# BudgetThinker: Empowering Budget-aware LLM Reasoning with Control Tokens

arXiv: https://arxiv.org/abs/2508.17196 · HTML: https://mlsanity.com/paper/2508.17196/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 35 of its 48 references that are in the map.
- First posted on arXiv 24 Aug 2025.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 30 of 35)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs](https://mlsanity.com/paper/2412.21187/) (2024)
- [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [Process Reinforcement through Implicit Rewards](https://mlsanity.com/paper/2502.01456/) (2025)
- [LIMO: Less is More for Reasoning](https://mlsanity.com/paper/2502.03387/) (2025)
- [Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach](https://mlsanity.com/paper/2502.05171/) (2025)
- [L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning](https://mlsanity.com/paper/2503.04697/) (2025)
- [Chain of Draft: Thinking Faster by Writing Less](https://mlsanity.com/paper/2502.18600/) (2025)
- [TokenSkip: Controllable Chain-of-Thought Compression in LLMs](https://mlsanity.com/paper/2502.12067/) (2025)
- [Token-Budget-Aware LLM Reasoning](https://mlsanity.com/paper/2412.18547/) (2024)
- [Training Language Models to Reason Efficiently](https://mlsanity.com/paper/2502.04463/) (2025)
- [ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning](https://mlsanity.com/paper/2504.01296/) (2025)
- [Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.07572/) (2025)
- [Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models](https://mlsanity.com/paper/2503.20752/) (2025)
- [Learning How Hard to Think: Input-Adaptive Allocation of LM Computation](https://mlsanity.com/paper/2410.04707/) (2024)
- [Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning](https://mlsanity.com/paper/2408.13457/) (2024)
- [RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?](https://mlsanity.com/paper/2501.11284/) (2025)
- [Efficiently Scaling LLM Reasoning with Certaindex](https://mlsanity.com/paper/2412.20993/) (2024)
- [SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning](https://mlsanity.com/paper/2505.11274/) (2025)
- [THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models](https://mlsanity.com/paper/2504.13367/) (2025)
- [Pruning the Unsurprising: Efficient LLM Reasoning via First-Token Surprisal](https://mlsanity.com/paper/2508.05988/) (2025)
- [Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization](https://mlsanity.com/paper/2501.17974/) (2025)

## Built on by (most cited first, 29 of 29)

- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)
- [ParaThinker: Native Parallel Thinking as a New Paradigm to Scale LLM Test-time Compute](https://mlsanity.com/paper/2509.04475/) (2025)
- [CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents](https://mlsanity.com/paper/2511.02734/) (2025)
- [Single-Agent LLMs Outperform Multi-Agent Systems on Multi-Hop Reasoning Under Equal Thinking Token Budgets](https://mlsanity.com/paper/2604.02460/) (2026)
- [BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactions](https://mlsanity.com/paper/2510.05318/) (2025)
- [ContextBudget: Budget-Aware Context Management for Long-Horizon Search Agents](https://mlsanity.com/paper/2604.01664/) (2026)
- [From Efficiency to Adaptivity: A Deeper Look at Adaptive Reasoning in Large Language Models](https://mlsanity.com/paper/2511.10788/) (2025)
- [Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases](https://mlsanity.com/paper/2512.10398/) (2025)
- [BeyondBench: Contamination-Resistant Evaluation of Reasoning in Language Models](https://mlsanity.com/paper/2509.24210/) (2025)
- [Timely Machine: Awareness of Time Makes Test-Time Scaling Agentic](https://mlsanity.com/paper/2601.16486/) (2026)
- [Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners](https://mlsanity.com/paper/2509.26226/) (2025)
- [ReasoningFlow: Discourse Structures for Understanding LLM Reasoning Traces](https://mlsanity.com/paper/2606.05402/) (2026)
- [Beyond Penalizing Mistakes: Stabilizing Efficiency Training in Large Reasoning Models via Adaptive Correct-Only Rewards](https://mlsanity.com/paper/2606.22716/) (2026)
- [SeqRoute: Global Budget-Aware Sequential LLM Routing via Offline Reinforcement Learning](https://mlsanity.com/paper/2605.25424/) (2026)
- [One Policy, Any Budget: Internalizing Budget-Aware Search via Reinforcement Learning](https://mlsanity.com/paper/2609.00813/) (2026)
- [Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning](https://mlsanity.com/paper/2606.03965/) (2026)
- [Shorter Reasoning, Earlier Answers? An Evaluation of Reasoning Interfaces](https://mlsanity.com/paper/2608.03401/) (2026)
- [Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions](https://mlsanity.com/paper/2608.07968/) (2026)
- [Think Longer to Explore Deeper: Learn to Explore In-Context via Length-Incentivized Reinforcement Learning](https://mlsanity.com/paper/2602.11748/) (2026)
- [Apriel-Reasoner: RL Post-Training for General-Purpose and Efficient Reasoning](https://mlsanity.com/paper/2604.02007/) (2026)
- [Behavior Cue Reasoning: Monitorable Reasoning Improves Efficiency and Safety through Oversight](https://mlsanity.com/paper/2605.07021/) (2026)
- [Nice Fold or Hero Call: Learning Budget-Efficient Thinking for Adaptive Reasoning](https://mlsanity.com/paper/2605.11625/) (2026)
- [LLM Code Smells: A Taxonomy and Detection Approach](https://mlsanity.com/paper/2605.22976/) (2026)
- [AdaTurn: Budget-Aware Test-Time Scaling for Active Visual Perception Agents](https://mlsanity.com/paper/2607.14547/) (2026)
- [Budget-Aware LLM Discovery via Cost-Calibrated Frontier Utility](https://mlsanity.com/paper/2607.26828/) (2026)
- [Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs](https://mlsanity.com/paper/2608.12781/) (2026)
- [LIMBO: Lifelong Inference-Time Memory and Budget Optimization for LLM Agents](https://mlsanity.com/paper/2609.14138/) (2026)
- [PAGE: Partition-Aware Gated KV-Cache Eviction](https://mlsanity.com/paper/2609.22157/) (2026)
- [Diversity Combining for Multi-Path LLM Reasoning](https://mlsanity.com/paper/2609.38829/) (2026)

## Abstract (arXiv)

Recent advancements in Large Language Models (LLMs) have leveraged increased test-time computation to enhance reasoning capabilities, a strategy that, while effective, incurs significant latency and resource costs, limiting their applicability in real-world time-constrained or cost-sensitive scenarios. This paper introduces BudgetThinker, a novel framework designed to empower LLMs with budget-aware reasoning, enabling precise control over the length of their thought processes. We propose a methodology that periodically inserts special control tokens during inference to continuously inform the model of its remaining token budget. This approach is coupled with a comprehensive two-stage training pipeline, beginning with Supervised Fine-Tuning (SFT) to familiarize the model with budget constraints, followed by a curriculum-based Reinforcement Learning (RL) phase that utilizes a length-aware reward function to optimize for both accuracy and budget adherence. We demonstrate that BudgetThinker significantly surpasses strong baselines in maintaining performance across a variety of reasoning budgets on challenging mathematical benchmarks. Our method provides a scalable and effective solution for developing efficient and controllable LLM reasoning, making advanced models more practical for deployment in resource-constrained and real-time environments.