Research map / Large language models / Agents, code and math
ControlLLM: Augment Language Models with Tools by Searching on Graphs
Zhaoyang Liu, Zeqiang Lai, Zhangwei Gao, erfei cui, Ziheng Li, Xizhou Zhu, Lewei Lu, Qifeng Chen, Yu Qiao, Jifeng Dai, Wenhai Wang
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 |
|---|---|---|---|
| search a pre-built tool graph (Thoughts-on-Graph) instead of LLM-generated chain or tree planning | ControlLLM · ControlLLM tool benchmark | solution evaluation (All): 0.59 -> 0.93 | Improved |
| use beam search instead of greedy search on the tool graph (ablation) | ToG · ControlLLM tool benchmark | solution evaluation (All): 0.49 -> 0.88 | Improved |
| use adaptive search instead of exhaustive search (ablation) | ToG · ControlLLM tool benchmark | solution evaluation (All): 0.97 -> 0.93 | Mixed |
| add prior knowledge (likely tools) to subtask description (ablation) | ControlLLM task decomposition with ChatGPT-3.5 · ControlLLM tool benchmark | solution evaluation (All): 0.83 -> 0.93 | Improved |
| add prior knowledge to subtask description with Llama2-13B (ablation) | ControlLLM task decomposition · ControlLLM tool benchmark | solution evaluation (All): 0.68 -> 0.82 | Improved |
| use a stronger LLM (GPT-4 instead of Llama2-13B) in task decomposition (ablation) | ControlLLM · ControlLLM tool benchmark | solution evaluation (All): 0.82 -> 0.98 | Improved |
| finetune LLaMA-7B for task decomposition instead of using ChatGPT zero-shot (Mix vs ChatGPT) (ablation) | ControlLLM · ControlLLM tool benchmark | solution evaluation (All): 0.64 -> 0.93 | Improved |
Closest papers by meaning
- ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs (ICLR 2024 · similarity 0.90)
- Large Language Models as Tool Makers (ICLR 2024 · similarity 0.88)
- Adaptable Logical Control for Large Language Models (NeurIPS 2024 · similarity 0.88)
- TaskBench: Benchmarking Large Language Models for Task Automation (NeurIPS 2024 · similarity 0.88)
- CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets (ICLR 2024 · similarity 0.88)
- Joint Optimization of Tool Creation and Use for Large Language Model Agents (NeurIPS 2026 · similarity 0.87)
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.
