arXiv Computation and Language
Rubric-Guided Process Reward for Stepwise Model Routing
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv Machine Learning
Oct 23
Route-and-Generate: KL-Regularized Router Improvement for Reasoning Routing in LLMs
Route-and-Generate (Rouge) is a hierarchical training framework that lets large language models decide how much reasoning to apply to each input. It separates reasoning effort from answer generation by using a routing policy that distributes a fixed sampling budget across different reasoning formats, while the base model is trained with GRPO and per-sample rewards. The method employs a rank‑based reward favoring shorter correct solutions and updates the router through a closed‑form KL‑regularized policy improvement, leading to more concise answers on easy tasks and longer reasoning on harder ones, thereby improving accuracy‑efficiency trade‑offs on multiple reasoning benchmarks.
arXiv Computation and Language
Oct 22
A Strong MoE Is All You Need for Process Supervision
The paper demonstrates that expert routing statistics in Mixture-of-Experts (MoE) models can serve as an intrinsic process-confidence signal, rivaling conventional output-logit confidence. Leveraging this insight, the authors develop RoCo-Rethink, which selectively regenerates uncertain reasoning steps, and RoCo-PRM, which automatically annotates reasoning trajectories using routing-derived step scores and distills them into a standalone process reward model. Across various MoE architectures and reasoning tasks, both methods outperform strong baselines and transfer effectively between models and tasks.
arXiv Machine Learning
Sep 22
AgentRouter: Heterogeneous Model Routing for Cost-Optimal Multi-Step Agentic Workflows
arXiv:2609.22951v1 Announce Type: cross Abstract: Enterprise agentic systems that route every trajectory step to a frontier model waste 60-80% of their inference budget on subtasks that smaller model...
arXiv Machine Learning
Aug 5
Beyond Solving: Prescriptive Probing for Neural Routing Solvers
arXiv:2602. 07216v2 Announce Type: replace Abstract: Neural combinatorial optimization (NCO) trains fast heuristics for routing problems, but planners often need more than a single solve: they ask which stop to drop, which transition to preserve, or which subset of stops to remove if a route is infeasible.
arXiv AI
Sep 23
ProcessLight: Process Supervision for Large Language Model Based Traffic Signal Control
arXiv:2609.22746v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently been introduced into traffic signal control (TSC) as decision agents due to their strengths in human-readabl...
arXiv AI
Oct 27
EvoRouter: Cost-Efficient Multi-Agent Routing via Insight-Guided On-Policy Distillation
arXiv:2610.35690v1 Announce Type: new Abstract: Serving web queries at scale with multi-agent systems requires jointly configuring large language models, collaboration modes, agent counts, interactio...