Task-Aware LLM Routing with Multi-Level Task-Profile-Guided Data Synthesis for Cold-Start Scenarios

• URL: http://arxiv.org/abs/2604.09377v1
• Date: Fri, 10 Apr 2026 14:46:20 GMT
• Title: Task-Aware LLM Routing with Multi-Level Task-Profile-Guided Data Synthesis for Cold-Start Scenarios
• Abstract summary: Large language models (LLMs) exhibit substantial variability in performance and computational cost across tasks and queries.<n>We introduce T, a task-type-aware router approach that models query-conditioned cost and performance via latent task-type variables.
• Score: 51.44288759906005
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) exhibit substantial variability in performance and computational cost across tasks and queries, motivating routing systems that select models to meet user-specific cost-performance trade-offs. However, existing routers generalize poorly in cold-start scenarios where in-domain training data is unavailable. We address this limitation with a multi-level task-profile-guided data synthesis framework that constructs a hierarchical task taxonomy and produces diverse question-answer pairs to approximate the test-time query distribution. Building on this, we introduce TRouter, a task-type-aware router approach that models query-conditioned cost and performance via latent task-type variables, with prior regularization derived from the synthesized task taxonomy. This design enhances TRouter's routing utility under both cold-start and in-domain settings. Across multiple benchmarks, we show that our synthesis framework alleviates cold-start issues and that TRouter delivers effective LLM routing.

Related papers

• ProgRouter: Online Progress-Guided Orchestration for Multi-Agent LLM Workflows under Quality-Cost Tradeoffs [20.369237729934664]
  Multi-agent large language model (LLM) have emerged as a powerful paradigm for solving complex, open-ended tasks.<n>Existing cascade routing methods make one-shot, state-dependent decisions and cannot adapt to the dynamic, state-dependent nature of multi-step query-level decisions.<n>We present Prog, an online progress-guided routing framework that adaptively selects LLM agents across workflow steps to preserve task-solving quality while adhering to time and cost budgets.
  arXiv  Detail & Related papers  (2026-08-26T16:42:02Z)
• TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning [29.41888837689613]
  Time series reasoning is essential for real-world problem-solving.<n>Large Language Models (LLMs) and Vision-Language Models (VLMs) can reason about time-series data.<n>We introduce TS, a graph-based dynamic routing framework.
  arXiv  Detail & Related papers  (2026-07-09T21:09:05Z)
• Agent-as-a-Router: Agentic Model Routing for Coding Tasks [54.00153674547733]
  Agent-as-a-router (AC) formalizes routing as a C-A-F loop (Context->Action->FeedbackContext)<n>AC achieves the lowest cumulative regret on in-distribution tasks and generalizes to out-of-distribution agentic-programming tasks.
  arXiv  Detail & Related papers  (2026-06-22T06:37:31Z)
• Why Search When You Can Transfer? Amortized Agentic Workflow Design from Structural Priors [51.95306551061392]
  Automated agentic workflow design currently relies on per-task iterative search.<n>We present SWIFT, a framework that amortizes workflow design into reusable structural priors.<n> SWIFT outperforms the state-of-the-art search-based method on five benchmarks.
  arXiv  Detail & Related papers  (2026-04-27T21:25:00Z)
• Efficient and Interpretable Multi-Agent LLM Routing via Ant Colony Optimization [58.59491516762626]
  We propose AMRO-S, an efficient and interpretable routing framework for Multi-Agent Systems (MAS)<n>AMRO-S models MAS routing as a semantic-conditioned path selection problem, enhancing routing performance through three key mechanisms.<n>Extensive experiments on five public benchmarks and high-concurrency stress tests demonstrate that AMRO-S consistently improves the quality--cost trade-off over strong routing baselines.
  arXiv  Detail & Related papers  (2026-03-13T12:26:05Z)
• CASTER: Breaking the Cost-Performance Barrier in Multi-Agent Orchestration via Context-Aware Strategy for Task Efficient Routing [25.48759875572515]
  CASTER (Context-Aware Strategy for Task Efficient Routing) is a lightweight router for dynamic model selection in graph-based MAS.<n>CASTER reduces inference cost by up to 72.4% compared to strong-model baselines.
  arXiv  Detail & Related papers  (2026-01-27T16:52:47Z)
• RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory [57.449129198822476]
  RCR is a role-aware context routing framework for multi-agent large language model (LLM) systems.<n>It dynamically selects semantically relevant memory subsets for each agent based on its role and task stage.<n>A lightweight scoring policy guides memory selection, and agent outputs are integrated into a shared memory store.
  arXiv  Detail & Related papers  (2025-08-06T21:59:34Z)
• Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning [27.70756702796812]
  We present textbf generalization-R1, a reinforcement learning framework that formulates multi-LLM routing and aggregation as a sequential decision process.<n>To facilitate learning, we employ a lightweight rule-based reward comprising format rewards, final outcome rewards, and a novel cost reward for optimizing the balance between performance and cost.
  arXiv  Detail & Related papers  (2025-06-10T17:56:45Z)
• Route-and-Reason: Scaling Large Language Model Reasoning with Reinforced Model Router [9.580226379350737]
  Multi-step reasoning has proven essential for enhancing the problem-solving capabilities of Large Language Models.<n>Yet, many reasoning steps are relatively simple and can be handled by more efficient smaller-scale language models.<n>We propose R2-Reasoner, a novel framework that enables collaborative reasoning across heterogeneous LLMs.
  arXiv  Detail & Related papers  (2025-06-06T09:18:56Z)
• RAGRouter: Learning to Route Queries to Multiple Retrieval-Augmented Language Models [45.58601993849455]
  Retrieval-Augmented Generation (RAG) significantly improves the performance of Large Language Models (LLMs) on knowledge-intensive tasks.<n>We observe that external documents dynamically affect LLMs' ability to answer queries, while existing routing methods exhibit suboptimal performance in RAG scenarios.<n>We propose RAG, a parametric RAG-aware routing design, which leverages document embeddings and RAG capability embeddings with contrastive learning to capture knowledge representation shifts.
  arXiv  Detail & Related papers  (2025-05-29T03:44:56Z)
• MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learning [71.90902837008278]
  We propose to incorporate neural architecture search (NAS) into general-purpose multi-task learning (GP-MTL) In order to adapt to different task combinations, we disentangle the GP-MTL networks into single-task backbones. We also propose a novel single-shot gradient-based search algorithm that closes the performance gap between the searched architectures.
  arXiv  Detail & Related papers  (2020-03-31T09:49:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.