arXiv:2608. 13626v1 Announce Type: new Abstract: A hidden state signal can be decodable or causally usable without supporting a reusable action map.
arXiv:2608. 15809v1 Announce Type: new Abstract: Behavioral accuracy, linear decodability, and successful activation interventions do not by themselves show that a model carries an operation-level structure from one symbolic domain to another.
The paper introduces the concept of intervention fidelity in latent world models, measuring whether a model’s open‑loop transitions align with actual environment interventions. Experiments on TD‑MPC2, Cheetah, and DreamerV3 show that high reward fit does not guarantee fidelity, and that self‑supervised models can outperform task‑anchored ones in preserving intervention effects. The authors propose a capture‑gated audit to localize failures and argue that fidelity must be directly audited on the model’s native interface.
arXiv:2605. 09692v3 Announce Type: replace Abstract: Autonomous language agents increasingly expose traces, memories, plans and constraints, but existing evaluations rarely test whether these state variables are bound to final actions.
The paper introduces the concept of causal retention in interactive agents, examining whether a frozen learned state can correctly answer a mechanism‑probe map that is fixed independently of training. It shows that for finite structural causal models the optimal probe error is a Bayes decision risk, vanishing only when each learning‑interface fiber lies within a single probe‑answer fiber, and provides theoretical results such as a posterior‑coverage theorem and an exact edit decomposition. Experiments on finite causal systems, continuous simulators, TD‑MPC2, and Qwen2.5‑7B‑Instruct demonstrate that causal retention can be achieved with high accuracy, outperforming task‑performance‑based approaches.
arXiv:2606. 00930v1 Announce Type: cross Abstract: Mechanistic interpretability often assumes that probes identifying a representational signature also identify the circuit executing the corresponding computation.
FLIP is a final‑layer inference‑time probe designed to test whether a logit‑facing intervention site in an open‑weight vision‑language model (VLM) supports structured, task‑linked computation rather than generic perturbation. The probe applies elementwise flooring to the final normalized hidden state before logit computation, leaving other model components unchanged. By sweeping intervention strength on a controlled detection/counting task, FLIP identifies three regimes—negligible change, a bounded interior regime with improved detection recall and reduced counting error, and over‑suppression—while a four‑criterion protocol ensures the observed effects are mechanistically interpretable.
arXiv:2607. 24425v1 Announce Type: new Abstract: Large language models place structured concepts on geometrically faithful manifolds: weekdays lie on a circle, months on another, usually taken to be a fixed world-model the network stores and looks up.
arXiv:2609.39971v1 Announce Type: cross Abstract: Vision-language-action (VLA) models can exceed 90% success on in-distribution tasks and withstand nuisance changes that preserve the required action,...
arXiv:2608. 03842v1 Announce Type: cross Abstract: When a language model fails on surface-perturbed input (typos, OCR noise, homophones), "which layer is responsible" has three natural operationalizations: where representations diverge most (sensitivity), where restoring clean activations recovers the prediction (causality), and where a small adapter can repair the damage (compensatory capacity) - and we show these three layer maps dissociate.
SCIT (Suffix Cache Interchange Test) is a causal protocol designed to identify which transformer components carry counterfactual computations in latent chain-of-thought models. By constructing exact source‑recipient counterfactuals and applying sufficiency tests, K/V splits, hidden‑state controls, and semantic source controls, SCIT demonstrates that counterfactual arithmetic primarily transfers through value‑cache suffix trajectories rather than hidden states or keys. The method reveals carrier‑regime shifts across different GPT‑2 checkpoints, providing a cache‑level diagnostic and a competence‑gated carrier map for arithmetic mechanisms.
The study investigates whether independently trained language‑model societies share a common packet language and how inherited interface states affect learning. A comprehensive audit of 30 pairwise interactions among six restricted societies shows that only one pair is fully interoperable, another is partially compatible, and the remaining 26 pairs fail across all alignment levels. Further experiments reveal that a globally trained communication interface can act as a severe negative‑transfer prior, but inherited interfaces never outperform fresh‑interface controls by the preregistered margin.
arXiv:2608. 02302v1 Announce Type: cross Abstract: Long-horizon coding-agent trajectories are poorly matched to the credit units available to train on: a single action has no stable value, an episode label merges productive exploration with abandoned directions, and a fixed window cuts where the logging mechanics fall.