AI Paper Atlas

Research map / Large language models / Reasoning and chain of thought

Efficient Inference for Large Reasoning Models: A Survey

Yue Liu, J. F. Wu, Yufei He, Ruihan Gong, Jun Xia, Liang Li, Hongcheng Gao, Hongyu Chen, Baolong Bi, Jiaheng Zhang, Zhiqi Huang, Bryan Hooi and 2 more

TPAMI 2026 · Large language models › Reasoning and chain of thought · approach: Long CoT dynamics and efficiency

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
lower TokenSkip compression ratio from 1.0 to 0.5 (ablation)TokenSkip LLaMA-3.1-8B-Instruct · GSM8Kaccuracy: 78.20% -> 86.70%Improved
few-shot prompting instead of zero-shot for CoD (ablation)CoD GPT-4o · GSM8Kaccuracy: 84.40% -> 91.10%Improved
few-shot prompting instead of zero-shot for CoD (ablation)CoD Claude 3.5 Sonnet · GSM8Kaccuracy: 65.50% -> 91.40%Improved
train TALE with SFT instead of prompting (ablation)TALE LLaMA-3.1-8B-Instruct · GSM8Kaccuracy: 84.46% -> 74.11%Hurt
use DPO rather than SFT in TALE (ablation)TALE LLaMA-3.1-8B-Instruct · GSM8Kaccuracy: 74.11% -> 78.41%Improved
use thought-level rather than token-level compression in LightThinker (ablation)LightThinker R1-Distill-Qwen-7B · GSM8Kaccuracy: 87.11% -> 90.14%Improved
add topo-rewarding then hybrid-scaling on top of topo-tuning (ablation)SOLAR Qwen2-VL-7B · GSM8Kaccuracy: 84.00% -> 89.02%Improved
initialize SelfBudgeter from s1k rather than GSM data (ablation)SelfBudgeter R1-Distill-Qwen-1.5B · GSM8Kaccuracy: 76.27% -> 81.50%Improved
use separated reward in ConciseRL (ablation)ConciseRL R1-Distill-Qwen-1.5B · GSM8Kaccuracy: 80.9% -> 72.5%Hurt
raise Constrained-CoT word limit from 15 to 100 (ablation)Constrained-CoT Falcon-40b · GSM8Kaccuracy: 31.5% -> 27.4%Hurt
scale ThinkLess from Qwen2.5-7B to 14B (ablation)ThinkLess · GSM8Kaccuracy: 88.40% -> 92.49%Improved
apply Overclocking to R1-Distill-LLaMA-8B instead of Qwen-32BOverclocking alpha=100 · GSM8Kaccuracy: 85.96% -> 39.87%Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy