arXiv Machine Learning July 24, 2026 By Ishan S. Kshirsagar

The Weight of Silence: A Causal Case for Weights Over the Scratchpad in Latent Chess Reasoning

Read the original on arXiv Machine Learning →

arXiv:2607. 20952v1 Announce Type: new Abstract: Latent, or silent, reasoning lets language models carry out intermediate computation in continuous vector space instead of words, and is widely assumed to function as an internal scratchpad the model actively consults during inference.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 9

Final Checkpoints Are Not Enough: Analyzing Latent Reasoning Faithfulness Along Training Trajectories

arXiv:2607. 06648v1 Announce Type: new Abstract: Latent reasoning methods perform multi-step inference entirely in the model's continuous hidden states, promising more compact and efficient reasoning.

By Hengyu Jin, Shu Yang, Di Wang

benchmarks

arXiv AI

Jul 20

Understanding Reasoning from Pretraining to Post-Training

arXiv:2607. 16097v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become central to improving large language models (LLMs) on complex reasoning tasks, yet RL post-training is largely studied in isolation from the pretraining that precedes it.

By Jingyan Shen, Ang Li, Salman Rahman, Yifan Sun, Micah Goldblum, Matus Telgarsky, Pavel Izmailov

llms reinforcement-learning fine-tuning

arXiv AI

Aug 11

Reason Wide, Not Deep: Amortizing the Reasoning Premium into Distilled Skills

arXiv:2608. 07885v1 Announce Type: new Abstract: Reasoning modes of language models outperform their non-reasoning counterparts on multi-step agentic tasks, but pay a 3-6x premium in output tokens on every episode -- much of it spent re-deriving procedures that are shared across episodes of the same domain.

By Agamdeep Singh, Srishti Gautam, Priyanshu Gupta, Nikita Mehrotra, Tanmay Bakshi, Sumit Gulwani

llms agents efficiency benchmarks

arXiv Machine Learning

Jun 29

Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs

arXiv:2606. 27378v1 Announce Type: cross Abstract: We introduce an axiomatic evaluation framework for latent thought representations in LLMs, comprising metrics that are independent of downstream benchmark scores and reveal representational failures that benchmark accuracy masks.

By Fahd Seddik, Fatemeh Fard

llms rag reinforcement-learning benchmarks

arXiv Machine Learning

Jul 27

LeAct: Learning to Reason from Expert Actions

arXiv:2607. 21856v1 Announce Type: new Abstract: Modern reasoning models depend on reasoning data, today sourced from human annotations or distilled from stronger LLMs.

By Ziran Yang, Chengshuai Shi, Raj Ghugare, Benjamin Eysenbach, Karthik Narasimhan, Chi Jin

llms robotics benchmarks

arXiv Machine Learning

Jun 9

From Shortcuts to Reasoning: Robust Post-Training of Theory of Mind with Reinforcement Learning

arXiv:2606. 09092v1 Announce Type: new Abstract: Theory of Mind (ToM) is a must-acquire skill for modern foundation model systems to operate effectively and safely in the real world.

By Jike Zhong, Yuxiang Lai, Ming Li, Yuheng Li, Wuao Liu, Behzad Dariush, Konstantinos Psounis, Shao-Yuan Lo

reinforcement-learning fine-tuning multimodal

Related stories

Final Checkpoints Are Not Enough: Analyzing Latent Reasoning Faithfulness Along Training Trajectories

Understanding Reasoning from Pretraining to Post-Training

Reason Wide, Not Deep: Amortizing the Reasoning Premium into Distilled Skills

Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs

LeAct: Learning to Reason from Expert Actions

From Shortcuts to Reasoning: Robust Post-Training of Theory of Mind with Reinforcement Learning