Network-of-Thought (NoT) moves LLM reasoning from linear chains and trees to complex directed graphs, significantly improving multi-hop QA.
March 24, 2026
Original Paper
Reasoning Topology Matters: Network-of-Thought for Complex Reasoning Tasks
arXiv · 2603.20730
The Takeaway
While Chain-of-Thought and Tree-of-Thought are standard, many real-world problems require merging and revisiting hypotheses. This framework formalizes reasoning as a graph, showing that non-linear topologies provide better accuracy on complex reasoning tasks while maintaining token efficiency.
From the abstract
Existing prompting paradigms structure LLM reasoning in limited topologies: Chain-of-Thought (CoT) produces linear traces, while Tree-of-Thought (ToT) performs branching search. Yet complex reasoning often requires merging intermediate results, revisiting hypotheses, and integrating evidence from multiple sources. We propose Network-of-Thought (NoT), a framework that models reasoning as a directed graph with typed nodes and edges, guided by a heuristic-based controller policy. Across four benchm