AI RESEARCH
GRAFT: Graph-Tokenized LLMs for Tool Planning
arXiv CS.LG
•
ArXi:2605.11706v1 Announce Type: new 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.