# ThinkLess: A Training-Free Inference-Efficient Method for Reducing Reasoning Redundancy

arXiv: https://arxiv.org/abs/2505.15684 · HTML: https://mlsanity.com/paper/2505.15684/

## Key facts

- Cited by 17 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 28 of its 40 references that are in the map.
- First posted on arXiv 21 May 2025.

## Placed in

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

## Builds on (most cited first, 28 of 28)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [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)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Training Large Language Models to Reason in a Continuous Latent Space](https://mlsanity.com/paper/2412.06769/) (2024)
- [Automatic Chain of Thought Prompting in Large Language Models](https://mlsanity.com/paper/2210.03493/) (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)
- [Chain of Draft: Thinking Faster by Writing Less](https://mlsanity.com/paper/2502.18600/) (2025)
- [Reasoning with Language Model Prompting: A Survey](https://mlsanity.com/paper/2212.09597/) (2022)
- [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)
- [DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models](https://mlsanity.com/paper/2503.04472/) (2025)
- [A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond](https://mlsanity.com/paper/2503.21614/) (2025)
- [Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.07572/) (2025)
- [Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching](https://mlsanity.com/paper/2503.05179/) (2025)
- [Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning](https://mlsanity.com/paper/2412.09078/) (2024)
- [LightThinker: Thinking Step-by-Step Compression](https://mlsanity.com/paper/2502.15589/) (2025)
- [Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives](https://mlsanity.com/paper/2401.02009/) (2024)
- [A Comparative Study on Reasoning Patterns of OpenAI's o1 Model](https://mlsanity.com/paper/2410.13639/) (2024)
- [CAKE: Cascading and Adaptive KV Cache Eviction with Layer Preferences](https://mlsanity.com/paper/2503.12491/) (2025)
- [Multi-Agent Sampling: Scaling Inference Compute for Data Synthesis with Tree Search-Based Agentic Collaboration](https://mlsanity.com/paper/2412.17061/) (2024)
- [Will Pre-Training Ever End? A First Step Toward Next-Generation Foundation MLLMs via Self-Improving Systematic Cognition](https://mlsanity.com/paper/2503.12303/) (2025)

## Built on by (most cited first, 17 of 17)

- [Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback](https://mlsanity.com/paper/2506.03106/) (2025)
- [XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation](https://mlsanity.com/paper/2510.06672/) (2025)
- [Are Large Reasoning Models Interruptible?](https://mlsanity.com/paper/2510.11713/) (2025)
- [Asynchronous Reasoning: Training-Free Interactive Thinking LLMs](https://mlsanity.com/paper/2512.10931/) (2025)
- [Mitigating Overthinking in Large Reasoning Language Models via Reasoning Path Deviation Monitoring](https://mlsanity.com/paper/2603.14251/) (2026)
- [Seeing Through the Chain: Mitigate Hallucination in Multimodal Reasoning Models via CoT Compression and Contrastive Preference Optimization](https://mlsanity.com/paper/2602.03380/) (2026)
- [The Zero-Step Thinking: An Empirical Study of Mode Selection as Harder Early Exit in Reasoning Models](https://mlsanity.com/paper/2510.19176/) (2025)
- [BFS-PO: Best-First Search for Large Reasoning Models](https://mlsanity.com/paper/2602.14917/) (2026)
- [ThinkBrake: Efficient Reasoning via Log-Probability Margin Guided Decoding](https://mlsanity.com/paper/2510.00546/) (2025)
- [Inference-Time Chain-of-Thought Pruning with Latent Informativeness Signals](https://mlsanity.com/paper/2511.00699/) (2025)
- [ChainV: Atomic Visual Hints Make Multimodal Reasoning Shorter and Better](https://mlsanity.com/paper/2511.17106/) (2025)
- [CRISP: Compressing Redundancy in Chain-of-Thought via Intrinsic Saliency Pruning](https://mlsanity.com/paper/2604.17297/) (2026)
- [Strategic Reflectivism In Intelligent Systems](https://mlsanity.com/paper/2505.22987/) (2025)
- [Dual-Process Scaffold Reasoning for Enhancing LLM Code Debugging](https://mlsanity.com/paper/2511.08052/) (2025)
- [Multi-objective Evolutionary Merging Enables Efficient Reasoning Models](https://mlsanity.com/paper/2604.06465/) (2026)
- [Post-Reasoning: Improving the Performance of Non-Thinking Models at No Cost](https://mlsanity.com/paper/2605.06165/) (2026)
- [DRT: Dense Reasoning Trace for Efficient and Grounded Multimodal Reasoning](https://mlsanity.com/paper/2609.21675/) (2026)

## Abstract (arXiv)

While Chain-of-Thought (CoT) prompting improves reasoning in large language models (LLMs), the excessive length of reasoning tokens increases latency and KV cache memory usage, and may even truncate final answers under context limits. We propose ThinkLess, an inference-efficient framework that terminates reasoning generation early and maintains output quality without modifying the model. Atttention analysis reveals that answer tokens focus minimally on earlier reasoning steps and primarily attend to the reasoning terminator token, due to information migration under causal masking. Building on this insight, ThinkLess inserts the terminator token at earlier positions to skip redundant reasoning while preserving the underlying knowledge transfer. To prevent format discruption casued by early termination, ThinkLess employs a lightweight post-regulation mechanism, relying on the model's natural instruction-following ability to produce well-structured answers. Without fine-tuning or auxiliary data, ThinkLess achieves comparable accuracy to full-length CoT decoding while greatly reducing decoding time and memory consumption.