Cover Image

BudgetThinker: Empowering Budget-aware LLM Reasoning with Control Tokens

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wen, Hao, Wu, Xinrui, Sun, Yi, Zhang, Feifei, Chen, Liye, Wang, Jie, Liu, Yunxin, Liu, Yunhao, Zhang, Ya-Qin, Li, Yuanchun
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ParaThinker: Native Parallel Thinking as a New Paradigm to Scale LLM Test-time Compute
by: Wen, Hao, et al.
Published: (2025)

Token-Budget-Aware LLM Reasoning
by: Han, Tingxu, et al.
Published: (2024)

Reasoning in Token Economies: Budget-Aware Evaluation of LLM Reasoning Strategies
by: Wang, Junlin, et al.
Published: (2024)

SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning
by: Li, Zheng, et al.
Published: (2025)

Dual-Pool Token-Budget Routing for Cost-Efficient and Reliable LLM Serving
by: Liu, Xunzhuo, et al.
Published: (2026)

Token-Budget-Aware Pool Routing for Cost-Efficient LLM Inference
by: Chen, Huamin, et al.
Published: (2026)

Budget-aware Auto Optimizer Configurator
by: Liu, Kang, et al.
Published: (2026)

SwapMoE: Serving Off-the-shelf MoE-based Large Language Models with Tunable Memory Budget
by: Kong, Rui, et al.
Published: (2023)

ChainStream: An LLM-based Framework for Unified Synthetic Sensing
by: Liu, Jiacheng, et al.
Published: (2024)

AutoDroid: LLM-powered Task Automation in Android
by: Wen, Hao, et al.
Published: (2023)

An Empirical Study of LLM Reasoning Ability Under Strict Output Length Constraint
by: Sun, Yi, et al.
Published: (2025)

ORBIT: On-policy Exploration-Exploitation for Controllable Multi-Budget Reasoning
by: Liang, Kun, et al.
Published: (2026)

WebThinker: Empowering Large Reasoning Models with Deep Research Capability
by: Li, Xiaoxi, et al.
Published: (2025)

AgentProg: Empowering Long-Horizon GUI Agents with Program-Guided Context Management
by: Tian, Shizuo, et al.
Published: (2025)

BEAR: Budgeted Evidence Allocation for Multi-Document Reasoning
by: Sun, Lin, et al.
Published: (2026)

A First Look At Efficient And Secure On-Device LLM Inference Against KV Leakage
by: Yang, Huan, et al.
Published: (2024)

Inference-Time Budget Control for LLM Search Agents
by: Fang, Zhengru, et al.
Published: (2026)

Budget-Aware Anytime Reasoning with LLM-Synthesized Preference Data
by: Zhang, Xuanming, et al.
Published: (2026)

BAGEN: Are LLM Agents Budget-Aware?
by: Lin, Yuxiang, et al.
Published: (2026)

Hierarchical Budget Policy Optimization for Adaptive Reasoning
by: Lyu, Shangke, et al.
Published: (2025)

Budget-aware Query Tuning: An AutoML Perspective
by: Wu, Wentao, et al.
Published: (2024)

OmniRouter: Budget and Performance Controllable Multi-LLM Routing
by: Mei, Kai, et al.
Published: (2025)

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control
by: He, Xingyang, et al.
Published: (2025)

SD-E$^2$: Semantic Exploration for Reasoning Under Token Budgets
by: Mishra, Kshitij, et al.
Published: (2026)

Steering LLM Thinking with Budget Guidance
by: Li, Junyan, et al.
Published: (2025)

BRIDGE: Budget-aware Reasoning via Intermediate Distillation with Guided Examples
by: Le, Xuan-An, et al.
Published: (2025)

Conformal Thinking: Risk Control for Reasoning on a Compute Budget
by: Wang, Xi, et al.
Published: (2026)

LKV: End-to-End Learning of Head-wise Budgets and Token Selection for LLM KV Cache Eviction
by: Zhou, Enshuai, et al.
Published: (2026)

Simultaneous All-Pay Auctions with Budget Constraints
by: Liu, Yan, et al.
Published: (2025)

Multi-Metric Adaptive Experimental Design under Fixed Budget with Validation
by: Zhang, Qining, et al.
Published: (2025)

LLM-Explorer: Towards Efficient and Affordable LLM-based Exploration for Mobile Apps
by: Zhao, Shanhui, et al.
Published: (2025)

Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs
by: Alomrani, Mohammad Ali, et al.
Published: (2025)

Optimizing Anytime Reasoning via Budget Relative Policy Optimization
by: Qi, Penghui, et al.
Published: (2025)

CoT2-Meta: Budgeted Metacognitive Control for Test-Time Reasoning
by: Ma, Siyuan, et al.
Published: (2026)

Taming the Thinker: Conditional Entropy Shaping for Adaptive LLM Reasoning
by: Wei, Shuyu, et al.
Published: (2026)

Esc: An Early-stopping Checker for Budget-aware Index Tuning
by: Wang, Xiaoying, et al.
Published: (2025)

Budget-aware Test-time Scaling via Discriminative Verification
by: Montgomery, Kyle, et al.
Published: (2025)

LLM-as-Judge on a Budget
by: Saha, Aadirupa, et al.
Published: (2026)

Controlling Performance and Budget of a Centralized Multi-agent LLM System with Reinforcement Learning
by: Jin, Bowen, et al.
Published: (2025)

Adaptive Privacy Budgeting
by: Liang, Yuting, et al.
Published: (2026)