CARVIEW

MOTORHOMES

Select Language

HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Wed, 10 Dec 2025 04:06:53 GMT access-control-allow-origin: * strict-transport-security: max-age=31556952 etag: W/"6938f1dd-e0ef" expires: Sun, 28 Dec 2025 07:30:39 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: 72DE:444BC:762A16:845576:6950DA46 accept-ranges: bytes age: 0 date: Sun, 28 Dec 2025 07:20:40 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210055-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1766906440.801963,VS0,VE202 vary: Accept-Encoding x-fastly-request-id: d1da6393bd68e8044ffbdfcf58073bb5ba3482db content-length: 11656 The 1st Workshop on Efficient Reasoning

NeurIPS 2025 Workshop on

Efficient Reasoning

Dec 6, 2025

Contact: er.neurips2025@gmail.com

News

Best Paper: M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models, Junxiong Wang, Wen-Ding Li, Daniele Paliotta, Daniel Ritter, Alexander M Rush, Tri Dao
Video: https://neurips.cc/virtual/2025/loc/san-diego/workshop/109556
Poster: Authors are free to present poster at any section.
Camera-ready: Camera-ready submission will be open at October 16, 2025 (AoE), an extra page is allow for camera-ready version. The Camera-ready deadline has been extended to October 27 (AoE).
Deadline Extension: The old deadline overlaps with the Labor Day. We extend the submission deadline to September 8, 2025 (AoE).
Call for reviewers: We are actively looking for reviewers to join the program committee for the workshop. We encourage all interested researchers to apply, especially those from underrepresented groups. Prior reviewer experience is a nice-to-have, but not required. Interest and familiarity with subject matters related to the workshop is required. If you are interested, please fill out the application form to join us.
Call for papers: Submission portal open at OpenReview

About

Recent progress in large reasoning models (LRMs), like OpenAI o1 and Deepseek R1, has been pivotal for tackling complex applications, from mathematical and code reasoning to advanced symbolic and agentic planning. Their success often relies on test-time scaling, which involves increasing the generation length or depth. However, these approaches incur significant efficiency bottlenecks during training and inference. To overcome these limitations, further advancements are needed in data, algorithms, and systems applicable across various domains, as exemplified by work such as s1, Z1, and verl. The proposed workshop will bring together researchers and practitioners to rethink efficient reasoning under tight compute, memory, latency, throughput, and cost budgets, with the goal of translating theoretical breakthroughs into practical, deployable solutions.

Key Problems We Aim to Address

Dataset Curation

Design, create, and maintain high‑quality datasets for training and evaluating LRMs on challenging reasoning tasks under resource constraints. Contributions include long-context reasoning, symbolic planning, multi-hop deduction, and real-time decision-making on diverse domains.

Algorithmic Innovation

Develop efficient training algorithms for supervised fine-tuning or reinforcement learning, and efficient inference methods like pruning, compression, progressive generation, and search‑based strategies, reducing time/space complexity without eroding accuracy or faithfulness.

System Deployment

Implement efficient RL training systems and long-CoT inference engines to support current LRMs, while unlocking new reasoning potential on commodity GPUs. Techniques may include dynamic KV‑cache placement, quantized graph execution, and on‑device knowledge distillation

Application

Adapt LRMs to enable real-time reasoning in resource-constrained scenarios, like clinical decision-making, robotics, autonomous driving, developing-world health, and on-orbit autonomy.

Call for Papers

The 1st Workshop on Efficient Reasoning at NeurIPS 2025 invites submissions from researchers focused on the reasoning models. Additionally, we welcome contributions from researchers in the natural sciences (e.g., physics, chemistry, biology) and social sciences (e.g., pedagogy, sociology) to provide attendees with a more comprehensive perspective for their reasoning tasks.

Key Dates

Paper Submission Open: August 1, 2025
Paper Submission Deadline: September 1, 2025 (AoE) , September 8, 2025 (AoE)
Paper Notification Deadline: September 22, 2025 (AoE)
Second Round Submission Open: September 18, 2025 (AoE)
Second Round Submission Deadline: October 1, 2025 (AoE)
Second Round Notification Deadline: October 15, 2025 (AoE)
Review Deadline: October 14, 2025 (AoE)
Camera-ready Version Deadline: October 7, 2025 (AoE) , October 22, 2025 (AoE) ， October 27, 2025 (AoE)

Note:We have introduced a second submission round to accommodate researchers who may prefer to submit after the ICLR 2026 deadline. However, if you plan to apply for a visa early, we strongly encourage submitting in the first round.

Submission Site

Submit papers through the Workshop Submission Portal on OpenReview.

Scope

We welcome contributions across a broad spectrum of topics, including but not limited to:

Pipelines for creating high-quality training data with resource constraints or deployment environments.
Benchmark methodologies for assessing the efficiency and efficacy of LRMs in real-world settings
Innovations in techniques for training LRMs with a better trade-off between efficiency and performance
Approaches for accelerating LRM inference through the design of algorithms and systems
Advancements in improving the reasoning and planning abilities of LRMs in diverse tasks
Theoretical analysis of the time and space complexity of LRMs on synthetic and realistic tasks.
Empirical investigations into the practical efficiency (i.e., latency and throughput) of LRMs
Implementations to efficiently enable large-scale RL training systems or on-device inference engines
Strategies for overcoming practical limitations (e.g., memory, time, data) of LRMs
In-depth discussions exploring the efficient deployments and applications of LRMs

Submission Guidelines

Format: All submissions must be a single PDF file. We welcome high-quality original papers up to 4 pages, including both long and short papers. References and appendices are not included in the page limit, but the main text must be self-contained. Reviewers are not required to read beyond the main text

For the second track submissions, we open the page limit to 9 pages to match ICLR paper pages for the authors' convenience .

Style file: You must format your submission using the NeurIPS 2025 LaTeX style file. For your convenience, we modified all the conference style files to refer to our workshop: NeurIPS 2025 Style Files. Please include the references and supplementary materials in the same PDF. The maximum file size for submissions is 50MB. Submissions that violate the NeurIPS style (e.g., by decreasing margins or font sizes) or page limits may be rejected without further review.

Dual-submission and non-archival policy: We welcome ongoing and unpublished work. We will also accept papers that are under review at the time of submission, or that have been recently accepted, provided they do not breach any dual-submission or anonymity policies of those venues. The workshop is a non-archival venue and will not have official proceedings. Workshop submissions can be subsequently or concurrently submitted to other venues.

Visibility: Submissions and reviews will not be public. Only accepted papers will be made public.

Double-blind reviewing: All submissions must be anonymized and may not contain any identifying information that may violate the double-blind reviewing policy. This policy applies to any supplementary or linked material as well, including code. If you are including links to any external material, it is your responsibility to guarantee anonymous browsing. Please do not include acknowledgements at submission time. If you need to cite one of your own papers, you should do so with adequate anonymization to preserve double-blind reviewing. Any papers found to be violating this policy will be rejected.

Contact: For any questions, please contact us at er.neurips2025@gmail.com or EfficientReasoning2025@googlegroups.com

Schedule

This is the tentative schedule of the workshop. All slots are provided in local time.

Morning Session

08:00 - 08:45	Breakfast
08:45 - 09:00	Introduction and Opening Remarks
09:00 - 09:30	Jonas Geiping: The Promise of Recurrent Depth for Efficient Reasoning
09:30 - 10:00	Morning Break
10:00 - 10:30	Arman Cohan: Frameworks for Better Understanding Alignment Evaluation and Scientific Reasoning in Large Language
10:30 - 10:45	Oral Paper Talk: M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models
10:45 - 11:00	Oral Paper Talk: Generalized Parallel Scaling with Interdependent Generations
11:00 - 11:30	Wei Xu: Beyond Logic and Math: Probabilistic Reasoning for Real-World Decision Making
11:30 - 12:00	Wang Zhang: What's Now and Next for veRL?
12:00 - 13:00	Break
12:00 - 13:00	Poster Session 1

Afternoon Session

13:00 - 13:30	Yi Wu:AReaL: an Efficient and Flexible Framework for Agentic RL
13:30 - 14:00	Yuandong Tian: open the blackbox of neural network and use the insights for efficient reasoning
14:00 - 14:30	Panel Discussion
14:30 - 15:00	Hao Zhang: Reasoning with Confidence
15:00 - 15:30	Niklas Muennighoff: Test-time scaling
15:30 - 15:45	Oral Paper Talk: When Reasoning Meets Its Laws
15:45 - 16:00	Oral Paper Talk: In-the-Flow Agentic System Optimization for Effective Planning and Tool Use
16:00 - 16:30	Beidi Chen: Beyong FLOPs: Opportunities and Challenges of Test-Time Scaling on Modern Hardware
16:30 - 17:30	Poster Session 2

Invited Speakers

This is the tentative invited speakers. More speakers are invited.

News