arXiv Machine Learning June 29, 2026 By Xiang Gao, Kaiwen Dong, Yuguang Yao, Padmaja Jonnalagedda, Kamalika Das

Textual Belief States for World Models: Identifiable Representation Learning Under Strict Mediation

Read the original on arXiv Machine Learning →

arXiv:2606. 27681v1 Announce Type: new Abstract: World models in partially observed environments rely on latent representations that summarize interaction history, but in many modern LLM-based architectures predictive performance fails to reflect representation quality due to history bypass, rendering the latent state unidentifiable.

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

arXiv AI

Jun 2

Latent Collaboration in Multi-Agent Systems

arXiv:2511. 20639v3 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) extend large language models (LLMs) from independent single-model reasoning to coordinative system-level intelligence.

By Jiaru Zou, Ruizhong Qiu, Gaotang Li, Xiyuan Yang, Katherine Tieu, Pan Lu, Ke Shen, Hanghang Tong, Yejin Choi, Jingrui He, James Zou, Mengdi Wang, Ling Yang

llms rag agents diffusion benchmarks

arXiv Machine Learning

Jun 16

Next-Latent Prediction Transformers Learn Compact World Models

arXiv:2511. 05963v4 Announce Type: replace Abstract: Transformers replace recurrence with a memory that grows with sequence length and self-attention that enables ad-hoc lookups over past tokens.

By Jayden Teoh, Manan Tomar, Kwangjun Ahn, Edward S. Hu, Tim Pearce, Pratyusha Sharma, Akshay Krishnamurthy, Riashat Islam, Alex Lamb, John Langford

llms diffusion benchmarks safety

arXiv Machine Learning

Jun 25

ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning

arXiv:2501. 14622v5 Announce Type: replace Abstract: Learning efficient representations for decision-making policies is a challenge in imitation learning (IL).

By Aleksandar Vujinovic, Aleksandar Kovacevic

rag diffusion

arXiv AI

Aug 7

Hierarchical Latent Prediction for Language Models

arXiv:2608. 05806v1 Announce Type: cross Abstract: While standard Next-Token Prediction (NTP) lays the foundation of language model pre- training, its teacher-forced training paradigm may not be optimal for long-horizon reasoning and planning.

By Chang Shi, Tim Pearce, Manan Tomar, Siddhartha Sen, John Langford

llms diffusion benchmarks

arXiv AI

Jun 17

ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model

arXiv:2603. 22281v2 Announce Type: replace-cross Abstract: Recent progress in latent world models (e.

By Haichao Zhang, Yijiang Li, Shwai He, Tushar Nagarajan, Mingfei Chen, Jianglin Lu, Ang Li, Yun Fu

llms robotics multimodal safety

arXiv AI

Jun 10

Fact-Augmented Lookahead Planning for LLM Agents

arXiv:2506. 09171v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly capable, but LLM agents still struggle to plan effectively in interactive, partially observable, long-horizon environments when search is unguided or recent history is insufficient.

By Samuel Holt, Max Ruiz Luyten, Thomas Pouplin, Mihaela van der Schaar

llms agents

Related stories

Latent Collaboration in Multi-Agent Systems

Next-Latent Prediction Transformers Learn Compact World Models

ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning

Hierarchical Latent Prediction for Language Models

ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model

Fact-Augmented Lookahead Planning for LLM Agents