홈 › Papers

Learning Agent Routing From Early Experience

2026-05-08 · Yimin Wang, Jiahao Qiu, Xuan Qi, Xinzhe Juan, Jingzhe Shi, Zelin Zhao, Hongru Wang, Shilong Liu, Mengdi Wang arxiv

LLM agents achieve strong performance on complex reasoning tasks but incur high latency and compute cost. In practice, many queries fall within the capability boundary of cutting-edge LLMs and do not require full agent execution, making effective routing between LLMs and agents a key challenge. We study the problem of routing queries between lightweight LLM inference and full agent execution under realistic cold-start settings. To address this, we propose BoundaryRouter, a training-free routing framework that uses early behavioral experience and rubric-guided reasoning to decide whether to answer a query with direct LLM inference or escalate to an agent. BoundaryRouter builds a compact experience memory by executing both systems on a shared seed set and retrieves similar cases at inference time to guide routing decisions. To evaluate this method, we introduce RouteBench, a benchmark covering in-domain, paraphrased, and out-of-domain route settings. Experiments show that BoundaryRouter reduces inference time by 60.6% compared to the agent while improving performance by 28.6% over direct LLM inference, outperforming prompt-based and retrieval-only routing by an average of 37.9% and 8.2%, respectively.

📄 PDF Abstract BibTeX arXiv:2605.07180

Code (0)

등록된 구현이 없습니다.

STDPG: A Spatio-Temporal Deterministic Policy Gradient Agent for Dynamic Routing in SDN

2020-04-21 · Juan Chen, Zhiwen Xiao, Huanlai Xing, Penglin Dai 외

Dynamic routing in software-defined networking (SDN) can be viewed as a centralized decision-making problem. Most of the existing deep reinforcement learning (DRL) agents can address it, thanks to the deep neural network…

Decision Making Deep Reinforcement Learning Reinforcement Learning

An Agent-Oriented Pluggable Experience-RAG Skill for Experience-Driven Retrieval Strategy Orchestration

2026-05-05 · Dutao Zhang, Tian Liao arxiv

Retrieval-augmented generation systems often assume that one fixed retrieval pipeline is sufficient across heterogeneous tasks, yet factoid question answering, multi-hop reasoning, and scientific verification exhibit dif…

Question Answering

EvoRoute: Experience-Driven Self-Routing LLM Agent Systems

2026-01-06 · Guibin Zhang, Haiyang Yu, Kaiming Yang, Bingli Wu 외 arxiv

Complex agentic AI systems, powered by a coordinated ensemble of Large Language Models (LLMs), tool and memory modules, have demonstrated remarkable capabilities on intricate, multi-turn tasks. However, this success is s…

Agent Learning via Early Experience

2025-10-09 · Kai Zhang, Xiangchao Chen, Bo Liu, Tianci Xue 외 arxiv

A long-term goal of language agents is to learn and improve through their own experience, ultimately outperforming humans in complex, real-world tasks. However, training agents from experience data with reinforcement lea…

Reinforcement Learning Domain Generalization

Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning

2017-02-28 · ICML 2017 8 · Jakob Foerster, Nantas Nardelli, Gregory Farquhar, Triantafyllos Afouras 외

Many real-world problems, such as network packet routing and urban traffic control, are naturally modeled as multi-agent reinforcement learning (RL) problems. However, existing multi-agent RL methods typically scale poor…

Multi-agent Reinforcement Learning Q-Learning reinforcement-learning Reinforcement Learning+2