arXiv AI
Jun 12
Order Is Not Control
arXiv:2606. 12923v1 Announce Type: cross Abstract: AI alignment, interpretability, steering, and neural perturbation studies identify order-inducing objects.
Order Is Not Control: Driven-Dissipative Response Laws Across Artificial and Biological Systems
arXiv:2606. 12923v2 Announce Type: replace-cross Abstract: AI alignment, interpretability, steering, and neural perturbation studies identify order-inducing objects.
Related stories
arXiv Machine Learning
4d ago
NeuronSifter: Intervention Planning in CNS Microenvironments
NeuronSifter is a framework for planning interventions in central nervous system microenvironments by converting treatment regimens into state‑conditional target‑occupancy fields and propagating them through microenvironment dynamics. It selects measurements based on their expected reduction in intervention loss, integrating typed outcomes into a unified posterior. In synthetic Alzheimer’s disease scenarios, occupancy conditioning improves trajectory probability scores and intervention ordering accuracy, and decision‑directed acquisition reduces terminal risk compared to a Bayesian experimental design planner.
arXiv Machine Learning
Jun 19
Leverage Is Not Reach: A Control-Window Law for Single-Neuron Steering in Language Models
arXiv:2606. 19831v1 Announce Type: cross Abstract: Aligned language models gate behaviors such as refusal and language routing through sparse feed forward neurons, yet no theory predicts when a single neuron intervention controls a behavior coherently rather than collapsing the output.
arXiv AI
Aug 21
Mechanistic Tomography: Designed Measurement for Control-Oriented Interpretability
arXiv:2608. 19338v1 Announce Type: cross Abstract: Mechanistic interpretability seeks quantities that models do not expose directly: represented states, component effects, interactions, and responses to interventions.
arXiv Machine Learning
Jul 31
Safety-Gated Agentic Supervisory Control on a Coupled Distillation Benchmark: Regime Map, Auditable Gate, and Co-Design Findings
arXiv:2607. 27849v1 Announce Type: cross Abstract: An open-weight LLM can write composition setpoints every five minutes.
arXiv AI
Aug 11
Emergence Invariance: From Symbolized Thought to Structural Control
arXiv:2608. 01548v2 Announce Type: replace Abstract: Language-first intelligence is constrained by which distinctions enter its symbolic record, which mappings its language--interpreter--environment complex can execute, and which possibilities can be realized with finite resources.
arXiv AI
Sep 4
ObserverBench: Testing Mechanistic Estimates for Intervention and Control
ObserverBench is a benchmark framework that evaluates whether internal mechanistic estimators—called observers—are suitable for guiding interventions, control, or safety actions in language models. It separates estimation accuracy from the loss incurred by the chosen action, showing that accurate predictions do not always lead to better decisions. Experiments on GPT‑2‑small, Qwen2.5‑7B, Gemma‑2‑9B‑it, and Qwen3.5‑9B demonstrate that observers trained on action loss can reduce deployment loss, while traditional metrics like AUROC may rank monitors differently from actual performance.
arXiv Machine Learning
Jul 13
Present but Rescaled: Chat-to-Agent Transfer of Additive Activation Steering
arXiv:2607. 09156v1 Announce Type: new Abstract: Additive activation steering (injecting a scaled residual-stream direction during generation) is calibrated almost entirely in single-turn chat, yet the models it targets are increasingly deployed as tool-using ReAct agents.
arXiv AI
Jul 28
Gubernaut: A Deterministic Homeostatic Controller for Affect-Regulated LLM Agents, Validated Across Independent Model Families
arXiv:2607. 24339v1 Announce Type: new Abstract: Large language model (LLM) agents inherit reactive failure modes: escalation under provocation, sycophantic drift under flattery, perseveration when stuck.
arXiv Machine Learning
Sep 25
Intrinsic-Extrinsic Coupling in Learning Dynamics
The paper introduces a framework for intrinsic‑extrinsic coupling in learning dynamics, defining it via a continuation‑conditioned value of a constrained learning‑state intervention and observation‑relative fibers. It presents an executable finite‑frame classifier‑head that protects current logits while repairing historical margins, and distinguishes local admissibility, intervention value, and complete‑policy performance. Experiments on CLINC‑derived class‑incremental tasks, output distillation with RoBERTa, and SGDW dynamics demonstrate that coupling can produce both positive and negative interactions, and that coordinated content controls can match or exceed development gains while guided allocation reduces cross‑entropy loss compared to standard replay.
arXiv Machine Learning
Aug 27
LM-X: Explainable Action Modeling with Progress, Event, and Uncertainty Prediction for Generalist Robot Manipulation
LM‑X is a generalist vision‑language‑action policy that augments action prediction with three online, explicitly supervised signals: return‑to‑go (RTG) for task progress, event‑to‑go (ETG) for the next semantic transition, and heteroscedastic action flow for local reliability. By conditioning action generation on these signals, LM‑X embeds explainability directly into control rather than as a post‑hoc explanation. After a 20‑day pretraining run on 64 GPUs, LM‑X outperforms an action‑only backbone by 16.0 points and a single‑head variant by 10.8 points, and achieves 74.1 % success on 50 RoboTwin2.0 tasks and 68.6 % on seven real‑robot tasks, surpassing the GR00T N1.7 baseline.
arXiv Machine Learning
Jun 30
Predictive Objectives Discard Exogenous Control-Relevant Features: A Controlled Mechanistic Study
arXiv:2606. 30068v1 Announce Type: new Abstract: Joint-embedding predictive (JEPA-style) objectives learn representations by predicting future latents.