Learning Which Device to Call: Online Tool Grounding for LLM Agents in IoT

Yichen Liu; Xiaochong Jiang; Haoran Yu; Lifei Liu

cs.AIOct 18, 2026

Learning Which Device to Call: Online Tool Grounding for LLM Agents in IoT

Authors: Yichen Liu, Xiaochong Jiang, Haoran Yu, Lifei Liu

Organizations: Independent Researcher, Seattle, WA, USA · Independent Researcher, Boston, MA, USA

Abstract

The Internet of Things (IoT) gives large language model (LLM) agents access to physical observations, but one requested capability is usually offered by several devices, and the agent's plan does not say which one to call. Existing work retrieves relevant tools and checks plan feasibility, without learning which eligible device returns a useful observation. Unlike previous works, we study online tool grounding: binding an already specified tool call to one physical endpoint under service cost and device participation constraints. We propose a framework that learns which physical device should execute each agent-issued call. It formulates selection as a contextual bandit problem and combines adaptive context partitions with hierarchical endpoint trees, so that execution feedback is reused across related requests and devices. Selection balances task success against service cost while respecting device capability, authorization, battery reserves, and availability. Gaussian reward aggregation provides an optional mechanism for protecting individual feedback values. Theoretical results establish a finite-horizon regret bound and differential privacy for released reward statistics under fixed, reward-independent assignments. In a simulated loading-dock workload, the proposed router achieves higher step success and better cost-adjusted service, at lower simulated device energy and latency, than nearest-device, advertised-quality, UCB1, and LinUCB selection.

Figures & tables

Fig. 1: Tool-grounding workflow. Steps 1–6 form the routing loop for one tool call: the router selects an endpoint, the call is executed and verified, and the reward updates the learner. The top arrow returns the observation to the LLM agent. The dashed line marks the agent’s own check of its decision against the user goal; this check stays with the LLM and is not part of the evaluated loop. The evaluation covers provider selection in simulation rather than the complete agent–device loop.

Fig. 2: Context-specific endpoint partitioning. (a) The current request enters context cell $C_{n}$ . (b) Its endpoint hierarchy organizes eligible providers; the highlighted route ends at the sampled leaf. (c) That leaf is a region of endpoint feature space, from which one eligible device is selected. The coordinate plots show illustrative two-dimensional slices. Refinement splits one context or endpoint cell at a time; new children start without feedback.

Fig. 3: Performance over $N=100{,}000$ requests: (a) step success rate, (b) mean reward, (c) device energy per successful step, (d) tool-call latency, (e) cumulative regret, and (f) rolling mean reward over a 250-request window. Bars and lines are five-seed means; error bars and shaded bands show $\pm 1$ sample standard deviation. The noisy variant uses $\varepsilon=8$ . Energy and latency are simulated device-side quantities and exclude LLM inference and router computation.

Parameter	Value
Zones; targets per zone; endpoints	6; 5; 300
Eligible endpoints per call	52–72 (by seed)
Advertised quality	mean 0.58–0.85, s.d. 0.09–0.18
Latency; energy per call	0.20–1.10 s; 0.4–5.0 J
Battery capacity $\Gamma_{p}$ ; reserve $V_{p}^{\rm min}$	$U(4000,12000)$ J; $U(0.20,0.45)$
Committed usage $U_{n}(p)$ ; recharge	$U(0.02,0.12)$ ; $1.2\times 10^{-5}$ per round

TABLE I: Simulation and Learner Settings

LLM Tool Use

Large language model tool use studies how models select, call, and coordinate external tools to extend their reasoning and take actions.

See all 289 papers

Utility-Guided Agent Orchestration for Efficient LLM Tool Use
Mar 20, 2026Boyan Liu, Gongming Zhao, Hongli XuLLM Agent Orchestration LLM Tool Use
University of Science and Technology of China, Hefei, Anhui, China · Suzhou Institute for Advanced Research, University of Science and Technology of China
Scores Are Not Decisions: Cost-Aware Stopping for Tool Acquisition in LLM Agents
Jul 29, 2026Yicheng Feng, Yan Zhang, Yan Cheng +1Decision-Focused Learning Tool-Using Agents
School of Advanced Manufacturing and Robotics, Peking University · Desautels Faculty of Management, McGill University · Business School, Shanghai University of Finance and Economics +1
Hera: Learning Long-Horizon Coordination for Device-Cloud Collaborative LLM Agents
May 23, 2026Yuxin Zhang, Mengxue Hu, Zheng Lin +8LLM Agent Training LLM Routing
1Fudan University · 2Alibaba Group · 3The University of Hong Kong +4

Mar 20, 2026J/K move · Enter open · S save

Utility-Guided Agent Orchestration for Efficient LLM Tool Use

Boyan Liu, Gongming Zhao, Hongli Xu

University of Science and Technology of China, Hefei, Anhui, China · Suzhou Institute for Advanced Research, University of Science and Technology of China

LLM Agent Orchestration LLM Tool Use LLM Agent Workflow Optimization LLM Decision-Making

Open paper AskPDF arXiv

Tool-using large language model (LLM) agents often face a fundamental tension between answer quality and execution cost. Fixed workflows are stable but inflexible, while free-form multi-step reasoning methods such as ReAct may improve task performance at the expense of excessive tool calls, longer trajectories, higher token consumption, and increased latency. In this paper, we study agent orchestration as an explicit decision problem rather than leaving it entirely to prompt-level behavior. We propose a utility-guided orchestration policy that selects among actions such as respond, retrieve, tool call, verify, and stop by balancing estimated gain, step cost, uncertainty, and redundancy. Our goal is not to claim universally best task performance, but to provide a controllable and analyzable policy framework for studying quality-cost trade-offs in tool-using LLM agents. Experiments across direct answering, threshold control, fixed workflows, ReAct, and several policy variants show that explicit orchestration signals substantially affect agent behavior. Additional analyses on cost definitions, workflow fairness, and redundancy control further demonstrate that lightweight utility design can provide a defensible and practical mechanism for agent control.

Abstract

LLM Tool Use

Explore similar work

Utility-Guided Agent Orchestration for Efficient LLM Tool Use

Scores Are Not Decisions: Cost-Aware Stopping for Tool Acquisition in LLM Agents

Hera: Learning Long-Horizon Coordination for Device-Cloud Collaborative LLM Agents