The paper introduces recirculation, an inference‑time architectural enhancement for foundation models that reduces perplexity and improves accuracy on generation and reasoning tasks without adding significant latency. Recirculation adds a specific form of recurrence, enabling the model to function as a dynamical system that tracks belief states, and is distinct from chain‑of‑thought or depth‑recurrence methods. An adaptive variant requires minimal hyperparameter tuning and achieves notable gains on the Gemma3 family, including a 23% perplexity drop and a 21% accuracy increase on GSM8k.
By Michael C. Mozer, Shoaib Ahmed Siddiqui, Danny Sawyer, Sunny Sanyal, Rosanne Liu
arXiv:2603. 25414v4 Announce Type: replace-cross Abstract: A prevailing assumption in machine learning is that model correctness must be enforced after the fact.
By Houston Haynes
arXiv:2603. 14147v2 Announce Type: replace Abstract: The generative artificial intelligence (AI) ecosystem is undergoing rapid transformations that threaten its sustainability.
By Margarita Belova, Yuval Kansal, Yihao Liang, Jiaxin Xiao, Niraj K. Jha
arXiv:2604. 21495v2 Announce Type: replace-cross Abstract: Numerical reasoning over expert-domain tables often exhibits high in-domain accuracy but limited robustness to domain shift.
By Hanjun Cho, Gahyun Yoo, Hanseong Kim, Jay-Yoon Lee
arXiv:2602. 15327v2 Announce Type: replace-cross Abstract: Machine learning model performance improvements tend to arise from competition and application.
By Hanlin Zhang, Jikai Jin, Vasilis Syrgkanis, Sham Kakade
arXiv:2606. 09930v1 Announce Type: cross Abstract: The boundary between program execution and gradient-based optimization has long limited the use of code itself as a learnable scientific model.
By Lucas Sheneman
arXiv:2607. 03574v1 Announce Type: cross Abstract: AI systems increasingly propose executable scientific models whose value depends on both their symbolic structure and their fitted continuous parameters.
By Lucas Sheneman
arXiv:2608. 00029v1 Announce Type: cross Abstract: The performance of deep learning models at scale relies heavily on how effectively high-level mathematical operations are mapped to underlying physical hardware.
By Adwaid Suresh, Aparna A, Harshini V M, Jona Delcy C A, Killi Uma Maheswara Rao, Ram Charan Golla, Surendra Vendra
arXiv:2606. 20002v1 Announce Type: cross Abstract: This work presents a general framework for training large language models (LLMs) to "Connect the Dots" (CoD), a meta-capability required by long-lifecycle agents: as an LLM-based AI agent gets deployed in an environment, it solves a long sequence of tasks while continuously exploring the environment, learning from its own experiences, and iteratively self-updating its context about the environment, thereby achieving progressively better performance on future tasks conditioned on the updated context.
By Yanxi Chen, Weijie Shi, Yuexiang Xie, Boyi Hu, Yaliang Li, Bolin Ding, Jingren Zhou
arXiv:2609.39967v1 Announce Type: cross
Abstract: Recursive reasoning models apply a small shared Transformer block many times to refine a latent state. This gives them large effective depth with few...
By Yuliana Shakhvalieva, Dmitrii Kharchev, Viacheslav Bezrukov, Inessa Fedorova, Dmitry Bocharov, Ivan Oseledets, Valerii Ternovskii
arXiv:2602. 00510v2 Announce Type: replace Abstract: Most LLM code-synthesis benchmarks rely on unit tests as the reward oracle, but PCB schematic design has none: correctness is defined by structured physical constraints over real IC packages and pin-level assignments, per-task golden references are unavailable, and SPICE simulation does not validate schematic-level correctness.
By Huanghaohe Zou, Peng Han, Emad Nazerian, Mafu Zhang, Zhicheng Guo, Alex Q. Huang
arXiv:2604. 07328v3 Announce Type: replace Abstract: How does the choice of training data influence an AI model?
By Sam Gunn