Adaptive Computation

Follow this topic Ask about this topic

Momentum

21 papers in the last four weeks, up 133% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 70

All topics

Measuring AI Reasoning: A Guide for Researchers
May 4, 2026Munachiso Samuel Nwadike, Zangir Iklassov, Kareem Ali +2Reasoning Evaluation LLM Reasoning
MBZUAI, Department of Natural Language Processing · MBZUAI, Department of Machine Learning
HALO: Hybrid Adaptive Latent Reasoning for Language Models
May 3, 2026Micah ZhangLLM Inference Acceleration Adaptive Computation
Lockheed Martin
Don't Pause! Every prediction matters in a streaming video
Apr 27, 2026Dibyadip Chatterjee, Zhanzhong Pang, Fadime Sener +2Streaming Video Understanding Efficient VLM Inference
National University of Singapore · Google Inc.
A Comparative Analysis on the Performance of Upper Confidence Bound Algorithms in Adaptive Deep Neural Networks
Apr 27, 2026Grigorios Papanikolaou, Ioannis Kontopoulos, Konstantinos TserpesMulti-Armed Bandits Dynamic Neural Networks
Department of Electrical and Computer Engineering National Technical University of Athens, Greece
Do Not Imitate, Reinforce: Iterative Classification via Belief Refinement
Apr 23, 2026Mahdi Kallel, Johannes Tölle, Ahmed Hendawy +1Reinforcement Learning Classification
Center for Artificial Intelligence and Data Science, University of Würzburg · Department of Computer Science, Technical University of Darmstadt
Universal Transformers Need Memory: Depth-State Trade-offs in Adaptive Recursive Reasoning
Apr 23, 2026Grigory SapunovMemory-Augmented Neural Networks Recurrent Transformers
Intento
Depth Adaptive Efficient Visual Autoregressive Modeling
Apr 19, 2026Chunliang Li, Tianze Cao, Sanyuan ZhaoEfficient Transformer Inference Visual Autoregressive Models
Beijing Institute of Technology · Beijing Institute of Technology, Zhuhai
Adaptive Computation Depth via Learned Token Routing in Transformers
Apr 18, 2026Ahmed Abdelmuniem Abdalla MohammedEfficient Transformer Inference Transformer
Independent Researcher
Scaling Latent Reasoning via Looped Language Models
Oct 29, 2025Rui-Jie Zhu, Zixuan Wang, Kai Hua +30Language Model Pretraining Implicit Reasoning in Language Models
1ByteDance Seed · 2UC Santa Cruz · 3Princeton University +8
Granular-ball computing: an efficient, robust, and interpretable adaptive multi-granularity representation and computation method
Apr 21, 2023Shuyin Xia, Guoyin Wang, Xinbo Gao +2Interpretable ML Adaptive Computation
Chongqing Key Laboratory of Computational Intelligence, Key Laboratory of Cyberspace Big Data Intelligent Security, Ministry of Education, and Key Laboratory of Big Data Intelligent Computing, Chongqing University of Posts and Telecommunications, 400065, Chongqing, China · College of Computer and Information Science, the National Center for Applied Mathematics in Chongqing, Chongqing Normal University, Chongqing 401331, China

May 4, 2026, cs.AIJ/K move · Enter open · S save

Measuring AI Reasoning: A Guide for Researchers

Munachiso Samuel Nwadike, Zangir Iklassov, Kareem Ali, Rifo Genadi+1

MBZUAI, Department of Natural Language Processing · MBZUAI, Department of Machine Learning

Reasoning Evaluation LLM Reasoning Adaptive Computation Reasoning Trace Analysis

Open paper AskPDF arXiv

In this paper, we offer a guide for researchers on evaluating reasoning in language models, building the case that reasoning should be assessed through evidence of adaptive, multi-step search rather than final-answer accuracy alone. Under an evaluation-oriented definition, reasoning requires selecting intermediate steps and halting according to input-dependent conditions, which we formalize as a search-like procedure. We show that single forward passes in scalable architectures are structurally limited in their ability to realize such variable-depth computation, motivating intermediate decoding and externalized reasoning traces as appropriate evaluation interfaces. Central to our argument is that final-answer accuracy alone is an insufficient measure of reasoning, because it provides little ability to diagnose or debug the underlying processes that produce individual solutions in frontier models. We therefore argue for a shift toward process-based evaluation, in which reasoning is assessed through the faithfulness and validity of intermediate reasoning traces as first-class evaluation targets.

Momentum

Related topics

Latest papers 70