# e1: Learning Adaptive Control of Reasoning Effort

arXiv: https://arxiv.org/abs/2510.27042 · HTML: https://mlsanity.com/paper/2510.27042/

## Key facts

- Cited by 6 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 20 of its 26 references that are in the map.
- First posted on arXiv 30 Oct 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, 20 of 20)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning](https://mlsanity.com/paper/2503.04697/) (2025)
- [Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models](https://mlsanity.com/paper/2408.00724/) (2024)
- [Training Language Models to Reason Efficiently](https://mlsanity.com/paper/2502.04463/) (2025)
- [GRPO-LEAD: A Difficulty-Aware Reinforcement Learning Approach for Concise Mathematical Reasoning in Language Models](https://mlsanity.com/paper/2504.09696/) (2025)
- [Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation](https://mlsanity.com/paper/2410.02725/) (2024)
- [Just Enough Thinking: Efficient Reasoning with Adaptive Length Penalties Reinforcement Learning](https://mlsanity.com/paper/2506.05256/) (2025)
- [ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models](https://mlsanity.com/paper/2508.18773/) (2025)
- [AI Agents as Universal Task Solvers](https://mlsanity.com/paper/2510.12066/) (2025)
- [LATTS: Locally Adaptive Test-Time Scaling](https://mlsanity.com/paper/2509.20368/) (2025)

## Built on by (most cited first, 6 of 6)

- [Mull-Tokens: Modality-Agnostic Latent Thinking](https://mlsanity.com/paper/2512.10941/) (2025)
- [Thinking Without Words: Efficient Latent Reasoning with Abstract Chain-of-Thought](https://mlsanity.com/paper/2604.22709/) (2026)
- [Re-FORC: Adaptive Reward Prediction for Efficient Chain-of-Thought Reasoning](https://mlsanity.com/paper/2511.02130/) (2025)
- [ExecTune: Effective Steering of Black-Box LLMs with Guide Models](https://mlsanity.com/paper/2604.09741/) (2026)
- [LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models](https://mlsanity.com/paper/2605.09806/) (2026)
- [One Size Does Not Fit All! Dynamic Retriever and Generator Selection for RAG](https://mlsanity.com/paper/2609.17709/) (2026)

## Abstract (arXiv)

Increasing the thinking budget of AI models can significantly improve accuracy, but not all questions warrant the same amount of reasoning. Users may prefer to allocate different amounts of reasoning effort depending on how they value output quality versus latency and cost. To leverage this tradeoff effectively, users need fine-grained control over the amount of thinking used for a particular query, but few approaches enable such control. Existing methods require users to specify the absolute number of desired tokens, but this requires knowing the difficulty of the problem beforehand to appropriately set the token budget for a query. To address these issues, we propose textitAdaptive Effort Control, a self-adaptive reinforcement learning method that trains models to use a user-specified fraction of tokens relative to the current average chain-of-thought length for each query. This approach eliminates dataset- and phase-specific hyperparameter tuning. Users can dynamically adjust the cost-accuracy trade-off through a continuous effort parameter specified at inference time. We observe that the model automatically learns to allocate resources proportionally to the task difficulty. Across model scales ranging from 1.5B to 32B parameters, our approach reduces chain-of-thought length on math tasks by 1.9-3.7x at matched accuracy relative to the base model used for RL training.