GRAFT: Graph-Tokenized LLMs for Tool Planning

• URL: http://arxiv.org/abs/2605.11706v1
• Date: Tue, 12 May 2026 07:59:41 GMT
• Title: GRAFT: Graph-Tokenized LLMs for Tool Planning
• Abstract summary: Large language models (LLMs) are increasingly used to complete complex tasks by selecting and coordinating external tools across multiple steps.<n>This requires aligning tool choices with subtask intent while satisfying directional execution dependencies among tools.<n>We propose GRAFT, a graph-tokenized language model framework for dependency-aware tool planning.
• Score: 41.72670983284452
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• HyperAgent: Planning and Acting over Tool-Schema Hypergraphs for Tool-Use LLM Agents [8.462939802909888]
  Large language model (LLM) agents increasingly rely on external tools to complete complex real-world tasks.<n>Reliable tool-use planning remains challenging due to the limitations of implicit reasoning and the evolving nature of real-world execution environments.
  arXiv  Detail & Related papers  (2026-07-31T21:42:35Z)
• SIT-Graph: State Integrated Tool Graph for Multi-Turn Agents [35.85800795225018]
  State Integrated Tool Graph (SIT-Graph) is inspired by human decision-making that integrates episodic and procedural memory.<n>At inference time, SIT-Graph enables a human-like balance between episodic recall and procedural execution.<n> Experiments across multiple stateful multi-turn tool-use benchmarks show that SIT-Graph consistently outperforms strong memory- and graph-based baselines.
  arXiv  Detail & Related papers  (2025-12-08T08:27:24Z)
• GAP: Graph-Based Agent Planning with Parallel Tool Use and Reinforcement Learning [20.75113227786218]
  Graph-based Agent Planning (GAP) is a novel framework that explicitly models inter-task dependencies through graph-based planning.<n>Our approach trains agent foundation models to decompose complex tasks into dependency-aware sub-task graphs.<n>This dependency-aware orchestration achieves substantial improvements in both execution efficiency and task accuracy.
  arXiv  Detail & Related papers  (2025-10-29T09:35:55Z)
• GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning [50.40400074353263]
  Graph Neural Networks (GNNs) are powerful tools for precessing relational data but often struggle to generalize to unseen graphs.<n>We introduce textbfGraph textbfIn-context textbfL textbfTransformer (GILT), a framework built on an LLM-free and tuning-free architecture.
  arXiv  Detail & Related papers  (2025-10-06T08:09:15Z)
• TRAJECT-Bench:A Trajectory-Aware Benchmark for Evaluating Agentic Tool Use [74.47746287181383]
  Large language model (LLM)-based agents increasingly rely on tool use to complete real-world tasks.<n>We introduce TRAJECT-Bench, a trajectory-aware benchmark to comprehensively evaluate LLMs' tool use capability.
  arXiv  Detail & Related papers  (2025-10-06T07:30:25Z)
• GTool: Graph Enhanced Tool Planning with Large Language Model [20.584869026691695]
  We propose textttGTool to enhance the tool planning ability of large language models (LLMs) under incomplete dependencies.<n>textttGTool constructs a request-specific tool graph to select tools efficiently and generate the textttgraph token> which provides sufficient dependency information.<n>Extensive experiments show that textttGTool achieves more than 29.6% performance improvements compared with the state-of-the-art (SOTA) baselines.
  arXiv  Detail & Related papers  (2025-08-18T08:46:55Z)
• Plan-over-Graph: Towards Parallelable LLM Agent Schedule [53.834646147919436]
  Large Language Models (LLMs) have demonstrated exceptional abilities in reasoning for task planning.<n>This paper introduces a novel paradigm, plan-over-graph, in which the model first decomposes a real-life textual task into executable subtasks and constructs an abstract task graph.<n>The model then understands this task graph as input and generates a plan for parallel execution.
  arXiv  Detail & Related papers  (2025-02-20T13:47:51Z)
• Towards Completeness-Oriented Tool Retrieval for Large Language Models [60.733557487886635]
  Real-world systems often incorporate a wide array of tools, making it impractical to input all tools into Large Language Models. Existing tool retrieval methods primarily focus on semantic matching between user queries and tool descriptions. We propose a novel modelagnostic COllaborative Learning-based Tool Retrieval approach, COLT, which captures not only the semantic similarities between user queries and tool descriptions but also takes into account the collaborative information of tools.
  arXiv  Detail & Related papers  (2024-05-25T06:41:23Z)
• ToolNet: Connecting Large Language Models with Massive Tools via Tool Graph [43.95759808077083]
  Existing in-context learning approaches simply format tools into a list of plain text descriptions and input them to large language models. This paper proposes ToolNet, a plug-and-play framework that scales up the number of tools to thousands with a moderate increase in token consumption.
  arXiv  Detail & Related papers  (2024-02-29T02:04:00Z)
• ControlLLM: Augment Language Models with Tools by Searching on Graphs [97.62758830255002]
  We present ControlLLM, a novel framework that enables large language models (LLMs) to utilize multi-modal tools for solving real-world tasks. Our framework comprises three key components: (1) a textittask decomposer that breaks down a complex task into clear subtasks with well-defined inputs and outputs; (2) a textitThoughts-on-Graph (ToG) paradigm that searches the optimal solution path on a pre-built tool graph; and (3) an textitexecution engine with a rich toolbox that interprets the solution path and runs the
  arXiv  Detail & Related papers  (2023-10-26T21:57:21Z)
• Structural Embeddings of Tools for Large Language Models [0.0]
  It is evident that the current state of Large Language Models (LLMs) necessitates the incorporation of external tools. The ontological nature of tool utilization for a specific task can be well formulated with a Directed Acyclic Graph (DAG) We propose an exemplary framework to guide the orchestration of exponentially increasing numbers of external tools with LLMs.
  arXiv  Detail & Related papers  (2023-08-01T10:46:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.