Cover Image

Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Hengli, Li, Chenxi, Wu, Tong, Zhu, Xuekai, Wang, Yuxuan, Yu, Zhaoxin, Jiang, Eric Hanchen, Zhu, Song-Chun, Jia, Zixia, Wu, Ying Nian, Zheng, Zilong
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MILR: Improving Multimodal Image Generation via Test-Time Latent Reasoning
by: Mi, Yapeng, et al.
Published: (2025)

Discrete Markov Bridge
by: Li, Hengli, et al.
Published: (2025)

BEDA: Belief Estimation as Probabilistic Constraints for Performing Strategic Dialogue Acts
by: Li, Hengli, et al.
Published: (2025)

TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation
by: Wu, Tong, et al.
Published: (2025)

Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning
by: Wu, Tong, et al.
Published: (2025)

MindDial: Belief Dynamics Tracking with Theory-of-Mind Modeling for Situated Neural Dialogue Generation
by: Qiu, Shuwen, et al.
Published: (2023)

LangSuitE: Planning, Controlling and Interacting with Large Language Models in Embodied Text Environments
by: Jia, Zixia, et al.
Published: (2024)

$\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space
by: Wang, Peihao, et al.
Published: (2026)

How to Synthesize Text Data without Model Collapse?
by: Zhu, Xuekai, et al.
Published: (2024)

Reasoning in the Dark: Interleaved Vision-Text Reasoning in Latent Space
by: Chen, Chao, et al.
Published: (2025)

TongSearch-QR: Reinforced Query Reasoning for Retrieval
by: Qin, Xubo, et al.
Published: (2025)

The Thinking Pixel: Recursive Sparse Reasoning in Multimodal Diffusion Latents
by: Sun, Yuwei, et al.
Published: (2026)

ManCAR: Manifold-Constrained Latent Reasoning with Adaptive Test-Time Computation for Sequential Recommendation
by: Yang, Kun, et al.
Published: (2026)

Multiple Latent Space Mapping for Compressed Dark Image Enhancement
by: Zeng, Yi, et al.
Published: (2024)

Agent Q-Mix: Selecting the Right Action for LLM Multi-Agent Systems through Reinforcement Learning
by: Jiang, Eric Hanchen, et al.
Published: (2026)

MorphSeek: Fine-grained Latent Representation-Level Policy Optimization for Deformable Image Registration
by: Zhang, Runxun, et al.
Published: (2025)

Skew-adjoint linear relatioins between Banach spaces
by: Li, Hanchen, et al.
Published: (2024)

Designing Instance-Level Sampling Schedules via REINFORCE with James-Stein Shrinkage
by: Yu, Peiyu, et al.
Published: (2025)

Understanding and Leveraging the Expert Specialization of Context Faithfulness in Mixture-of-Experts LLMs
by: Bai, Jun, et al.
Published: (2025)

Anomalous bulk-edge correspondence of nonlinear Rice-Mele model
by: Bai, Chenxi, et al.
Published: (2025)

Fractional Thouless pumping of solitons: a unique manifestation of bulk-edge correspondence of nonlinear eigenvalue problems
by: Bai, Chenxi, et al.
Published: (2025)

MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding
by: Zuo, Yuxin, et al.
Published: (2025)

Statistical Inference on Latent Space Models for Network Data
by: Li, Jinming, et al.
Published: (2023)

Learning to Rank Chain-of-Thought: Using a Small Model
by: Jiang, Eric Hanchen, et al.
Published: (2025)

The AI Hippocampus: How Far are We From Human Memory?
by: Jia, Zixia, et al.
Published: (2026)

AsynFusion: Towards Asynchronous Latent Consistency Models for Decoupled Whole-Body Audio-Driven Avatars
by: Zhang, Tianbao, et al.
Published: (2025)

Policy Gradient Guidance Enables Test Time Control
by: Qi, Jianing, et al.
Published: (2025)

Q-Tacit: Image Quality Assessment via Latent Visual Reasoning
by: Jiang, Yuxuan, et al.
Published: (2026)

Latent Space Energy-based Neural ODEs
by: Cheng, Sheng, et al.
Published: (2024)

Combining Supervised Learning and Reinforcement Learning for Multi-Label Classification Tasks with Partial Labels
by: Jia, Zixia, et al.
Published: (2024)

Adaptive Preference Optimization with Uncertainty-aware Utility Anchor
by: Wang, Xiaobo, et al.
Published: (2025)

A Study on the Ancient theater of official house in The Taihang mountain area of North Henan Province in China
by: Hengli Peng
Published: (2023)

InterPreT: Interactive Predicate Learning from Language Feedback for Generalizable Task Planning
by: Han, Muzhi, et al.
Published: (2024)

DisenReason: Behavior Disentanglement and Latent Reasoning for Shared-Account Sequential Recommendation
by: Cheng, Jiawei, et al.
Published: (2026)

ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection
by: Li, Jiaqi, et al.
Published: (2025)

Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning
by: Deng, Jingcheng, et al.
Published: (2026)

Sparser is Faster and Less is More: Efficient Sparse Attention for Long-Range Transformers
by: Lou, Chao, et al.
Published: (2024)

LaSER: Internalizing Explicit Reasoning into Latent Space for Dense Retrieval
by: Jin, Jiajie, et al.
Published: (2026)

ExoViP: Step-by-step Verification and Exploration with Exoskeleton Modules for Compositional Visual Reasoning
by: Wang, Yuxuan, et al.
Published: (2024)

Wasserstein Proximal Policy Gradient
by: Zhu, Zhaoyu, et al.
Published: (2026)