the flexibility of our approach can be leveraged to define a new agent with more complex behavior, the Plan-Act-Summarize-Solve (PASS) agent. Lastly, we demonstrate that our method outperforms other agents on multiple popular reasoning-centric question-answering benchmarks. |
| title | Formally Specifying the High-Level Behavior of LLM-Based Agents |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2310.08535 |