# GRAFT: Graph-Tokenized LLMs for Tool Planning

arXiv: https://arxiv.org/abs/2605.11706 · HTML: https://mlsanity.com/paper/2605.11706/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 37 references that are in the map.
- First posted on arXiv 12 May 2026.

## Builds on (most cited first, 30 of 32)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](https://mlsanity.com/paper/2303.17580/) (2023)
- [Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks](https://mlsanity.com/paper/1506.03099/) (2015)
- [Sequence Level Training with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06732/) (2015)
- [Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models](https://mlsanity.com/paper/2601.18734/) (2026)
- [GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction](https://mlsanity.com/paper/2305.18752/) (2023)
- [Professor Forcing: A New Algorithm for Training Recurrent Networks](https://mlsanity.com/paper/1610.09038/) (2016)
- [Large Language Models on Graphs: A Comprehensive Survey](https://mlsanity.com/paper/2312.02783/) (2023)
- [On-Policy Context Distillation for Language Models](https://mlsanity.com/paper/2602.12275/) (2026)
- [The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey](https://mlsanity.com/paper/2404.11584/) (2024)
- [A Survey of On-Policy Distillation for Large Language Models](https://mlsanity.com/paper/2604.00626/) (2026)
- [TaskBench: Benchmarking Large Language Models for Task Automation](https://mlsanity.com/paper/2311.18760/) (2023)
- [Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarios](https://mlsanity.com/paper/2401.17167/) (2024)
- [A Survey of Graph Meets Large Language Model: Progress and Future Directions](https://mlsanity.com/paper/2311.12399/) (2023)
- [ToolGen: Unified Tool Retrieval and Calling via Generation](https://mlsanity.com/paper/2410.03439/) (2024)
- [AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2509.08755/) (2025)
- [In-the-Flow Agentic System Optimization for Effective Planning and Tool Use](https://mlsanity.com/paper/2510.05592/) (2025)
- [LLM With Tools: A Survey](https://mlsanity.com/paper/2409.18807/) (2024)
- [ToolNet: Connecting Large Language Models with Massive Tools via Tool Graph](https://mlsanity.com/paper/2403.00839/) (2024)
- [ControlLLM: Augment Language Models with Tools by Searching on Graphs](https://mlsanity.com/paper/2310.17796/) (2023)
- [Can Graph Learning Improve Planning in LLM-based Agents?](https://mlsanity.com/paper/2405.19119/) (2024)
- [Graph-enhanced Large Language Models in Asynchronous Plan Reasoning](https://mlsanity.com/paper/2402.02805/) (2024)
- [Toolink: Linking Toolkit Creation and Using through Chain-of-Solving on Open-Source Model](https://mlsanity.com/paper/2310.05155/) (2023)
- [LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error](https://mlsanity.com/paper/2403.04746/) (2024)

## Abstract (arXiv)

Large language models (LLMs) are increasingly used to complete complex tasks by selecting and coordinating external tools across multiple steps. This requires aligning tool choices with subtask intent while satisfying directional execution dependencies among tools. To do this, existing methods model these dependencies as tool graphs and incorporate the graphs with LLMs through retrieval, serialization, or prompt-level injection. However, these external graph-use strategies all follow a matching paradigm, which often fails to align tool choices with the underlying subtask structure, producing semantically plausible plans that violate graph constraints. This issue is further exacerbated by error accumulation, where an early incorrect tool selection shifts the plan into an invalid graph state and causes subsequent predictions to drift away from the valid execution path. To address these challenges, we propose GRAFT, a graph-tokenized language model framework for dependency-aware tool planning. GRAFT internalizes the tool graph by mapping each tool node to a dedicated special token and learning directed tool dependencies within the representation space. It further introduces on-policy tool context distillation, training the model on its own sampled trajectories while distilling stepwise planning signals. Experiments show that GRAFT achieves state-of-the-art performance in exact sequence matching and dependency legality, supporting more reliable LLM tool planning in complex workflows.