Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization Pressure

Single-axis mitigations of reward-model biases (e.g., reducing proxy reliance on length, sycophancy, or style) can rotate optimization pressure onto correlated proxies rather than eliminate it, a failure mode we call reward bias substitution. The failure is enabled by a measurement-versus-optimization gap between audit and policy-induced distributions during mitigation evaluation and policy training. We formalize mitigation outcomes into a regime taxonomy and prove that successful mitigation, bias substitution, and overcorrection produce identical observables under any audit-distribution scoring, including ranking accuracy and win-rate, even when granted oracle access to the true reward. Across published preference-learning mitigation work, no method we survey reports the evidence needed to certify successful mitigation. Augmenting evaluation with policy-induced distributions while tracking multiple biases provably closes the gap, and we translate this into actionable prescriptions for mitigation methods and benchmarks. We demonstrate bias substitution in language model RLHF, where a length penalty during GRPO training compresses responses as intended yet redirects optimization pressure onto confidence calibration, driving the policy into overconfidence while factual free-form accuracy falls. We also show a published length-debiasing operator that zeroes reward-length correlation on the audit distribution but reintroduces bias under best-of-N selection on three of four SOTA reward models, and a length-sycophancy coupling whose direction reverses under human-LLM judge disagreement.

Mechanistic Interpretability for Learning Assurance of a Vision-Based Landing System

EASA's learning-assurance guidance requires data-driven aviation systems to build and monitor their own situation representation, yet for neural networks the technical means to provide such evidence remain an open problem. We address this gap for a vision-based aircraft landing system: we propose that a minimally assurable model must at least be shown to separate content from style in its own situation representation. Showing that the model's predictions then rely largely on the contentful representation components leads to a concrete assurance path. To demonstrate this assurance path on a concrete model we train a vision transformer model for runway keypoint regression on the LARDv2 dataset. The model, which acts as the subject for our assurance demonstration, produces per-patch embeddings that we decompose into interpretable atoms via K-SVD sparse dictionary learning. A qualitative visualization confirms that contentful atoms track task-relevant runway structure and stylistic atoms track domain-specific appearance, and the regression head is shown to place almost all of its linear weight on contentful atoms. We further build on the content/style separation and define out-of-model-scope (OOMS) detection, a novel runtime assurance approach directly monitoring the model's situation representation. OOMS monitoring is complementary to operational design domain and output-space out-of-distribution monitoring and addresses concrete requirements of the recent EASA guidance. By directly analyzing a model's situation representation both at test time and runtime, this work delivers the first concrete piece of the representation-level evidence that EASA learning-assurance guidance demands, and points to mechanistic interpretability as a practical building block of future aviation safety cases.

Enhancing a Risk Model by Adding Transient Statistical Factors

Estimating the covariance of asset returns, i.e., the risk model, is a key component of financial portfolio construction and evaluation. Most risk modeling approaches produce a factor model that decomposes the asset variability into two components: the first attributed to a small number of factors that are common among the assets and the second attributed to the idiosyncratic behavior of each asset. Third-party providers typically provide risk models to investors, and while these models are typically of high quality, they may fail to capture important information, e.g., changing market regimes and transient factors. To overcome these limitations, we propose a systematic method based on maximum likelihood estimation to enhance an existing factor model by both refining the given model and adding new statistical factors. Our approach relies only on the observed sequence of realized returns and on the choice of two hyperparameters: the number of additional factors and the half-life parameter that determines the weights assigned to returns in the log-likelihood objective. Importantly, our methodology applies to the situation where asset returns may be missing, making it suitable for typical equity datasets. We demonstrate our approach on the Barra short-term US risk model, a high-quality risk model used in practice, for a universe of US high-capitalization equities. We show that the proposed extension captures structure in the returns that is missed by the original model.

Optimizing Task Completion Time Updates Using POMDPs

Managing announced task completion times is a fundamental control problem in project management. While extensive research exists on estimating task durations and task scheduling, the problem of when and how to update completion times communicated to stakeholders remains understudied. Organizations must balance announcement accuracy against the costs of frequent timeline updates, which can erode stakeholder trust and trigger costly replanning. Despite the prevalence of this problem, current approaches rely on static predictions or ad-hoc policies that fail to account for the sequential nature of announcement management. In this paper, we formulate the task announcement problem as a Partially Observable Markov Decision Process (POMDP) where the control policy must decide when to update announced completion times based on noisy observations of true task completion. Since most state variables (current time and previous announcements) are fully observable, we leverage the Mixed Observability MDP (MOMDP) framework to enable more efficient policy optimization. Our reward structure captures the dual costs of announcement errors and update frequency, enabling synthesis of optimal announcement control policies. Using off-the-shelf solvers, we generate policies that act as feedback controllers, adaptively managing announcements based on belief state evolution. Simulation results demonstrate significant improvements in both accuracy and announcement stability compared to baseline strategies, achieving up to 75\% reduction in unnecessary updates while maintaining or improving prediction accuracy.

A Semi-Decentralized Approach to Multiagent Control

We introduce an expressive framework and algorithms for the semi-decentralized control of cooperative agents in environments with communication uncertainty. Whereas semi-Markov control admits a distribution over time for agent actions, semi-Markov communication, or what we refer to as semi-decentralization, gives a distribution over time for what actions and observations agents can store in their histories. We extend semi-decentralization to the partially observable Markov decision process (POMDP). The resulting SDec-POMDP unifies decentralized and multiagent POMDPs and several existing explicit communication mechanisms. We present recursive small-step semi-decentralized A* (RS-SDA*), an exact algorithm for generating optimal SDec-POMDP policies. RS-SDA* is evaluated on semi-decentralized versions of several standard benchmarks and a maritime medical evacuation scenario. This paper provides a well-defined theoretical foundation for exploring many classes of multiagent communication problems through the lens of semi-decentralization.

The FABRIC Strategy for Verifying Neural Feedback Systems

Forward reachability analysis is a dominant approach for verifying reach-avoid specifications in neural feedback systems, i.e., dynamical systems controlled by neural networks, and a number of directions have been proposed and studied. In contrast, far less attention has been given to backward reachability analysis for these systems, in part because of the limited scalability of known techniques. In this work, we begin to address this gap by introducing new algorithms for computing both over- and underapproximations of backward reachable sets for nonlinear neural feedback systems. We also describe and implement an integration of these backward reachability techniques with existing ones for forward analysis. We call the resulting algorithm Forward and Backward Reachability Integration for Certification (FaBRIC). We evaluate our algorithms on a representative set of benchmarks and show that they significantly outperform the prior state of the art.

World Model Failure Classification and Anomaly Detection for Autonomous Inspection

Autonomous inspection robots for monitoring industrial sites can reduce costs and risks associated with human-led inspection. However, accurate readings can be challenging due to occlusions, limited viewpoints, or unexpected environmental conditions. We propose a hybrid framework that combines supervised failure classification with anomaly detection, enabling classification of inspection tasks as a success, known failure, or anomaly (i.e., out-of-distribution) case. Our approach uses a world model backbone with compressed video inputs. This policy-agnostic, distribution-free framework determines classifications based on two decision functions set by conformal prediction (CP) thresholds before a human observer does. We evaluate the framework on gauge inspection feeds collected from office and industrial sites and demonstrate real-time deployment on a Boston Dynamics Spot. Experiments show over 90% accuracy in distinguishing between successes, failures, and OOD cases, with classifications occurring earlier than a human observer. These results highlight the potential for robust, anticipatory failure detection in autonomous inspection tasks or as a feedback signal for model training to assess and improve the quality of training data. Project website: https://autoinspection-classification.github.io

A New Strategy for Verifying Reach-Avoid Specifications in Neural Feedback Systems

Forward reachability analysis is the predominant approach for verifying reach-avoid properties in neural feedback systems (dynamical systems controlled by neural networks). This dominance stems from the limited scalability of existing backward reachability methods. In this work, we introduce new algorithms that compute both over- and under-approximations of backward reachable sets for such systems. We further integrate these backward algorithms with established forward analysis techniques to yield a unified verification framework for neural feedback systems.

Learning to Trust: Bayesian Adaptation to Varying Suggester Reliability in Sequential Decision Making

Autonomous agents operating in sequential decision-making tasks under uncertainty can benefit from external action suggestions, which provide valuable guidance but inherently vary in reliability. Existing methods for incorporating such advice typically assume static and known suggester quality parameters, limiting practical deployment. We introduce a framework that dynamically learns and adapts to varying suggester reliability in partially observable environments. First, we integrate suggester quality directly into the agent's belief representation, enabling agents to infer and adjust their reliance on suggestions through Bayesian inference over suggester types. Second, we introduce an explicit ``ask'' action allowing agents to strategically request suggestions at critical moments, balancing informational gains against acquisition costs. Experimental evaluation demonstrates robust performance across varying suggester qualities, adaptation to changing reliability, and strategic management of suggestion requests. This work provides a foundation for adaptive human-agent collaboration by addressing suggestion uncertainty in uncertain environments.

Robust Planning for Autonomous Vehicles with Diffusion-Based Failure Samplers

High-risk traffic zones such as intersections are a major cause of collisions. This study leverages deep generative models to enhance the safety of autonomous vehicles in an intersection context. We train a 1000-step denoising diffusion probabilistic model to generate collision-causing sensor noise sequences for an autonomous vehicle navigating a four-way intersection based on the current relative position and velocity of an intruder. Using the generative adversarial architecture, the 1000-step model is distilled into a single-step denoising diffusion model which demonstrates fast inference speed while maintaining similar sampling quality. We demonstrate one possible application of the single-step model in building a robust planner for the autonomous vehicle. The planner uses the single-step model to efficiently sample potential failure cases based on the currently measured traffic state to inform its decision-making. Through simulation experiments, the robust planner demonstrates significantly lower failure rate and delay rate compared with the baseline Intelligent Driver Model controller.