REVIEW 3 cited by
Agents Thinking Fast and Slow: A Talker-Reasoner Architecture
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Large language models have enabled agents of all kinds to interact with users through natural conversation. Consequently, agents now have two jobs: conversing and planning/reasoning. Their conversational responses must be informed by all available information, and their actions must help to achieve goals. This dichotomy between conversing with the user and doing multi-step reasoning and planning can be seen as analogous to the human systems of "thinking fast and slow" as introduced by Kahneman. Our approach is comprised of a "Talker" agent (System 1) that is fast and intuitive, and tasked with synthesizing the conversational response; and a "Reasoner" agent (System 2) that is slower, more deliberative, and more logical, and is tasked with multi-step reasoning and planning, calling tools, performing actions in the world, and thereby producing the new agent state. We describe the new Talker-Reasoner architecture and discuss its advantages, including modularity and decreased latency. We ground the discussion in the context of a sleep coaching agent, in order to demonstrate real-world relevance.
Forward citations
Cited by 3 Pith papers
-
Let's Get You Hired: A Job Seeker's Perspective on Multi-Agent Recruitment Systems for Explaining Hiring Decisions
A multi-agent LLM chatbot for job seekers was perceived by 20 interviewed participants as more actionable, trustworthy, and fair than their recalled experiences with traditional hiring methods.
-
KC-Agent: A Dual-Process Cognitive Architecture for Efficient ML Model Improvement
A dual-process LLM agent (System 1 fast retrieval + System 2 atomic changes) is claimed to improve drifted ML models faster and more accurately, but the reported gains are weakened by evaluating on the same data used ...
-
AIvilization v0: Toward Large-Scale Artificial Social Simulation with a Unified Agent Architecture and Adaptive Agent Profiles
A deployed LLM-agent society with branch-thinking planning and dual-process memory claims to reproduce heavy-tailed returns, volatility clustering, and education-driven wealth stratification, but key evidence reduces ...
Discussion (0). Continue with ORCID to comment.