Cognitive Architectures for Language Agents

By Theodore R. Sumers, Shunyu Yao, Karthik Narasimhan, Thomas L. Griffiths. Trans. Mach. Learn. Res., 2023

440 citations recorded by the source corpus.

Recent efforts have augmented large language models (LLMs) with external resources (e.g., the Internet) or internal control flows (e.g., prompt chaining) for tasks requiring grounding or reasoning, leading to a new class of language agents. While these agents have achieved substantial empirical success, we lack a systematic framework to organize existing agents and plan future developments. In this paper, we draw on the rich history of cognitive science and symbolic artificial intelligence to propose Cognitive Architectures for Language Agents (CoALA). CoALA describes a language agent with modular memory components, a structured action space to interact with internal memory and external environments, and a generalized decision-making process to choose actions. We use CoALA to retrospectively survey and organize a large body of recent work, and prospectively identify actionable directions towards more capable agents. Taken together, CoALA contextualizes today's language agents within the broader history of AI and outlines a path towards language-based general intelligence.

Subfields: Artificial Intelligence, Cultural Studies

View Paper: https://www.semanticscholar.org/paper/e4bb1b1f97711a7634bf4bff72c56891be2222e6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Cultural Studies

Citations in the corpus

Building Cooperative Embodied Agents Modularly with Large Language Models (2023, background): “Recently, numerous studies have explored language agents which use LLMs for sequential decision-making (Yang et al., 2023; Wang et al., 2023b; Xi et al., 2023; Sumers et al., 2023).”
τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains (2024, background): “There is increasing excitement around the potential of language agents [20, 24, 18, 1] to enable new levels of automation across various industries.”
OS-ATLAS: A Foundation Action Model for Generalist GUI Agents (2024, background): “Autonomous agents powered by LLMs, known as language agents (Weng, 2023; Sumers et al., 2023), have recently garnered significant attention due to their interactive capabilities (Wang et al., 2023; Sun et al., 2023; Hong et al., 2024a; Durante et al., 2024).”
SGLang: Efficient Execution of Structured Language Model Programs (2023, neutral): “Recent increases in the capabilities of LLMs have broadened their utility, enabling them to tackle a wider range of general tasks and act as autonomous agents [35, 6, 36, 52, 46].”
Large Language Model based Multi-Agents: A Survey of Progress and Challenges (2024, background): “Single-Agent systems empowered by LLMs have shown in-spiring cognitive abilities [Sumers et al. , 2023].”
TravelPlanner: A Benchmark for Real-World Planning with Language Agents (2024, methodology): “A new generation of language agents (Su, 2023; Sumers et al., 2023; Xie et al., 2023) powered by LLMs has emerged, characterized by their capability of using language as a vehicle for thought and communication.”
Empowering Biomedical Discovery with AI Agents (2024, positive): “An AI agent is built as a compound system that consists of modules [3, 57, 58] each implementing a distinct functionality.”