arXiv:2607. 20708v1 Announce Type: new Abstract: A recent line of work measures causal emergence in reinforcement learning agents through Integrated Information Decomposition, reporting that $\Phi_r$ grows with training and tracks reward improvement.
arXiv:2607. 11953v1 Announce Type: new Abstract: Does a reinforcement-learning agent that earns high reward represent its task's latent state, or only a reward-correlated shortcut?
arXiv:2608. 02713v1 Announce Type: cross Abstract: Continually improving agents require dynamic interaction feedback beyond static supervision, yet direct real-environment interaction is costly, slow, unsafe, and hard to parallelize.
The paper studies when joint-embedding predictive architectures (JEPAs) can recover underlying causal states from high‑dimensional observations. It introduces a latent variable model where observations arise from causal states with action‑conditioned dynamics, and proposes an information‑theoretic objective that maximizes conditional likelihood while preserving state entropy. The authors prove identifiability conditions—particularly sufficient action‑induced variation—and instantiate the objective as an action‑modulated Gaussian additive‑noise model (A‑JEPA), demonstrating theoretical and empirical success in synthetic and visual benchmarks.
arXiv:2607. 11958v1 Announce Type: new Abstract: Under the free energy principle, a predictive system does not observe reality directly; it maintains a generative model of the world and experiences that model's best current hypothesis.
arXiv:2608.30067v1 Announce Type: cross Abstract: How do LLM agents come to both understand environments they act in and master tasks set within them? Through controlled experiments combining world-m...
Continually improving agents require dynamic interaction feedback beyond static supervision, yet direct real-environment interaction is costly, slow, unsafe, and hard to parallelize. World modeling offers a natural intermediate proxy that allows agents to query lower-cost, more controllable feedback before committing to real actions.
The paper introduces Retrospective World Modeling, a new paradigm for vision‑language‑model (VLM) agents that allows them to reason backward by estimating which action most likely caused a state transition. It proposes the Self‑Consistency Reward (SCR), an intrinsic signal that measures how well a policy action aligns with this retrospective explanation, providing dense transition‑level feedback. Experiments demonstrate that incorporating SCR improves policy robustness and generalization compared to purely prospective world‑modeling approaches.
arXiv:2606. 01520v1 Announce Type: new Abstract: A single action-conditioned latent predictive architecture can in principle be trained on the structured state of a driving scene, a robot workspace, or a financial order book.
The paper proposes CANOPY, a minimalist reinforcement learning protocol that addresses two common pitfalls—signal starvation and policy drift—in outcome‑only RL for long‑horizon interactive tasks. By scaling same‑task exploration, keeping updates on‑policy, and anchoring updates with KL divergence, CANOPY enables a Qwen3‑14B agent to achieve top leaderboard results on the AppWorld coding benchmark without auxiliary supervision or elaborate scaffolding. The approach also improves performance on SWE‑bench for a Qwen3.5‑9B model.
arXiv:2609.16056v1 Announce Type: cross Abstract: Humans carry behaviour knowledge of how to act in familiar situations into every new task rather than relearning it from scratch. There is no reason...
arXiv:2608. 01548v1 Announce Type: cross Abstract: Language can be viewed as a formalized subset of thought: a consequence-governed symbolic structure projected from wider situated cognition.
arXiv:2607. 06648v1 Announce Type: new Abstract: Latent reasoning methods perform multi-step inference entirely in the model's continuous hidden states, promising more compact and efficient reasoning.