# Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards

arXiv: https://arxiv.org/abs/2505.18298 · HTML: https://mlsanity.com/paper/2505.18298/

## Key facts

- Cited by 20 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 31 of its 34 references that are in the map.
- First posted on arXiv 23 May 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 31)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems](https://mlsanity.com/paper/2402.14008/) (2024)
- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs](https://mlsanity.com/paper/2412.21187/) (2024)
- [Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models](https://mlsanity.com/paper/2503.16419/) (2025)
- [Training Language Models to Self-Correct via Reinforcement Learning](https://mlsanity.com/paper/2409.12917/) (2024)
- [L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning](https://mlsanity.com/paper/2503.04697/) (2025)
- [Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models](https://mlsanity.com/paper/2410.07985/) (2024)
- [O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning](https://mlsanity.com/paper/2501.12570/) (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)
- [Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems](https://mlsanity.com/paper/2412.09413/) (2024)
- [C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness](https://mlsanity.com/paper/2412.11664/) (2024)
- [Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning](https://mlsanity.com/paper/2502.18080/) (2025)
- [Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs](https://mlsanity.com/paper/2505.00127/) (2025)
- [Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost](https://mlsanity.com/paper/2407.19825/) (2024)
- [Self-Training Elicits Concise Reasoning in Large Language Models](https://mlsanity.com/paper/2502.20122/) (2025)
- [Efficient Reasoning Models: A Survey](https://mlsanity.com/paper/2504.10903/) (2025)
- [ShorterBetter: Guiding Reasoning Models to Find Optimal Inference Length for Efficient Reasoning](https://mlsanity.com/paper/2504.21370/) (2025)
- [Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging](https://mlsanity.com/paper/2503.20641/) (2025)

## Built on by (most cited first, 20 of 20)

- [GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization](https://mlsanity.com/paper/2601.05242/) (2026)
- [Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning](https://mlsanity.com/paper/2508.09726/) (2025)
- [Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models](https://mlsanity.com/paper/2508.02120/) (2025)
- [Leash: Adaptive Length Penalty and Reward Shaping for Efficient Large Reasoning Model](https://mlsanity.com/paper/2512.21540/) (2025)
- [RADAR: Reasoning-Ability and Difficulty-Aware Routing for Reasoning LLMs](https://mlsanity.com/paper/2509.25426/) (2025)
- [Think Dense, Not Long: Dynamic Decoupled Conditional Advantage for Efficient Reasoning](https://mlsanity.com/paper/2602.02099/) (2026)
- [Overthinking Reduction with Decoupled Rewards and Curriculum Data Scheduling](https://mlsanity.com/paper/2509.25827/) (2025)
- [Efficient Reasoning with Balanced Thinking](https://mlsanity.com/paper/2603.12372/) (2026)
- [Learning to Reason Efficiently with Discounted Reinforcement Learning](https://mlsanity.com/paper/2510.23486/) (2025)
- [System 1&2 Synergy via Dynamic Model Interpolation](https://mlsanity.com/paper/2601.21414/) (2026)
- [Beyond Penalizing Mistakes: Stabilizing Efficiency Training in Large Reasoning Models via Adaptive Correct-Only Rewards](https://mlsanity.com/paper/2606.22716/) (2026)
- [Step-GRPO: Internalizing Dynamic Early Exit for Efficient Reasoning](https://mlsanity.com/paper/2604.16890/) (2026)
- [Implicit Compression Regularization: Concise Reasoning via Internal Shorter Distributions in RL Post-Training](https://mlsanity.com/paper/2605.07316/) (2026)
- [Benchmarking and Evolving Reason-Reflect-Rectify for Reflective Visual Generation](https://mlsanity.com/paper/2605.19639/) (2026)
- [APR: Penalizing Structural Redundancy in Large Reasoning Models via Anchor-based Process Rewards](https://mlsanity.com/paper/2602.00760/) (2026)
- [Balancing the Reasoning Load: Difficulty-Differentiated Policy Optimization with Length Redistribution for Efficient and Robust Reinforcement Learning](https://mlsanity.com/paper/2603.18533/) (2026)
- [CLORE: Content-Level Optimization for Reasoning Efficiency](https://mlsanity.com/paper/2605.22211/) (2026)
- [CARE: Competence-Aware Reward Shaping for Adaptive Reasoning Length in Video-MLLMs](https://mlsanity.com/paper/2606.19927/) (2026)
- [Decomposer: Learning to Decompile Symbolic Music to Programs](https://mlsanity.com/paper/2607.01849/) (2026)
- [QLPO: Quadrant-weighted Sampling for Length-aware Policy Optimization](https://mlsanity.com/paper/2607.21793/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated strong reasoning abilities in mathematical tasks, often enhanced through reinforcement learning (RL). However, RL-trained models frequently produce unnecessarily long reasoning traces -- even for simple queries -- leading to increased inference costs and latency. While recent approaches attempt to control verbosity by adding length penalties to the reward function, these methods rely on fixed penalty terms that are hard to tune and cannot adapt as the model's reasoning capability evolves, limiting their effectiveness. In this work, we propose an adaptive reward-shaping method that enables LLMs to "think fast and right" -- producing concise outputs without sacrificing correctness. Our method dynamically adjusts the reward trade-off between accuracy and response length based on model performance: when accuracy is high, the length penalty increases to encourage faster length reduction; when accuracy drops, the penalty is relaxed to preserve correctness. This adaptive reward accelerates early-stage length reduction while avoiding over-compression in later stages. Experiments across multiple datasets show that our approach consistently and dramatically reduces reasoning length while largely maintaining accuracy, offering a new direction for cost-efficient adaptive reasoning in large-scale language models.