ThinkBrake: Efficient Reasoning via Log-Probability Margin Guided Decoding (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in Large Reasoning Models (LRMs) have demonstrated remarkable capabilities across various tasks. |
| Approach: | They propose a system that stops reasoning when the margin between continuation token and lt;/think gt; narrows. |
| Outcome: | The proposed model reduces thinking token usage by 30% and improves accuracy by 8% while reducing thinking tokens by 72%. |
Similar Papers
ThinkSwitcher: When to Think Hard, When to Think Fast (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large reasoning models excel at solving complex tasks by leveraging long chain-of-thought (CoT) reasoning. |
| Approach: | They propose a framework that enables a single LRM to dynamically switch between short and long CoT modes based on task complexity. |
| Outcome: | The proposed framework reduces computational cost by 20-30% while maintaining high accuracy on complex tasks. |
Think Faster Than Words: Efficient LLM Chain-of-Thought Reasoning via Dynamic Shortcut Decoding (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods that prune or employ early stopping to reduce latency often compromise reasoning reliability. |
| Approach: | They propose a shortcut decoding framework that integrates probes over internal hidden states with step-level entropy to detect convergence of reasoning during generation and adaptively selects between a fast-exit path and a stability-verified path to remove redundant steps while preserving answer correctness. |
| Outcome: | The proposed framework reduces token usage by approximately 35% and maintains accuracy comparable to full CoT decoding. |
R-TOFU: Unlearning in Large Reasoning Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Reasoning Models embed private or copyrighted information in their final answers and throughout multi-step chain-of-thought (CoT) traces. |
| Approach: | They propose a benchmark for Large Reasoning Models that augments existing unlearning tasks with realistic CoT annotations and step-wise metrics that expose residual knowledge invisible to answer-level checks. |
| Outcome: | The proposed benchmark shows that answer-only objectives leave substantial forget traces in reasoning. |
Think Better, Not Longer: Token-Level Marginal Utility for Efficient Reasoning in Large Reasoning Models (2026.acl-long)
Copied to clipboard
| Challenge: | Large reasoning models (LRMs) generate explicit Chain-of-Thought rationales, but often suffer from "overthinking". |
| Approach: | They propose a unified training framework to synthesize concise reasoning chains by identifying tokens that reduce the model’s likelihood of the correct answer. |
| Outcome: | Experiments on deepSeek-R1-Distill-Qwen backbones show that MUTO yields better efficiency-accuracy Pareto frontier. |
Do LLMs Really Need 10+ Thoughts for “Find the Time 1000 Days Later”? Towards Structural Understanding of LLM Overthinking (2026.acl-long)
Copied to clipboard
Xinliang Frederick Zhang, Anhad Mohananey, Alexandra Chronopoulou, Pinelopi Papalampidi, Somit Gupta, Tsendsuren Munkhdalai, Lu Wang, Shyam Upadhyay
| Challenge: | Existing studies on LLMs' thought processes are limited to superficial, profiling-based observations, failing to delve into their inner workings. |
| Approach: | They propose a utility-based definition of overthinking that moves beyond length-based metrics and provides a more insightful understanding of LLMs' thought progression. |
| Outcome: | The proposed model decomposes the LLM thought process into minimally complete sub-thoughts and identifies common thinking patterns for topically similar queries. |
Think Less, Know More: State-Aware Reasoning Compression with Knowledge Guidance for Efficient Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing CoT compression methods struggle to balance accuracy and efficiency . long CoT reasoning also introduces an overthinking phenomenon, authors say . |
| Approach: | They propose a framework that performs step-wise CoT compression by modeling stage-specific redundancy sources and integrating with a retrieval-augmented guidance. |
| Outcome: | The proposed framework reduces average response length by 59.9% while improving accuracy by 4.8 points over existing methods. |
ThinkPilot: Steering Reasoning Models via Automated Think-prefixes Optimization (2026.findings-eacl)
Copied to clipboard
| Challenge: | Large Reasoning Models (LRMs) are powerful but still suffer from inefficient and off-target reasoning. |
| Approach: | They propose a training-free framework that automatically optimizes Large Reasoning Models' reasoning by generating think-prefixes that evolve driven by a taxonomy of reasoning behaviors. |
| Outcome: | The proposed framework significantly improves accuracy-length trade-off for efficient reasoning, drastically improves safety and improves instruction following. |
From "Aha Moments" to Controllable Thinking: Toward Meta-Cognitive Reasoning in LRMs via Decoupled Reasoning and Control (2026.acl-long)
Copied to clipboard
| Challenge: | Large Reasoning Models exhibit step-by-step reasoning, reflection, and backtracking, but these behaviors are often unregulated, leading to overthinking. |
| Approach: | They propose a meta-cognitive reasoning framework that decouples reasoning from control to enable independent optimization of control strategies. |
| Outcome: | Experiments show that the proposed model improves efficiency and accuracy across reasoning benchmarks. |
When More Thinking Hurts: Overthinking in LLM Test-Time Compute Scaling (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing research implicitly assumes that longer thinking leads to better results . a recent study suggests that test-time compute scaling is more effective than model scaling . |
| Approach: | They challenge the assumption that longer thinking yields better results . they show that models exhibit overthinking and marginal returns diminish at higher budgets . |
| Outcome: | The proposed framework reduces computation significantly while maintaining comparable accuracy. |
Confidence-Aware Reasoning: Optimizing Self-Guided Thinking Trajectories in Large Reasoning Models (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Chain-of-thought enables large reasoning models to reason through multi-step problems but often leads to unnecessarily long or redundant reasoning traces, a phenomenon known as overthinking. |
| Approach: | They propose an inference-time framework that selectively prunes low-utility reasoning blocks and halts early when sufficient confidence has been achieved. |
| Outcome: | The proposed framework improves answer accuracy by up to +13.3% while reducing average reasoning length by 40%–50%. |