arXiv:2606. 05605v1 Announce Type: new Abstract: How does a system that merely predicts the world come to distinguish its own causal influence from everything else?
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.
Prospective Hindsight (PH) is a self‑calibrating training principle for reinforcement learning that augments any retrospective base method with a signal derived from the gap between an agent’s prospective prediction and its retrospective evaluation. By weighting gradients with a stop‑gradient surprise based on this prediction‑reality gap, PH highlights samples where the agent’s self‑model is most inaccurate and encourages the policy and predictor to co‑evolve, progressively focusing on remaining blind spots. Experiments on single‑turn verifiable tasks and a multi‑turn personal‑agent task show that PH improves both task performance and calibration across model scales, addressing overconfident failures in single‑turn settings and underconfident successes in multi‑turn settings.
arXiv:2606. 30191v1 Announce Type: new Abstract: How does an agent that can tell self from world come to be durably shaped by that distinction?
arXiv:2607. 10430v1 Announce Type: cross Abstract: Dimensionality reduction has proven powerful for identifying neural manifolds, which are low-dimensional structures underlying high-dimensional neural activity.
arXiv:2606. 15306v1 Announce Type: cross Abstract: We envision continually learning agentic systems that become more useful over time: as they encounter sequences of related tasks, they should infer the hidden structure shared across those tasks and use it to improve future decisions.
arXiv:2609.17325v1 Announce Type: new Abstract: Biological cells can be viewed as individual, interacting agents whose collective dynamics give rise to adaptive behaviour at multiple levels of organi...
JEPA‑TTT is a method that continuously adapts the latent dynamics predictor of a pretrained Joint‑Embedding Predictive Architecture (JEPA) world model during test time. It performs self‑supervised updates across episodes while keeping the visual encoder and reward head fixed, using dense replay to sample prediction windows from a growing buffer. In experiments on eight dynamics shifts across four continuous‑control environments, JEPA‑TTT reduces latent prediction error by 83% and improves planning performance by 153% compared to the frozen model.