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.
By Tien-Phat Nguyen, Truong Nguyen, Thanh-Thien Le, Hoang Phan, Thien Huu Nguyen, Linh Ngo Van, Trung Le
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.
By Guanzhi Deng, Zengyan Liu, Haibo Wang, Kuan Wu, Shing Yin Wong, Sichun Luo, Zhuoran Wang, Linqi Song
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...
By Rudrendu Kumar Paul, Sourav Nandy
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.
By Reuben Narad, L\'eonard Boussioux, Michael Wagner
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...
By Huaitao Zhao, Tianlong Zhou, Weijie Wang, Jiasheng Shi, Weixiong Rao
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...
By Yitao Xiao, Xu Zhang, Ye Cheng, Shaoyong Guo, Yan Sun, Ziyue Zhu, Sitao Xie, Guo Tong, Haoran Luo
arXiv:2606. 12479v1 Announce Type: cross Abstract: Large language model (LLM) routing has emerged as an effective paradigm for leveraging the complementary strengths of multiple LLMs through dynamic model and reasoning-strategy selection.
By Qihang Yu, Hanwen Tong, Zhengqi Zhang, Bo Zheng, Feng Wei, Shengyu Zhang, Zemin Liu, Fei Wu
arXiv:2607. 22465v1 Announce Type: cross Abstract: Routing to select large language models (LLMs) with different cost-quality trade-offs has become a fundamental deployment feature of enterprise AI.
By Ritik Raj, Souvik Kundu, Sarbartha Banerjee, Dheemanth Joshi, Ishita Vohra, Tushar Krishna
arXiv:2607. 11399v1 Announce Type: cross Abstract: Large language model agents are increasingly executed not by a single model call, but by an execution harness that manages observation, context, control, action, state, and verification.
By Xinchen Liu, Hang Zhou, Yingjie Zong, Yuchuan Tian, Liuyang Song, Shuo Zhang, Yulong Li, Wei He, Mengyu Zheng, Runke Liu, Siyang Cheng, Xiang Kuang, Hailin Hu, Kai Han, Yunhe Wang
arXiv:2606. 05464v1 Announce Type: new Abstract: Verifiable reward training has improved mathematical and coding reasoning, but these domains capture only part of step-by-step decision making.
By Nicol\'as Astorga, Nabeel Seedat, Mihaela van der Schaar
arXiv:2610.19705v1 Announce Type: new
Abstract: LLM routing dynamically selects and coordinates heterogeneous language models across diverse tasks. However, existing approaches are largely built arou...
By Xiaohan Wang, Haozhen Zhang, Qingyuan Liu, Tao Feng, Wenya Wang
The paper introduces Multi-Level Reasoning (MLR), a two-level stochastic framework that separates long chain-of-thought generation into a high-level planner producing structured step descriptors and a low-level executor generating detailed reasoning. MLR replaces single-policy reinforcement learning with an iterative Step‑DPO preference optimization that uses Twisted Sequential Monte Carlo for scalable, stepwise supervision, improving training stability and accuracy. Experiments on math, science, and logic benchmarks show that MLR outperforms both supervised fine‑tuning and strong RL baselines while maintaining robustness over extended reasoning horizons.
By Siheng Xiong, Ali Payani, Faramarz Fekri