Research map / Large language models / Agents, code and math
ToC: Tree-of-Claims Search with Multi-Agent Language Models
Shuyang Yu, Jianan Liang, Hui Hu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add ToC search (MCTS with Examiner and Editor agents) over zero-shot prompting | GPT-4o · USPTO wireless patent claims | overall composite score: 0.647 -> 0.701 | Improved |
| add ToC search over few-shot prompting | GPT-4o · USPTO wireless patent claims | overall composite score: 0.678 -> 0.701 | Improved |
| add ToC search over zero-shot prompting | OpenAI O1 · USPTO wireless patent claims | overall composite score: 0.631 -> 0.680 | Improved |
| add ToC search over zero-shot prompting | Qwen2.5-VL-32B · USPTO wireless patent claims | overall composite score: 0.592 -> 0.639 | Improved |
| add ToC search over zero-shot prompting | Qwen2.5-VL-72B · USPTO wireless patent claims | overall composite score: 0.611 -> 0.658 | Improved |
| add ToC search over zero-shot prompting | GPT-4o · USPTO wireless patent claims | coverage reward: 0.520 -> 0.582 | Improved |
| add ToC search over zero-shot prompting | GPT-4o · USPTO wireless patent claims | scope reward (penalty term): 0.417 -> 0.389 | Improved |
| add ToC search over zero-shot prompting | GPT-4o · USPTO wireless patent claims | perplexity: 8.93 -> 8.72 | Improved |
| add ToC search over zero-shot prompting | GPT-4o · USPTO wireless patent claims | JSON parse completeness: 0.994 -> 0.996 | No clear effect |
| use few-shot prompting with chain-of-thought exemplars instead of zero-shot | GPT-4o · USPTO wireless patent claims | overall composite score: 0.647 -> 0.678 | Improved |
| disable uncertainty gating, progressive widening, or multi-agent collaboration (ablation) | ToC · USPTO wireless patent claims | novelty, coverage, legal quality | Hurt |
| use progressive widening alpha 0.8 or search depth at most 5 (ablation) | ToC sensitivity · USPTO wireless patent claims | accuracy: 3-5 points lower | Hurt |
Closest papers by meaning
- PANORAMA: A Dataset and Benchmarks Capturing Decision Trails and Rationales in Patent Examination (NeurIPS 2025 · similarity 0.87)
- PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures (AAAI 2025 · similarity 0.82)
- Argumentative Large Language Models for Explainable and Contestable Claim Verification (AAAI 2025 · similarity 0.82)
- J&H: Evaluating the Robustness of Large Language Models Under Knowledge-Injection Attacks in Legal Domain (AAAI 2025 · similarity 0.81)
- Fleet of Agents: Coordinated Problem Solving with Large Language Models (ICML 2025 · similarity 0.81)
- Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search (ICML 2025 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
