Saved in:
Bibliographic Details
Main Authors: Dernbach, Stefan, Michel, Alejandro, Agarwal, Khushbu, Brissette, Christopher, Gupta, Geetika, Choudhury, Sutanay
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.07977
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929624227774464
author Dernbach, Stefan
Michel, Alejandro
Agarwal, Khushbu
Brissette, Christopher
Gupta, Geetika
Choudhury, Sutanay
author_facet Dernbach, Stefan
Michel, Alejandro
Agarwal, Khushbu
Brissette, Christopher
Gupta, Geetika
Choudhury, Sutanay
contents This paper introduces lateral thinking to implement System-2 reasoning capabilities in AI systems, focusing on anticipatory and causal reasoning under uncertainty. We present a framework for systematic generation and modeling of lateral thinking queries and evaluation datasets. We introduce Streaming Agentic Lateral Thinking (SALT), a multi-agent framework designed to process complex, low-specificity queries in streaming data environments. SALT implements lateral thinking-inspired System-2 reasoning through a dynamic communication structure between specialized agents. Our key insight is that lateral information flow across long-distance agent interactions, combined with fine-grained belief management, yields richer information contexts and enhanced reasoning. Preliminary quantitative and qualitative evaluations indicate SALT's potential to outperform single-agent systems in handling complex lateral reasoning tasks in a streaming environment.
format Preprint
id arxiv_https___arxiv_org_abs_2412_07977
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Thinking Fast and Laterally: Multi-Agentic Approach for Reasoning about Uncertain Emerging Events
Dernbach, Stefan
Michel, Alejandro
Agarwal, Khushbu
Brissette, Christopher
Gupta, Geetika
Choudhury, Sutanay
Artificial Intelligence
This paper introduces lateral thinking to implement System-2 reasoning capabilities in AI systems, focusing on anticipatory and causal reasoning under uncertainty. We present a framework for systematic generation and modeling of lateral thinking queries and evaluation datasets. We introduce Streaming Agentic Lateral Thinking (SALT), a multi-agent framework designed to process complex, low-specificity queries in streaming data environments. SALT implements lateral thinking-inspired System-2 reasoning through a dynamic communication structure between specialized agents. Our key insight is that lateral information flow across long-distance agent interactions, combined with fine-grained belief management, yields richer information contexts and enhanced reasoning. Preliminary quantitative and qualitative evaluations indicate SALT's potential to outperform single-agent systems in handling complex lateral reasoning tasks in a streaming environment.
title Thinking Fast and Laterally: Multi-Agentic Approach for Reasoning about Uncertain Emerging Events
topic Artificial Intelligence
url https://arxiv.org/abs/2412.07977