efficient-reasoning

Paper list for Efficient Reasoning.

😎 A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, Agent, and Beyond

[TMLR 2025] Efficient Reasoning Models: A Survey

[AAAI 2026] Code for "UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning"

Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models

[CVPR 2026] ReasonMap: Towards Fine-Grained Visual Reasoning from Transit Maps

FastCuRL: Curriculum Reinforcement Learning with Stage-wise Context Scaling for Efficient LLM Reasoning (EMNLP 2025)

[ICLR 2026] InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models

[NeurIPS 2025] Official implementation of "Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning"

🌿 DeepPrune: Parallel Scaling without Inter-trace Redundancy

DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning

[ICLR'26] SketchThinker-R1: Towards Efficient Sketch-Style Reasoning in Large Multimodal Models

Raw benchmark logs for Swift-Qwen3.8-27B vs the Qwen3.8-27B BF16 base: every response, score, and config across 9 benchmarks

Parallel Decoding of Language Models: A Survey. A systematic survey of parallel decoding, covering speculative decoding, diffusion LLMs, etc...

[ICLR 2026] FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning

Claim-Level Reliability Assessment for Efficient Test-Time Reasoning

[NeurIPS 2025] Code and Data Repo for Paper "Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding"

Learning when to reason and how much computation to allocate for efficient reasoning models.

Reasoning distillation research series: DRP, Rock Token, and TOPD — what to teach, where to focus, and how to guide.

Public code projection for “More Calls, Not Necessarily Better Coordination,” accepted at the COLM 2026 Workshop on Efficient Reasoning.