arXiv:2607. 25132v2 Announce Type: replace Abstract: A central challenge in interpreting learned decision-making systems is to determine whether their internal representations contain concepts that help explain their behavior.
arXiv:2606. 27136v1 Announce Type: new Abstract: For LLM agents in multi-step interactive environments, a key challenge is to make effective use of accumulated interaction experience.
arXiv:2606. 09936v1 Announce Type: cross Abstract: World models are now built on substantially different computational substrates.
arXiv:2606. 12200v1 Announce Type: cross Abstract: We study policy representation learning from unlabeled multi-policy behavioral data.
arXiv:2510. 19244v3 Announce Type: replace Abstract: Deep reinforcement learning (RL) achieves remarkable performance but lacks interpretability, limiting trust in policy behavior.
arXiv:2607. 07235v1 Announce Type: cross Abstract: Explainability remains a key issue in reinforcement learning (RL).
arXiv:2602. 06841v4 Announce Type: replace Abstract: Over the last decade, Explainable AI has primarily focused on interpreting individual model predictions, producing post-hoc explanations that relate inputs to outputs under a fixed decision structure.
arXiv:2606. 00183v1 Announce Type: cross Abstract: Tree search is a central abstraction behind many language-agent reasoning and decision-making tasks: agents must explore actions, remember failures, and backtrack toward promising alternatives.
Activation steering offers a lightweight approach to control language models' behavior at inference time, but whether it succeeds or fails heavily depends on the prompt, concept, model, and steering configuration. Finding the regime and boundaries of successful steering typically requires expensive grid searches and post-hoc evaluation of full autoregressive rollouts.
arXiv:2607. 07316v1 Announce Type: new Abstract: This article offers a comprehensive overview of mechanistic interpretability, an emerging field that seeks to reverse-engineer the internal algorithms of modern neural networks.
arXiv:2602. 23164v2 Announce Type: replace Abstract: Foundation models must handle multiple generative processes, yet mechanistic interpretability largely studies capabilities in isolation; it remains unclear how a single transformer organizes multiple, potentially conflicting "world models".
arXiv:2603. 03031v2 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved strong complex reasoning capabilities through Chain-of-Thought (CoT) reasoning.
arXiv:2605. 30880v4 Announce Type: replace-cross Abstract: World models for interactive text agents must typically be learned from observation-action trajectories alone.