Thinking Fast and Laterally: Multi-Agentic Approach for Reasoning about Uncertain Emerging Events

TL;DR

This paper presents SALT, a multi-agent framework that incorporates lateral thinking for enhanced System-2 reasoning in AI, especially under uncertainty and in streaming data environments, demonstrating improved reasoning capabilities over single-agent systems.

Contribution

Introduction of SALT, a multi-agent lateral thinking framework that enables complex reasoning in streaming environments through dynamic agent communication and belief management.

Findings

SALT outperforms single-agent systems in lateral reasoning tasks.

Lateral information flow enhances reasoning richness.

Preliminary evaluations show SALT's effectiveness in streaming data environments.

Abstract

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.