analiza aiqbench
This research introduces Causal Minimal Tool Filtering (CMTF), a training-free method that significantly improves LLM agent reliability by exposing only the minimal necessary tools based on causal sufficiency rather than semantic relevance. By reducing visible tool options from 100 to one per step, the approach cuts token usage by approximately 90% while maintaining high task success rates across diverse benchmarks. For developers building agentic systems, this offers a practical pathway to mitigate wrong-tool calls and premature actions without incurring additional training costs.
ToolChoiceConfusion: Causal Minimal Tool Filtering for Reliable LLM Agents
arXiv:2606.06284v1 Announce Type: new Abstract: Large language model agents increasingly rely on external tools, but larger tool menus can reduce reliability and efficiency by increasing wrong-tool calls, premature actions, and token cost. Existing tool-selection methods often optimize semantic relevance, exposing tools whose names or descriptions match the user request. We argue that relevance is insufficient: a tool may be related to the task while still being unnecessary or premature at the current step. We propose Causal Minimal Tool Filtering (CMTF), a training-free method that selects tools by causal sufficiency. CMTF uses lightweight precondition-effect contracts to expose only the minimal next-step tool frontier needed to advance from the current state toward the user goal. Across multi-step tool-use tasks, we compare CMTF with all-tools exposure, keyword retrieval, state-aware filtering, and causal-path ablations, measuring task success, wrong-tool calls, premature actions, tool exposure, and token cost. In the main benchmark with 102 tasks, 100 tools, four LLM backends, and 2448 task-method-model runs, CMTF matches the strongest causal baseline in aggregate success while reducing visible tools from 100 to one per step and reducing token usage by about 90% relative to all-tools exposure.
Abstract:Large language model agents increasingly rely on external tools, but larger tool menus can reduce reliability and efficiency by increasing wrong-tool calls, premature actions, and token cost. Existing tool-selection methods often optimize semantic relevance, exposing tools whose names or descriptions match the user request. We argue that relevance is insufficient: a tool may be related to the task while still being unnecessary or premature at the current step. We propose Causal Minimal Tool Filtering (CMTF), a training-free method that selects tools by causal sufficiency. CMTF uses lightweight precondition-effect contracts to expose only the minimal next-step tool frontier needed to advance from the current state toward the user goal. Across multi-step tool-use tasks, we compare CMTF with all-tools exposure, keyword retrieval, state-aware filtering, and causal-path ablations, measuring task success, wrong-tool calls, premature actions, tool exposure, and token cost. In the main benchmark with 102 tasks, 100 tools, four LLM backends, and 2448 task-method-model runs, CMTF matches the strongest causal baseline in aggregate success while reducing visible tools from 100 to one per step and reducing token usage by about 90% relative to all-tools exposure.
Artificial Intelligence (cs.AI)
arXiv:2606.06284 [cs.AI]
(or arXiv:2606.06284v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2606.06284 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 277 cuvinte
Subiecte conexe
GIST-CMTF: Goal-State Inference for Causal Minimal Tool Filtering in LLM Agents
arXiv · 16 iun. 2026
ToolMenuBench: Benchmarking Tool-Menu Filtering Strategies for Reliable and Efficient LLM Agents
arXiv · 16 iun. 2026
Reviewing failure modes in science as we prepare for AI researchers
LessWrong · 8 oct. 2026
Contract2Tool: Learning Preconditions and Effects for Reliable Tool-Augmented LLM Agents
arXiv · 9 iun. 2026