Reward models (RMs) are a core component in the post-training of large language models (LLMs), serving as proxies for human preference evaluation and guiding model alignment. However, training reliable RMs under limited resources remains challenging due to the reliance on large-scale preference annotations and the high cost of fine-tuning LLMs. To address this, we propose SparseRM, which leverages Sparse Autoencoder (SAE) to extract preference-relevant information encoded in model representations, enabling the construction of a lightweight and interpretable reward model. SparseRM first employs SAE to decompose LLM representations into interpretable directions that capture preference-relevant features. The representations are then projected onto these directions to compute alignment scores, which quantify the strength of each preference feature in the representations. A simple reward head aggregates these scores to predict preference scores. Experiments on three preference modeling tasks show that SparseRM achieves superior performance over most mainstream RMs while using less than 1% of trainable parameters.

Modern slavery affects millions of people worldwide, and regulatory frameworks such as Modern Slavery Acts now require companies to publish detailed disclosures. However, these statements are often vague and inconsistent, making manual review time-consuming and difficult to scale. While NLP offers a promising path forward, high-stakes compliance tasks require more than accurate classification: they demand transparent, rule-aligned outputs that legal experts can verify. Existing applications of large language models (LLMs) often reduce complex regulatory assessments to binary decisions, lacking the necessary structure for robust legal scrutiny. We argue that compliance verification is fundamentally a rule-matching problem: it requires evaluating whether textual statements adhere to well-defined regulatory rules. To this end, we propose a novel framework that harnesses AI for rule-level compliance verification while preserving expert oversight. At its core is the Compliance Alignment Judge (CA-Judge), which evaluates model-generated justifications based on their fidelity to statutory requirements. Using this feedback, we train the Compliance Alignment LLM (CALLM), a model that produces rule-consistent, human-verifiable outputs. CALLM improves predictive performance and generates outputs that are both transparent and legally grounded, offering a more verifiable and actionable solution for real-world compliance analysis.

Large Language Models (LLMs) based agents have demonstrated remarkable potential in autonomous task-solving across complex, open-ended environments. A promising approach for improving the reasoning capabilities of LLM agents is to better utilize prior experiences in guiding current decisions. However, LLMs acquire experience either through implicit memory via training, which suffers from catastrophic forgetting and limited interpretability, or explicit memory via prompting, which lacks adaptability. In this paper, we introduce a novel agent-centric, trainable, multi-layered graph memory framework and evaluate how context memory enhances the ability of LLMs to utilize parametric information. The graph abstracts raw agent trajectories into structured decision paths in a state machine and further distills them into high-level, human-interpretable strategic meta-cognition. In order to make memory adaptable, we propose a reinforcement-based weight optimization procedure that estimates the empirical utility of each meta-cognition based on reward feedback from downstream tasks. These optimized strategies are then dynamically integrated into the LLM agent's training loop through meta-cognitive prompting. Empirically, the learnable graph memory delivers robust generalization, improves LLM agents' strategic reasoning performance, and provides consistent benefits during Reinforcement Learning (RL) training.

Securing Dew-Enabled Edge-of-Things (EoT) networks against sophisticated intrusions is a critical challenge. This paper presents HybridGuard, a framework that integrates machine learning and deep learning to improve intrusion detection. HybridGuard addresses data imbalance through mutual information based feature selection, ensuring that the most relevant features are used to improve detection performance, especially for minority attack classes. The framework leverages Wasserstein Conditional Generative Adversarial Networks with Gradient Penalty (WCGAN-GP) to further reduce class imbalance and enhance detection precision. It adopts a two-phase architecture called DualNetShield to support advanced traffic analysis and anomaly detection, improving the granular identification of threats in complex EoT environments. HybridGuard is evaluated on the UNSW-NB15, CIC-IDS-2017, and IOTID20 datasets, where it demonstrates strong performance across diverse attack scenarios and outperforms existing solutions in adapting to evolving cybersecurity threats. This approach establishes HybridGuard as an effective tool for protecting EoT networks against modern intrusions.

Reinforcement learning (RL) systems, while achieving remarkable success across various domains, are vulnerable to adversarial attacks. This is especially a concern in vision-based environments where minor manipulations of high-dimensional image inputs can easily mislead the agent's behavior. To this end, various defenses have been proposed recently, with state-of-the-art approaches achieving robust performance even under large state perturbations. However, after closer investigation, we found that the effectiveness of the current defenses is due to a fundamental weakness of the existing $l_p$ norm-constrained attacks, which can barely alter the semantics of image input even under a relatively large perturbation budget. In this work, we propose SHIFT, a novel policy-agnostic diffusion-based state perturbation attack to go beyond this limitation. Our attack is able to generate perturbed states that are semantically different from the true states while remaining realistic and history-aligned to avoid detection. Evaluations show that our attack effectively breaks existing defenses, including the most sophisticated ones, significantly outperforming existing attacks while being more perceptually stealthy. The results highlight the vulnerability of RL agents to semantics-aware adversarial perturbations, indicating the importance of developing more robust policies.

Artificial Intelligence (AI) models have demonstrated expert-level performance in melanoma detection, yet their clinical adoption is hindered by performance disparities across demographic subgroups such as gender, race, and age. Previous efforts to benchmark the performance of AI models have primarily focused on assessing model performance using group fairness metrics that rely on the Area Under the Receiver Operating Characteristic curve (AUROC), which does not provide insights into a model's ability to provide accurate estimates. In line with clinical assessments, this paper addresses this gap by incorporating calibration as a complementary benchmarking metric to AUROC-based fairness metrics. Calibration evaluates the alignment between predicted probabilities and observed event rates, offering deeper insights into subgroup biases. We assess the performance of the leading skin cancer detection algorithm of the ISIC 2020 Challenge on the ISIC 2020 Challenge dataset and the PROVE-AI dataset, and compare it with the second and third place models, focusing on subgroups defined by sex, race (Fitzpatrick Skin Tone), and age. Our findings reveal that while existing models enhance discriminative accuracy, they often over-diagnose risk and exhibit calibration issues when applied to new datasets. This study underscores the necessity for comprehensive model auditing strategies and extensive metadata collection to achieve equitable AI-driven healthcare solutions. All code is publicly available at https://github.com/bdominique/testing_strong_calibration.

Achieving expert-level performance in simulation-based training relies on the creation of complex, adaptable scenarios, a traditionally laborious and resource intensive process. Although prior research explored scenario generation for military training, pre-LLM AI tools struggled to generate sufficiently complex or adaptable scenarios. This paper introduces a multi-agent, multi-modal reasoning framework that leverages Large Language Models (LLMs) to generate critical training artifacts, such as Operations Orders (OPORDs). We structure our framework by decomposing scenario generation into a hierarchy of subproblems, and for each one, defining the role of the AI tool: (1) generating options for a human author to select from, (2) producing a candidate product for human approval or modification, or (3) generating textual artifacts fully automatically. Our framework employs specialized LLM-based agents to address distinct subproblems. Each agent receives input from preceding subproblem agents, integrating both text-based scenario details and visual information (e.g., map features, unit positions and applies specialized reasoning to produce appropriate outputs. Subsequent agents process these outputs sequentially, preserving logical consistency and ensuring accurate document generation. This multi-agent strategy overcomes the limitations of basic prompting or single-agent approaches when tackling such highly complex tasks. We validate our framework through a proof-of-concept that generates the scheme of maneuver and movement section of an OPORD while estimating map positions and movements as a precursor demonstrating its feasibility and accuracy. Our results demonstrate the potential of LLM-driven multi-agent systems to generate coherent, nuanced documents and adapt dynamically to changing conditions, advancing automation in scenario generation for military training.

Testing marine robotics systems in controlled environments before field tests is challenging, especially when acoustic-based sensors and control surfaces only function properly underwater. Deploying robots in indoor tanks and pools often faces space constraints that complicate testing of control, navigation, and perception algorithms at scale. Recent developments of high-fidelity underwater simulation tools have the potential to address these problems. We demonstrate the utility of the recently released HoloOcean 2.0 simulator with improved dynamics for torpedo AUV vehicles and a new ROS 2 interface. We have successfully demonstrated a Hardware-in-the-Loop (HIL) and Software-in-the-Loop (SIL) setup for testing and evaluating a CougUV torpedo autonomous underwater vehicle (AUV) that was built and developed in our lab. With this HIL and SIL setup, simulations are run in HoloOcean using a ROS 2 bridge such that simulated sensor data is sent to the CougUV (mimicking sensor drivers) and control surface commands are sent back to the simulation, where vehicle dynamics and sensor data are calculated. We compare our simulated results to real-world field trial results.

This technical report describes the AIA Forecaster, a Large Language Model (LLM)-based system for judgmental forecasting using unstructured data. The AIA Forecaster approach combines three core elements: agentic search over high-quality news sources, a supervisor agent that reconciles disparate forecasts for the same event, and a set of statistical calibration techniques to counter behavioral biases in large language models. On the ForecastBench benchmark (Karger et al., 2024), the AIA Forecaster achieves performance equal to human superforecasters, surpassing prior LLM baselines. In addition to reporting on ForecastBench, we also introduce a more challenging forecasting benchmark sourced from liquid prediction markets. While the AIA Forecaster underperforms market consensus on this benchmark, an ensemble combining AIA Forecaster with market consensus outperforms consensus alone, demonstrating that our forecaster provides additive information. Our work establishes a new state of the art in AI forecasting and provides practical, transferable recommendations for future research. To the best of our knowledge, this is the first work that verifiably achieves expert-level forecasting at scale.

The equitable assessment of individual contribution in teams remains a persistent challenge, where conflict and disparity in workload can result in unfair performance evaluation, often requiring manual intervention - a costly and challenging process. We survey existing tool features and identify a gap in conflict resolution methods and AI integration. To address this, we propose a framework and implementation design for a novel AI-enhanced tool that assists in dispute investigation. The framework organises heterogeneous artefacts - submissions (code, text, media), communications (chat, email), coordination records (meeting logs, tasks), peer assessments, and contextual information - into three dimensions with nine benchmarks: Contribution, Interaction, and Role. Objective measures are normalised, aggregated per dimension, and paired with inequality measures (Gini index) to surface conflict markers. A Large Language Model (LLM) architecture performs validated and contextual analysis over these measures to generate interpretable and transparent advisory judgments. We argue for feasibility under current statutory and institutional policy, and outline practical analytics (sentimental, task fidelity, word/line count, etc.), bias safeguards, limitations, and practical challenges.