English
Related papers

Related papers: Budget-Aware Agentic Routing via Boundary-Guided T…

200 papers

Large Language Models (LLMs) have achieved remarkable performance in Machine Translation (MT), but deploying them at scale remains prohibitively expensive. A widely adopted remedy is the hybrid system paradigm, which balances cost and…

Computation and Language · Computer Science 2026-04-27 Yingfeng Luo , Hongyu Liu , Dingyang Lin , Kaiyan Chang , Chenglong Wang , Bei Li , Quan Du , Tong Xiao , Jingbo Zhu

Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that interleaves thoughts and tool calls under full context; this…

Artificial Intelligence · Computer Science 2025-10-08 Zhuofeng Li , Haoxiang Zhang , Seungju Han , Sheng Liu , Jianwen Xie , Yu Zhang , Yejin Choi , James Zou , Pan Lu

The proliferation of large language models (LLMs) with varying computational costs and performance profiles presents a critical challenge for scalable, cost-effective deployment in real-world applications. We introduce a unified routing…

Large Language Models (LLMs) have shown remarkable performance on general Question Answering (QA), yet they often struggle in domain-specific scenarios where accurate and up-to-date information is required. Retrieval-Augmented Generation…

Computation and Language · Computer Science 2026-02-13 Haoyue Bai , Haoyu Wang , Shengyu Chen , Zhengzhang Chen , Lu-An Tang , Wei Cheng , Haifeng Chen , Yanjie Fu

Test-time scaling has become a dominant paradigm for improving LLM agent reliability, yet current approaches treat compute as an abundant resource, allowing agents to exhaust token and tool budgets on redundant steps or dead-end…

Machine Learning · Computer Science 2026-03-16 Yushu Li , Wenlong Deng , Jiajin Li , Xiaoxiao Li

Prompt routing dynamically selects the most appropriate large language model from a pool of candidates for each query, optimizing performance while managing costs. As model pools scale to include dozens of frontier models with narrow…

Computation and Language · Computer Science 2026-03-24 Yunyi Zhang , Soji Adeshina , Sheng Guan , Ashwin Ganesh , Zhen Han , Vassilis N. Ioannidis , Huzefa Rangwala , George Karypis

Complex agentic AI systems, powered by a coordinated ensemble of Large Language Models (LLMs), tool and memory modules, have demonstrated remarkable capabilities on intricate, multi-turn tasks. However, this success is shadowed by…

Computation and Language · Computer Science 2026-01-07 Guibin Zhang , Haiyang Yu , Kaiming Yang , Bingli Wu , Fei Huang , Yongbin Li , Shuicheng Yan

Tool-using large language model (LLM) agents often face a fundamental tension between answer quality and execution cost. Fixed workflows are stable but inflexible, while free-form multi-step reasoning methods such as ReAct may improve task…

Artificial Intelligence · Computer Science 2026-03-23 Boyan Liu , Gongming Zhao , Hongli Xu

Large language models (LLMs) deliver superior performance but require substantial computational resources and operate with relatively low efficiency, while smaller models can efficiently handle simpler tasks with fewer resources. LLM…

Databases · Computer Science 2025-12-01 Kai Mei , Wujiang Xu , Minghao Guo , Shuhang Lin , Yongfeng Zhang

Recent advancements in agentic test-time scaling allow models to gather environmental feedback before committing to final actions. A key limitation of existing methods is that they typically employ undifferentiated exploration strategies,…

Artificial Intelligence · Computer Science 2026-05-13 Xingyuan Hua , Sheng Yue , Ju Ren

Large Language Model (LLM) serving systems must balance task performance against monetary cost. Two prominent optimization techniques have emerged independently: LLM routing, which directs each query to the most cost-effective model in a…

Databases · Computer Science 2026-05-28 Haotian Xu , Kangfei Zhao , Jiadong Xie

How should an agent decide when and how to plan? A dominant approach builds agents as reactive policies with adaptive computation (e.g., chain-of-thought), trained end-to-end expecting planning to emerge implicitly. Without control over the…

Artificial Intelligence · Computer Science 2026-05-22 Mingkai Deng , Jinyu Hou , Lara Sá Neves , Varad Pimpalkhute , Taylor W. Killian , Zhengzhong Liu , Eric P. Xing

Agents built on large language models (LLMs) rely on a range of reliability techniques, including retry, majority voting, and self-consistency, that have been developed in parallel rather than within a common analytical framework. We…

Machine Learning · Computer Science 2026-05-12 Hamed Omidvar , Vahideh Akhlaghi

We study the problem of modeling a population of agents pursuing unknown goals subject to unknown computational constraints. In standard models of bounded rationality, sub-optimal decision-making is simulated by adding homoscedastic noise…

Artificial Intelligence · Computer Science 2023-12-08 Athul Paul Jacob , Abhishek Gupta , Jacob Andreas

Reinforcement Learning (RL) has traditionally focused on training specialized agents to optimize predefined reward functions within narrowly defined environments. However, the advent of powerful Large Language Models (LLMs) and increasingly…

Artificial Intelligence · Computer Science 2026-05-18 Fangming Cui , Ruixiao Zhu , Cheng Fang , Sunan Li , Jiahong Li

Large language models (LLMs) have demonstrated remarkable capabilities across a range of text-generation tasks. However, LLMs still struggle with problems requiring multi-step decision-making and environmental feedback, such as online…

Artificial Intelligence · Computer Science 2025-02-18 Zhenfang Chen , Delin Chen , Rui Sun , Wenjun Liu , Chuang Gan

Recent deep-thinking large language models often reason extensively to improve performance, but such lengthy reasoning is not always desirable, as it incurs excessive inference costs with disproportionate performance gains. Controlling…

Computation and Language · Computer Science 2025-06-17 Junyan Li , Wenshuo Zhao , Yang Zhang , Chuang Gan

This paper introduces a multi-agent framework guided by Large Language Models (LLMs) to assist in the early stages of engineering design, a phase often characterized by vast parameter spaces and inherent uncertainty. Operating under a…

Artificial Intelligence · Computer Science 2026-04-21 Varun Kumar , George Em Karniadakis

In cloud manufacturing, unmanned aerial vehicles (UAVs) can support both product collection and mobile edge computing (MEC). This joint operation forms a hybrid scheduling problem, where physical logistics decisions are coupled with…

Artificial Intelligence · Computer Science 2026-05-14 Hanwen Zhang , Dusit Niyato , Wei Zhang , Xin Lou , Malcolm Yoke Hean Low

LLM routing aims to select the most appropriate model for each query, balancing competing performance metrics such as accuracy and cost across a pool of language models. Prior approaches typically adopt a decoupled strategy, where the…

Artificial Intelligence · Computer Science 2026-01-05 Asterios Tsiourvas , Wei Sun , Georgia Perakis