arXiv Machine Learning June 9, 2026 By Lorian Bannis

Lattice: A Confidence-Gated Hybrid System for Uncertainty-Aware Sequential Prediction with Behavioral Archetypes

Read the original on arXiv Machine Learning →

arXiv:2601. 15423v2 Announce Type: replace Abstract: We introduce Lattice, a hybrid sequential prediction system that conditionally activates learned behavioral structure using binary confidence gating.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Sep 10

DataFlex-RL: An Evaluation Platform for RLVR Data Policies

arXiv:2609.06107v1 Announce Type: new Abstract: Data policies for reinforcement learning with verifiable rewards (RLVR) determine which rollouts are used, how strongly they are weighted, and which do...

By Hao Liang, Mingrui Chen, Hengyi Feng, Meiyi Qiang, Wentao Zhang

llms reinforcement-learning benchmarks

arXiv Machine Learning

Aug 12

The Evaluation Protocol Determines the Result: An Independent Reproduction of LeWorldModel on TwoRoom

arXiv:2608. 10145v1 Announce Type: new Abstract: LeWorldModel trains a latent world model with a prediction loss and a single anti-collapse regulariser, and reports approximately 87% of goals reached on TwoRoom, its simplest diagnostic environment.

By Joyjeet Singh

arXiv AI

Aug 12

Actionable Hallucination Detection: Translating Latent Uncertainty into Agentic Critique

arXiv:2608. 10430v1 Announce Type: cross Abstract: Large Language Models (LLMs) deployed as AI agents frequently exhibit user specification-grounding failures, executing hallucinated, undesired actions to force a resolution rather than expressing uncertainty.

By Sanidhya Vijayvargiya, Rahul Lokesh

llms agents diffusion robotics fine-tuning efficiency safety

arXiv Machine Learning

Jun 8

A Held-Out Transition-Pair Falsifier for Long-Horizon Non-Abelian State Tracking

arXiv:2606. 07254v1 Announce Type: new Abstract: State tracking exposes a sharp limitation of sequence models: the relevant signal is often not a summary of observed tokens, but an ordered latent state that evolves through non-commutative transformations.

By Jeonghoon Lee

benchmarks safety

arXiv AI

Jun 30

Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL

arXiv:2604. 28123v3 Announce Type: replace-cross Abstract: The standard post-training recipe for large multimodal models (LMMs) applies supervised fine-tuning (SFT) on curated demonstrations followed by reinforcement learning with verifiable rewards (RLVR).

By Sudong Wang, Weiquan Huang, Xiaomin Yu, Zuhao Yang, Hehai Lin, Keming Wu, Chaojun Xiao, Chen Chen, Wenxuan Wang, Beier Zhu, Yunjian Zhang, Chengwei Qin

llms reinforcement-learning fine-tuning efficiency multimodal benchmarks safety

arXiv AI

Jul 16

When Agents Disagree With Themselves: Behavioral Consistency as an Uncertainty Signal for LLM Agents

arXiv:2602. 11619v2 Announce Type: replace Abstract: Running the same LLM agent on identical inputs yields 2.

By Aman Mehta

llms agents benchmarks

One email a morning, machine-written

Related stories

DataFlex-RL: An Evaluation Platform for RLVR Data Policies

The Evaluation Protocol Determines the Result: An Independent Reproduction of LeWorldModel on TwoRoom

Actionable Hallucination Detection: Translating Latent Uncertainty into Agentic Critique

A Held-Out Transition-Pair Falsifier for Long-Horizon Non-Abelian State Tracking

Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL

When Agents Disagree With Themselves: Behavioral Consistency as an Uncertainty Signal for LLM Agents