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.
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.
arXiv:2606. 28876v3 Announce Type: replace-cross Abstract: Proposal.
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.
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.
arXiv:2608. 15089v1 Announce Type: new Abstract: Long-horizon agents can fail even when their underlying models can solve the constituent steps.
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.
arXiv:2607. 27283v1 Announce Type: new Abstract: Long-horizon benchmarks often show that agents fail more as tasks become longer.
arXiv:2608. 02464v1 Announce Type: cross Abstract: LLM agents fail mid-episode -- they loop, cascade tool errors, drift off goal, fabricate results, or silently absorb corrupted content -- and the standard remedy, judging every step with a second LLM, costs more than the agent itself.
arXiv:2607. 26041v1 Announce Type: new Abstract: Computer-use agents (CUAs) increasingly act through desktop GUIs to complete long-horizon tasks.
arXiv:2607. 20436v1 Announce Type: cross Abstract: Safety evaluations often assume that behavior observed during testing reflects behavior in ordinary use, but fine-tuning can break this assumption.
arXiv:2608. 12939v1 Announce Type: new Abstract: Joint-embedding predictive architectures (JEPAs) learn world models that predict in a compact latent space rather than in pixels, reducing the pressure to model nuisance appearance.
arXiv:2607. 01854v1 Announce Type: cross Abstract: Can a platform tell, before deployment, whether an open-weight checkpoint has had its refusal mechanism stripped?