ToC: Tree-of-Claims Search with Multi-Agent Language Models

TL;DR

This paper introduces Tree of Claims (ToC), a novel framework combining Monte Carlo Tree Search with multi-agent LLMs to optimize patent claims by balancing novelty, scope, and coherence, outperforming standard LLMs in claim refinement tasks.

Contribution

ToC is the first to integrate MCTS with multi-agent LLMs for structured patent claim editing, enabling transparent and effective optimization.

Findings

ToC achieves an 8 ext% average improvement over standard LLMs.

Outperforms in zero-shot and few-shot claim revision scenarios.

Validated through extensive ablation studies.

Abstract

Optimizing patent claims is a critical yet challenging task, demanding careful balance between maximizing novelty and preserving legal scope. Manual claim drafting is labor-intensive, costly, and inherently inconsistent, while conventional Large Language Models (LLMs) often lack the structured, iterative reasoning essential for precise claim refinement. To address these challenges, we introduce Tree of Claims (ToC), an innovative framework that redefines claim editing as a guided search problem. ToC synergistically integrates Monte Carlo Tree Search (MCTS) with a collaborative multi-agent system, comprising an LLM-based EditorAgent that proposes contextually grounded edits, and an ExaminerAgent that mimics patent examiner critiques through structured, chain-of-thought analyses of novelty and prior art disclosure. Driven by a carefully designed multi-objective reward function, ToC jointly optimizes novelty, scope retention, and semantic coherence. Experimental evaluation on a benchmark of 1145 claims demonstrates that ToC significantly outperforms standard LLMs in zero-shot and few-shot scenarios, achieving an average composite score improvement of 8\%, and up to 9\% in certain cases. Extensive experiments, including detailed ablation studies, validate ToC's efficacy in generating superior, legally robust claim revisions. Overall, ToC establishes a transparent, controllable, and interpretable methodology that effectively bridges advanced LLM reasoning capabilities with strategic MCTS planning for structured patent claim optimization.The source code is available at https://github.com/ysy2003/ToC.