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

Stefan Dernbach, Alejandro Michel, Khushbu Agarwal, Christopher Brissette, geetika gupta, Sutanay Choudhury

Keywords: reasoning, streaming, multi-agent systems, agent networks

TL;DR: This paper introduces lateral thinking for AI reasoning, presenting a framework for generating queries and datasets, and proposing $\ourSystem$, a multi-agent system for lateral thinking-inspired reasoning 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. Preliminary quantitative and qualitative evaluations indicate SALT's potential to outperform single-agent systems in handling complex reasoning tasks.

Submission Number: 64