Budget-Constrained Agentic Large Language Models: Intention-Based Planning for Costly Tool Use

2026-02-12 · Hanbing Liu, Chunhao Tian, Nan An, Ziyuan Wang, Pinyan Lu, Changyuan Yu, Qi Qi arxiv

We study budget-constrained tool-augmented agents, where a large language model must solve multi-step tasks by invoking external tools under a strict monetary budget. We formalize this setting as sequential decision making in context space with priced and stochastic tool executions, making direct planning intractable due to massive state-action spaces, high variance of outcomes and prohibitive exploration cost. To address these challenges, we propose INTENT, an inference-time planning framework that leverages an intention-aware hierarchical world model to anticipate future tool usage, risk-calibrated cost, and guide decisions online. Across cost-augmented StableToolBench, INTENT strictly enforces hard budget feasibility while substantially improving task success over baselines, and remains robust under dynamic market shifts such as tool price changes and varying budgets.

📄 PDF Abstract BibTeX arXiv:2602.11541

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Making

Quantifying the Accuracy and Cost Impact of Design Decisions in Budget-Constrained Agentic LLM Search

2026-03-09 · Kyle McCleary, James Ghawaly arxiv

Agentic Retrieval-Augmented Generation (RAG) systems combine iterative search, planning prompts, and retrieval backends, but deployed settings impose explicit budgets on tool calls and completion tokens. We present a con…

ReflectVLN: Training Vision-Language Navigation Agents with Reflective Reasoning

2026-07-14 · Jiahang Wang, Yirong Yang, Yanqing Zhu, Minghua Luo 외 arxiv

Existing vision-language navigation methods often couple a VLM with waypoint decoders to produce multi-step action plans, but they typically lack an explicit closed-loop mechanism for tracking semantic progress, diagnosi…

Vision-Language Navigation

Timely Machine: Awareness of Time Makes Test-Time Scaling Agentic

2026-01-23 · Yichuan Ma, Linyang Li, Yongkang chen, Peiji Li 외 arxiv

As large language models (LLMs) increasingly tackle complex reasoning tasks, test-time scaling has become critical for enhancing capabilities. However, in agentic scenarios with frequent tool calls, the traditional gener…

Reinforcement Learning

Tool-Schema Compression Enables Agentic RAG Under Constrained Context Budgets

2026-05-24 · Furkan Sakizli arxiv

Agentic RAG systems that equip language models with dozens to hundreds of tool definitions face a critical resource conflict: tool schemas consume the same context window needed for retrieval-augmented generation. We pre…

On Time, Within Budget: Constraint-Driven Online Resource Allocation for Agentic Workflows

2026-05-07 · Xinglin Wang, Zishen Liu, Shaoxiong Feng, Peiwen Yuan 외 arxiv

Agentic systems increasingly solve complex user requests by executing orchestrated workflows, where subtasks are assigned to specialized models or tools and coordinated according to their dependencies. While recent work …