The paper introduces OMVV, an online multi-verifier algorithm that maintains a pool of weak verifiers with varying costs and performance. It adaptively selects a verifier each round using an online score combiner and exponential-weights routing, providing distribution-free guarantees on false-accept and false-reject rates. Experiments on reasoning benchmarks show OMVV achieves higher accuracy at lower verification cost than any single fixed verifier across different budgets.
By Erfan Hajihashemi, Yanning Shen
arXiv:2510. 03243v3 Announce Type: replace-cross Abstract: Efficient scheduling of large language model (LLM) inference tasks is critical for achieving low latency and high throughput, a challenge that is becoming increasingly acute with the rise of reasoning-capable LLMs whose generation lengths are highly variable.
By Yiheng Tao, Yihe Zhang, Matthew Dearing, Xin Wang, Yuping Fan, Michael E. Papka, Zhiling Lan
arXiv:2606. 27743v1 Announce Type: cross Abstract: Large Language Models (LLMs) inference is typically deployed under a static resource assumption, where models execute a fixed computational graph regardless of the runtime environment.
By Yuhang Chen, Jinhao Duan, Ruichen Zhang, Mingfu Liang, Xiaohan Wei, Yunchen Pu, Fei Tian, Chonglin Sun, Parish Aggarwal, Frank Shyu, Luke Simon, Sandeep Pandey, Tianlong Chen, Xi Liu
arXiv:2601. 10560v2 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) coordinate multiple LLM-powered agents through structured workflows, gaining reasoning power but incurring high inference latency from multi-step execution and repeated model invocations.
By Xi Shi, Mengxin Zheng, Qian Lou
arXiv:2606. 17489v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly deployed in edge-cloud inference systems to handle diverse user tasks with heterogeneous accuracy, latency, and cost profiles.
By Yin Huang, Qingsong Liu, Jie Xu
arXiv:2608.25992v2 Announce Type: replace
Abstract: Multi-agent large language model (LLM) workflows have emerged as a powerful paradigm for solving complex, open-ended tasks through collaborative re...
By Songyuan Li, Ahmed M. Abdelmoniem, Shiqiang Wang
arXiv:2606. 04402v1 Announce Type: new Abstract: Modern reasoning models can allocate different amounts of test-time computation, such as thinking tokens, model calls, or compute budget, to different tasks.
By Jingbo Wen, Liang He, Ziqi He
The paper introduces compositional online learning for semantic data processing systems, addressing the high cost and latency of large language model (LLM) calls. It proposes a framework that combines lightweight online-learning components—such as memoization, per-call filter-ordering, and per-batch cascade-routing—within the LLM call boundary, allowing each component to make real-time decisions and update its models without exceeding the LLM round-trip time. A production case study in Cortex AISQL demonstrates that these components can reduce the per-row LLM cost by up to 8× compared to a baseline workload.
By Pawe\l{} Liskowski, Fuheng Zhao, Benjamin Han, Anupam Datta, Dimitris Tsirogiannis
arXiv:2608. 09217v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a central post-training paradigm for eliciting reasoning capabilities in large language models, yet uniform task sampling allocates compute without regard to differences in how tasks respond to optimization.
By Ting Zhou, Zhenqing Ling, Daoyuan Chen, Qianli Shen, Yilun Huang, Ying Shen, Yaliang Li
The paper introduces SCX Router, a lightweight GLiClass-based model selector that assigns suitability scores to inference-time language models without autoregressive generation. It uses a 0.6B-parameter Qwen3 decoder with a shallow bidirectional scorer, preserving a text-only key–value cache across sessions and predicting task attributes such as type, difficulty, and expected output length. The authors build a comprehensive task ontology with 23 families, 115 types, and 1,173 synthetic examples, generating 150,000 verifier-scored tasks to train the router, which outperforms baseline models on LiveBench subsets with a top‑1 score of 0.707 versus 0.696 for the strongest fixed model.
By Ihor Stepanov, Aleksandr Smechov, Mykhailo Shtopko, Dmytro Vodianytskyi, Oleksandr Lukashov
Online Self-Weighted Fine‑Tuning (OSW‑FT) augments standard supervised fine‑tuning by adding online, trajectory‑level weighting: for each query the model estimates its current success rate from a small number of inference‑only rollouts and rescales the SFT loss accordingly. The method keeps the optimization direction anchored to the expert trajectory while adapting the update magnitude online, and it is shown to be unbiased for any finite rollout count with a convergence analysis. Across Qwen3 models from 0.6B to 4B, OSW‑FT consistently outperforms plain SFT on challenging benchmarks such as AIME, achieving a favorable compute‑performance trade‑off with only two online rollouts.
By Haiquan Wen, Yiwei He, Bei Peng, Guangliang Cheng
The paper surveys efficient reasoning in large language models, contrasting fast intuitive (System 1) and slow deep (System 2) reasoning. It analyzes why System 2 is computationally costly yet more accurate, and why System 1 is efficient but less effective. The survey covers causes of inefficiency, patterns of reasoning behavior, and potential solutions to balance performance and computational budgets, offering actionable insights and an open‑source repository for ongoing research.
By Rui Wang, Hongru Wang, Boyang Xue, Jianhui Pang, Shudong Liu, Yi Chen, Jiahao Qiu, Derek Fai Wong, Heng Ji, Kam-Fai Wong