Thinking Fast and Laterally: Multi-Agentic Approach for Reasoning about Uncertain Emerging Events
This work addresses the challenge of enhancing AI reasoning capabilities for uncertain emerging events, representing an incremental advancement in multi-agent systems for reasoning tasks.
The paper tackles the problem of implementing System-2 reasoning for anticipatory and causal reasoning under uncertainty in AI systems by introducing a multi-agent framework called SALT, which shows potential to outperform single-agent systems in handling complex lateral reasoning tasks in streaming environments.
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.