arXiv Machine Learning August 12, 2026 By Joyjeet Singh

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

Read the original on arXiv Machine Learning →

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.

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

arXiv AI

5d ago

The Objective Is the Bottleneck: Latent World Models Encode What Their Planners Cannot Use

arXiv:2608. 12959v1 Announce Type: cross Abstract: Latent world models are judged by how well they predict, so when planning fails at long horizons the natural reading is that the predictor degrades.

By Joyjeet Singh

rag

arXiv Machine Learning

6d ago

MMLA: How Memory Lets the Past Shape the Future

arXiv:2606. 28876v3 Announce Type: replace-cross Abstract: Proposal.

By Junyi Zou, Avrova Donz

llms

arXiv AI

Jul 21

First-Order Predictable but Pairwise Fragile: Local Task Adaptation in Trained Transformers

arXiv:2607. 16821v1 Announce Type: cross Abstract: Task arithmetic, sequential fine-tuning, activation steering, and first-order random search all operate through relatively small perturbations around an already trained checkpoint, and they rely on different local approximations: individual perturbations should be first-order predictable, task updates should compose with controlled interference, useful tangent structure should be stable and possible to estimate, and weight edits should have counterparts in representation space.

By Irina Piontkovskaia, Sergey Nikolenko

llms fine-tuning

arXiv Machine Learning

1d ago

Paired Exact-Reset Evaluation of a Prediction-Derived Medium-to-Full World-Model Cascade

arXiv:2608. 14650v1 Announce Type: new Abstract: Existing adaptive-inference and world-action-model systems use cheap-stage outputs or predicted futures to allocate additional computation.

By Malo de Pastor

arXiv AI

1d ago

StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling

arXiv:2608. 15089v1 Announce Type: new Abstract: Long-horizon agents can fail even when their underlying models can solve the constituent steps.

By Ziheng Qin, Yaxin Lu, Zhangyang Atlas Wang, Kai Wang

llms agents

arXiv Machine Learning

Jul 21

Auditing Invisible Weight Updates with Reference Traces

arXiv:2607. 09800v2 Announce Type: replace Abstract: Master weights and stochastic rounding bypass invisible stored-weight updates but do not locate lost direct-storage proposals or parameters worth protecting.

By Zekai Shang

llms

Related stories

The Objective Is the Bottleneck: Latent World Models Encode What Their Planners Cannot Use

MMLA: How Memory Lets the Past Shape the Future

First-Order Predictable but Pairwise Fragile: Local Task Adaptation in Trained Transformers

Paired Exact-Reset Evaluation of a Prediction-Derived Medium-to-Full World-Model Cascade

StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling

Auditing Invisible Weight Updates with Reference Traces