Spend Less, Reason Better: Budget-Aware Value Tree Search for LLM Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Yushu, Deng, Wenlong, Li, Jiajin, Li, Xiaoxiao
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

Policy Guided Tree Search for Enhanced LLM Reasoning
by: Li, Yang
Published: (2025)

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

BudgetThinker: Empowering Budget-aware LLM Reasoning with Control Tokens
by: Wen, Hao, et al.
Published: (2025)

Spend Search Where It Pays: Value-Guided Structured Sampling and Optimization for Generative Recommendation
by: Jiang, Jie, et al.
Published: (2026)

Textual Equilibrium Propagation for Deep Compound AI Systems
by: Chen, Minghui, et al.
Published: (2026)

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search
by: Zhang, Yifei, et al.
Published: (2026)

Spend Less, Fit Better: Budget-Efficient Scaling Law Fitting via Active Experiment Selection
by: Li, Sijie, et al.
Published: (2026)

Revisiting Tree Search for LLMs: Gumbel and Sequential Halving for Budget-Scalable Reasoning
by: Ugadiarov, Leonid, et al.
Published: (2026)

Better LLM Reasoning via Dual-Play
by: Zhang, Zhengxin, et al.
Published: (2025)

LLM-Assisted Content Conditional Debiasing for Fair Text Embedding
by: Deng, Wenlong, et al.
Published: (2024)

Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers
by: Sareen, Kusha, et al.
Published: (2025)

Tree Search for LLM Agent Reinforcement Learning
by: Ji, Yuxiang, et al.
Published: (2025)

OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in LLM Reasoning
by: Li, Yu, et al.
Published: (2026)

RaaS: Reasoning-Aware Attention Sparsity for Efficient LLM Reasoning
by: Hu, Junhao, et al.
Published: (2025)

Graph Inference Towards ICD Coding
by: Deng, Xiaoxiao
Published: (2026)

DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned Models
by: Deng, Wenlong, et al.
Published: (2024)

Efficient LLM Reasoning via Variational Posterior Guidance with Efficiency Awareness
by: Chen, Zizhao, et al.
Published: (2026)

Scaling-Aware Adapter for Structure-Grounded LLM Reasoning
by: Jing, Zihao, et al.
Published: (2026)

Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory
by: Zhang, Haozhen, et al.
Published: (2026)

A Discordance-Aware Multimodal Framework with Multi-Agent Clinical Reasoning
by: Ahadian, Pegah, et al.
Published: (2026)

AgentKit: Structured LLM Reasoning with Dynamic Graphs
by: Wu, Yue, et al.
Published: (2024)

Learning to Spend: Model Predictive Control for Budgeting under Non-Stationary Returns
by: Pathak, Nilavra, et al.
Published: (2026)

Less Greedy Equivalence Search
by: Ejaz, Adiba, et al.
Published: (2025)

HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents
by: Li, Guankai, et al.
Published: (2026)

Improve Value Estimation of Q Function and Reshape Reward with Monte Carlo Tree Search
by: Li, Jiamian
Published: (2024)

Unsupervised Outlier Detection in Audit Analytics: A Case Study Using USA Spending Data
by: Li, Buhe, et al.
Published: (2025)

Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning
by: Liu, Yong, et al.
Published: (2024)

BPO: Staying Close to the Behavior LLM Creates Better Online LLM Alignment
by: Xu, Wenda, et al.
Published: (2024)

The Larger the Better? Improved LLM Code-Generation via Budget Reallocation
by: Hassid, Michael, et al.
Published: (2024)

OPT-BENCH: Evaluating LLM Agent on Large-Scale Search Spaces Optimization Problems
by: Li, Xiaozhe, et al.
Published: (2025)

RF-Agent: Automated Reward Function Design via Language Agent Tree Search
by: Gao, Ning, et al.
Published: (2026)

SeqRoute: Global Budget-Aware Sequential LLM Routing via Offline Reinforcement Learning
by: Xu, Zhongling, et al.
Published: (2026)

Learning Evolving Latent Strategies for Multi-Agent Language Systems without Model Fine-Tuning
by: Tang, Wenlong
Published: (2025)

Not All Negative Samples Are Equal: LLMs Learn Better from Plausible Reasoning
by: Di, Zixiang, et al.
Published: (2026)

Less is More: Recursive Reasoning with Tiny Networks
by: Jolicoeur-Martineau, Alexia
Published: (2025)

Language Models can Self-Improve at State-Value Estimation for Better Search
by: Mendes, Ethan, et al.
Published: (2025)

Is More Context Always Better? Examining LLM Reasoning Capability for Time Interval Prediction
by: Cao, Yanan, et al.
Published: (2026)

Capacity-Aware Planning and Scheduling in Budget-Constrained Multi-Agent MDPs: A Meta-RL Approach
by: Vora, Manav, et al.
Published: (2024)

Less is More: Empowering GUI Agent with Context-Aware Simplification
by: Chen, Gongwei, et al.
Published: (2025)