Paper Detail

RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing

Xiaohan Wang, Haozhen Zhang, Qingyuan Liu, Tao Feng, Wenya Wang

huggingface Score 11.5

Published 2026-10-19 · First seen 2026-10-23

General AI

Abstract

LLM routing dynamically selects and coordinates heterogeneous language models across diverse tasks. However, existing approaches are largely built around a predefined execution paradigm, such as single-round, multi-round, or agentic routing, which fixes how model calls are organized and limits adaptation to different query needs. We propose RouteWeaver, a unified routing framework that integrates these routing modes within a single LLM policy, jointly learning which mode to use and how to select models within that mode. To jointly optimize mode selection and within-mode execution, we develop COMET-GRPO (COordinated Mode-Execution Training), which decouples the trajectory-level advantage into separate signals for mode selection and within-mode execution, enabling more targeted credit assignment to each decision level. We further introduce progressive exploration, which gradually shifts training from externally assigned modes to autonomous selection, so that the router first learns how to execute each mode before deciding when to use it. We evaluate RouteWeaver across mathematics, coding, knowledge, logical reasoning, and factual recall. RouteWeaver achieves an average accuracy of 61.4%, an 11.03% relative improvement over the strongest baseline, and outperforms all compared baselines in each of the five domains. Ablations show that both COMET-GRPO and progressive exploration are important for adaptive routing; without progressive exploration, the routing policy collapses entirely to single-round execution.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{wang2026routeweaver,
  title = {RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing},
  author = {Xiaohan Wang and Haozhen Zhang and Qingyuan Liu and Tao Feng and Wenya Wang},
  year = {2026},
  abstract = {LLM routing dynamically selects and coordinates heterogeneous language models across diverse tasks. However, existing approaches are largely built around a predefined execution paradigm, such as single-round, multi-round, or agentic routing, which fixes how model calls are organized and limits adaptation to different query needs. We propose RouteWeaver, a unified routing framework that integrates these routing modes within a single LLM policy, jointly learning which mode to use and how to select},
  url = {https://huggingface.co/papers/2610.19705},
  keywords = {LLM routing, RouteWeaver, COMET-GRPO, progressive exploration, mode selection, trajectory-level advantage, credit assignment, code available, huggingface daily},
  eprint = {2610.19705},
  archiveprefix = {arXiv},
}

Metadata

{}