Go to ICLR 2026 Conference homepageGraphPlanner: Graph-Based Agentic Routing for LLMs
Keywords: Agentic LLM, Memory utilization, Heterogeneous agents
TL;DR: GraphPlanner is a graph-based framework that enables agentic LLM routing by modeling cooperation and memory with reinforcement learning, achieving scalable, efficient, and generalizable routing.
Abstract: LLM routing has achieved promising results in integrating the strengths of di-
verse models while balancing efficiency and performance. However, to support
more realistic and challenging applications, routing must extend into agentic LLM
settings—where task planning, multi-round cooperation among heterogeneous
agents, and memory utilization are indispensable. To address this gap, we pro-
pose GraphPlanner, a heterogeneous graph-based agentic router that generates
routing workflows for each query and supports both inductive and transductive
inference. GraphPlanner formulates workflow generation as a Markov Deci-
sion Process (MDP), where at each step it selects both the LLM backbone and
the agent role (Planner, Executor, Summarizer). By leveraging a heterogeneous
graph, denoted as GARNet, to capture interactions among queries, agents, and
responses, GraphPlanner integrates historical and contextual information into
richer state representations. The entire pipeline is optimized with reinforcement
learning, jointly improving task-specific performance and computational efficiency.
We evaluate GraphPlanner across 14 diverse LLM tasks and demonstrate that:
(1) GraphPlanner outperforms strong single- and multi-round routers, improv-
ing accuracy by up to 9.3% while reducing GPU cost from 186.26 GiB to 1.04 GiB;
(2) GraphPlanner generalizes robustly to unseen tasks and LLMs, exhibiting
strong zero-shot capabilities; and (3) GraphPlanner effectively leverages his-
torical interactions, supporting both inductive and transductive inference for more
adaptive routing.
Primary Area: learning on graphs and other geometries & topologies
Submission Number: 20197
Loading