Cover Image

Latent Reasoning in TRMs is Secretly a Policy Improvement Operator

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Asadulaev, Arip, Banerjee, Rayan, Karray, Fakhri, Takac, Martin
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Zero-Shot Off-Policy Learning
by: Asadulaev, Arip, et al.
Published: (2026)

Expert or not? assessing data quality in offline reinforcement learning
by: Asadulaev, Arip, et al.
Published: (2025)

Y-Shaped Generative Flows
by: Asadulaev, Arip, et al.
Published: (2025)

Zero-shot adaptation to order book dynamics
by: Asadulaev, Arip
Published: (2026)

Vision Language Models for Dynamic Human Activity Recognition in Healthcare Settings
by: Abid, Abderrazek, et al.
Published: (2025)

REMONI: An Autonomous System Integrating Wearables and Multimodal Large Language Models for Enhanced Remote Health Monitoring
by: Ho, Thanh Cong, et al.
Published: (2025)

Convex Compositional Reasoning Models
by: Roketlishvili, Meir, et al.
Published: (2026)

HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMs
by: Li, Qing, et al.
Published: (2025)

Internal Activation Revision: Safeguarding Vision Language Models Without Parameter Update
by: Li, Qing, et al.
Published: (2025)

Latent Principle Discovery for Language Model Self-Improvement
by: Ramji, Keshav, et al.
Published: (2025)

The AI Data Scientist
by: Akimov, Farkhad, et al.
Published: (2025)

Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space
by: Li, Hengli, et al.
Published: (2025)

Enhance Hyperbolic Representation Learning via Second-order Pooling
by: Song, Kun, et al.
Published: (2024)

Policy Improvement using Language Feedback Models
by: Zhong, Victor, et al.
Published: (2024)

Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains
by: Subramaniam, Vighnesh, et al.
Published: (2025)

Reasoning to Learn from Latent Thoughts
by: Ruan, Yangjun, et al.
Published: (2025)

TTSR: Test-Time Self-Reflection for Continual Reasoning Improvement
by: He, Haoyang, et al.
Published: (2026)

Reasoning with Latent Thoughts: On the Power of Looped Transformers
by: Saunshi, Nikunj, et al.
Published: (2025)

Group-Relative REINFORCE Is Secretly an Off-Policy Algorithm: Demystifying Some Myths About GRPO and Its Friends
by: Yao, Chaorui, et al.
Published: (2025)

Parallel Test-Time Scaling for Latent Reasoning Models
by: You, Runyang, et al.
Published: (2025)

Method-Based Reasoning for Large Language Models: Extraction, Reuse, and Continuous Improvement
by: Su, Hong
Published: (2025)

Your Transformer is Secretly Linear
by: Razzhigaev, Anton, et al.
Published: (2024)

Internalizing LLM Reasoning via Discovery and Replay of Latent Actions
by: Shi, Zhenning, et al.
Published: (2026)

Thinking in Latents: Adaptive Anchor Refinement for Implicit Reasoning in LLMs
by: Sheshanarayana, Disha, et al.
Published: (2026)

LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning
by: Kang, Haoqiang, et al.
Published: (2025)

Depth-Recurrent Attention Mixtures: Giving Latent Reasoning the Attention it Deserves
by: Knupp, Jonas, et al.
Published: (2026)

Learning to Reason under Off-Policy Guidance
by: Yan, Jianhao, et al.
Published: (2025)

Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation
by: Casademunt, Helena, et al.
Published: (2026)

How Do Latent Reasoning Methods Perform Under Weak and Strong Supervision?
by: Cui, Yingqian, et al.
Published: (2026)

When Shallow Wins: Silent Failures and the Depth-Accuracy Paradox in Latent Reasoning
by: Sahoo, Subramanyam, et al.
Published: (2026)

Regularization Through Reasoning: Systematic Improvements in Language Model Classification via Explanation-Enhanced Fine-Tuning
by: Shah, Vivswan, et al.
Published: (2025)

Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization
by: Su, Zhenpeng, et al.
Published: (2025)

Dual-Uncertainty Guided Policy Learning for Multimodal Reasoning
by: Liu, Rui, et al.
Published: (2025)

Simple Policy Gradients for Reasoning with Diffusion Language Models
by: Zhan, Anthony
Published: (2025)

Effect of Document Packing on the Latent Multi-Hop Reasoning Capabilities of Large Language Models
by: Prato, Gabriele, et al.
Published: (2025)

ThinkRouter: Efficient Reasoning via Routing Thinking between Latent and Discrete Spaces
by: Xu, Xin, et al.
Published: (2026)

Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximization
by: Persiianov, Mikhail, et al.
Published: (2024)

Optimizing Anytime Reasoning via Budget Relative Policy Optimization
by: Qi, Penghui, et al.
Published: (2025)

On the Design of KL-Regularized Policy Gradient Algorithms for LLM Reasoning
by: Zhang, Yifan, et al.
Published: (2025)

SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning
by: Limozin, Alexis, et al.
Published: (2026)