arXiv AI

Certified Task-Conditioned Active Observability

The paper introduces the concept of task‑conditioned active observability, defining the minimal interaction cost needed for an autonomous agent to identify task‑relevant states while guaranteeing safe abstention. It formalizes this complexity, proving that task‑predictive equivalence yields a unique minimal sufficient quotient that preserves complexity and eliminates unnecessary distinctions. The authors present theoretical characterizations for deterministic and noisy regimes, and demonstrate a certified observer that reduces sensor usage and model steps while maintaining zero false acceptances in extensive high‑dimensional trials.

arXiv AI
Sep 18

Diagnose, Recover, Certify: Task Readiness under Hidden Dynamics Changes

The paper introduces a framework for diagnosing and recovering from hidden dynamics changes in deployed control policies, focusing on the problem of task readiness under dormant dynamics drift. It proposes an intervention-based Bayesian method called Evidence‑Gated Matched‑Pulse Transport that localizes faults and estimates actuator effectiveness, enabling agents to certify readiness for future tasks with limited, task‑agnostic interactions. The approach is evaluated on diverse benchmarks, measuring readiness coverage, selective risk, interaction cost, and return, and identifies regimes where transported evidence is decisive.

By Nguyen Viet Tuan Kiet, Huynh Thi Thanh Binh
arXiv Computer Vision
Oct 28

How Much Can Best-of-N Help a World Action Model? Measuring Selectable Headroom and Realizing It in Closed Loop

The paper introduces a denoised counterfactual protocol to accurately measure the selectable headroom of world action models (WAMs) and uses these measurements to build a fail‑gated selector. Across four WAMs and two benchmarks, the study shows that the standard estimate overstates selectable headroom, that structured action perturbations can add up to 16 points of headroom, and that imagined futures retain candidate‑outcome information without loss. The selector improves closed‑loop task success from 76.9 % to 81.6 % on held‑out training episodes and from 62.6 % to 69.8 % on unseen tasks.

By Haojia Gao, Yue Cao, Yumin Liu, Haohua Que, Mingkai Liu, Guanqiu Guo, Zhuo Zou, Bokui Chen, Xueqian Wang
arXiv AI
6d ago

Model-Free Runtime Measurement of Task-Relevant Information

The paper introduces Acquisition‑State Telemetry (AST), a model‑free framework that monitors ongoing information gathering in autonomous systems. AST maps raw observations to task‑resolution coordinates and uses a fixed causal monitor to emit two real‑time signals: one indicating prospective progress on unresolved requirements, and another quantifying informational friction when new evidence yields little gain. Experiments across eight varied domains—ranging from search and rescue dialogue to robotic manipulation—show that the friction signal can distinguish unproductive stagnation from purposeful exploration and that penalizing friction in reinforcement learning leads to higher mission success under early‑termination constraints.

By Dimitris Panagopoulos, Adolfo Perrusqu\'ia, Yang Xing, Weisi Guo
arXiv AI
Sep 30

Distinguish or Homogenize: Last-Chance Policy Identification and Risk-Budgeted Recovery under Irreversible Resource Depletion

The paper introduces the Distinguish-or-Homogenize principle, where an agent can either spend resources to differentiate between latent fault models or alter the system state so that the remaining models share a common acceptable policy, eliminating further diagnosis. This leads to the Last-Chance Policy Identification (LCPI) framework, which evaluates correctness at the reached state rather than the initial one, and defines the Last Identifiable Margin (LIM) as the boundary between distinguishing and homogenizing. For deterministic diagnostic graphs, an Exact-LIM recursion is provided, while for noisy finite-horizon recovery the authors propose Risk-Budgeted Compatibility Planning (RBCP), which searches a compatibility-aware frontier under a hard worst-case failure constraint, demonstrating improved risk-feasible recovery in microservice and MiniGrid scenarios.

By Yibo Guo, Xiaodan Wang
arXiv Machine Learning
Nov 2

Certified Behavioral Retention for Continual Adaptation with Held-Out Anchors

Certified Anchor-Based Adaptation (CABA) is a post‑update gate for continual adaptation that reserves historical observations, compares old and candidate policies on frozen representations, and selects the largest interpolation coefficient whose worst‑anchor forward KL divergence stays within a declared budget. The method does not require action labels or complete trajectories and is supported by a theory‑led certification framework that provides uniform behavioral‑divergence bounds under representation‑coverage and Lipschitz assumptions. In a UCI Human Activity Recognition study, CABA reduced mean forgetting from 1.01 % to 0.00 % at a budget ε = 0.05, while slightly lowering final average accuracy.

By Ahanaf Hasan Ariq, Abrar Shahid