Cognitive Models and AI Algorithms Provide Templates for Designing Language Agents
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918357215739904 |
|---|---|
| author | Liu, Ryan Arumugam, Dilip Zhang, Cedegao E. Escola, Sean Pitkow, Xaq Griffiths, Thomas L. |
| author_facet | Liu, Ryan Arumugam, Dilip Zhang, Cedegao E. Escola, Sean Pitkow, Xaq Griffiths, Thomas L. |
| contents | While contemporary large language models (LLMs) are increasingly capable in isolation, there are still many difficult problems that lie beyond the abilities of a single LLM. For such tasks, there is still uncertainty about how best to take many LLMs as parts and combine them into a greater whole. This position paper argues that potential blueprints for designing such modular language agents can be found in the existing literature on cognitive models and artificial intelligence (AI) algorithms. To make this point clear, we formalize the idea of an agent template that specifies roles for individual LLMs and how their functionalities should be composed. We then survey a variety of existing language agents in the literature and highlight their underlying templates derived directly from cognitive models or AI algorithms. By highlighting these designs, we aim to call attention to agent templates inspired by cognitive science and AI as a powerful tool for developing effective, interpretable language agents. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_22523 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Cognitive Models and AI Algorithms Provide Templates for Designing Language Agents Liu, Ryan Arumugam, Dilip Zhang, Cedegao E. Escola, Sean Pitkow, Xaq Griffiths, Thomas L. Artificial Intelligence Computation and Language Neurons and Cognition While contemporary large language models (LLMs) are increasingly capable in isolation, there are still many difficult problems that lie beyond the abilities of a single LLM. For such tasks, there is still uncertainty about how best to take many LLMs as parts and combine them into a greater whole. This position paper argues that potential blueprints for designing such modular language agents can be found in the existing literature on cognitive models and artificial intelligence (AI) algorithms. To make this point clear, we formalize the idea of an agent template that specifies roles for individual LLMs and how their functionalities should be composed. We then survey a variety of existing language agents in the literature and highlight their underlying templates derived directly from cognitive models or AI algorithms. By highlighting these designs, we aim to call attention to agent templates inspired by cognitive science and AI as a powerful tool for developing effective, interpretable language agents. |
| title | Cognitive Models and AI Algorithms Provide Templates for Designing Language Agents |
| topic | Artificial Intelligence Computation and Language Neurons and Cognition |
| url | https://arxiv.org/abs/2602.22523 |