mlsanityData to 7 Oct 2026

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

arXiv 2602.11541 ↗First posted 12 Feb 2026cs.AI cs.LGcited by 8

On the map: LLM agents and tool use → Tool learning and function calling

Abstract (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.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 50 of its 65 references that are in the map. First posted on arXiv 12 Feb 2026.

Builds on

50 of 65 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025StableToolBench-MirrorAPI: Modeling Tool Environments as Mirrors of 7,000+ Real-World APIs26 Mar
  2. 2025Alignment for Efficient Tool Calling of Large Language Models9 Mar
  3. 2024StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models12 Mar
  4. 2024Budget-Constrained Tool Learning with Planning25 Feb
  5. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs31 Jul
  6. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases8 Jun

Other references · 44

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  6. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  7. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  8. 2017On Calibration of Modern Neural Networkscited by 4,860
  9. 2024Qwen2.5 Technical Reportcited by 4,713
  10. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,551
  11. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
  12. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,628
32 more
  1. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,442
  2. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  3. 2017Mixed Precision Trainingcited by 1,135
  4. 2023Accelerating Large Language Model Decoding with Speculative Samplingcited by 975
  5. 2023Reasoning with Language Model is Planning with World Modelcited by 846
  6. 2025UI-TARS: Pioneering Automated GUI Interaction with Native Agentscited by 584
  7. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Modelscited by 551
  8. 2025WebThinker: Empowering Large Reasoning Models with Deep Research Capabilitycited by 320
  9. 2024Training Software Engineering Agents and Verifiers with SWE-Gymcited by 300
  10. 2025TokenSkip: Controllable Chain-of-Thought Compression in LLMscited by 246
  11. 2025AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoningcited by 234
  12. 2025WebSailor: Navigating Super-human Reasoning for Web Agentcited by 218
  13. 2025ZeroSearch: Incentivize the Search Capability of LLMs without Searchingcited by 203
  14. 2025An Illusion of Progress? Assessing the Current State of Web Agentscited by 165
  15. 2025Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RLcited by 144
  16. 2024MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolutioncited by 132
  17. 2025LightThinker: Thinking Step-by-Step Compressioncited by 104
  18. 2025Reinforcement Learning for Long-Horizon Interactive LLM Agentscited by 103
  19. 2025VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Usecited by 92
  20. 2025AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learningcited by 68
  21. 2025Towards General Agentic Intelligence via Environment Scalingcited by 51
  22. 2025Budget-Aware Tool Use Enables Effective Agent Scalingcited by 42
  23. 2024Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Searchcited by 38
  24. 2024SAM Decoding: Speculative Decoding via Suffix Automatoncited by 38
  25. 2025RLFactory: A Plug-and-Play Reinforcement Learning Post-Training Framework for LLM Multi-Turn Tool-Usecited by 17
  26. 2025SSRL: Self-Search Reinforcement Learningcited by 13
  27. 2025GTM: Simulating the World of Tools for AI Agentscited by 12
  28. 2025Optimizing Agentic Language Model Inference via Speculative Tool Callscited by 11
  29. 2026Computer Environments Elicit General Agentic Intelligence in LLMscited by 11
  30. 2026SearchGym: Bootstrapping Real-World Search Agents via Cost-Effective and High-Fidelity Environment Simulationcited by 5
  31. 2025Foundation Models as World Models: A Foundational Study in Text-Based GridWorldscited by 1
  32. 2026A Benchmark for Language Models in Real-World System Buildingcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 8.

8 papers.

  1. 2026BAGEN: Are LLM Agents Budget-Aware?cited by 12
  2. 2026On Time, Within Budget: Constraint-Driven Online Resource Allocation for Agentic Workflowscited by 3
  3. 2026Bridging the Agent-World Gap: Text World Models for LLM-based Agentscited by 3
  4. 2026AllocBench: Measuring Online Tool Allocation Capability in LLM Agentscited by 2
  5. 2026ZEBRA: Zero-shot Budgeted Resource Allocation for LLM Orchestrationcited by 1
  6. 2026Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Cachingcited by 1
  7. 2026Cost-Utility Alignment in LLM Agent Trajectories:Profiling,Attribution,Diagnosis,Adaptation,and Evaluationcited by 1
  8. 2026When Should Agents Check External State? Budgeting Observations for Stored Intentionscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents
  2. 2024CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning
  3. 2026Long-Horizon Plan Execution in Large Tool Spaces through Entropy-Guided Branching
  4. 2026ToolAnchor: Anchoring Counterfactual Context to Boost Agentic Tool-use Capability
  5. 2026Internalizing Tool Knowledge in Small Language Models via QLoRA Fine-Tuning
  6. 2026Toward Efficient Agents: Memory, Tool learning, and Planning
  7. 2026EcoAgent-Bench: Evaluating Economic Decision-Making in Budget-Constrained LLM Agents
  8. 2026ToolTree: Efficient LLM Agent Tool Planning via Dual-Feedback Monte Carlo Tree Search and Bidirectional Pruning