The Long-Range (LoRa) protocol, known for its extensive range and low power, has increasingly been adopted in tags worn by mentally incapacitated persons (MIPs) and others at risk of going missing. We study the sequential decision-making process for a mobile sensor to locate a periodically broadcasting LoRa tag with the fewest moves (hops) in general, unknown environments, guided by the received signal strength indicator (RSSI). While existing methods leverage reinforcement learning for search, they remain vulnerable to domain shift and signal fluctuation, resulting in cascading decision errors that culminate in substantial localization inaccuracies. To bridge this gap, we propose LoRaCompass, a reinforcement learning model designed to achieve robust and efficient search for a LoRa tag. For exploitation under domain shift and signal fluctuation, LoRaCompass learns a robust spatial representation from RSSI to maximize the probability of moving closer to a tag, via a spatially-aware feature extractor and a policy distillation loss function. It further introduces an exploration function inspired by the upper confidence bound (UCB) that guides the sensor toward the tag with increasing confidence. We have validated LoRaCompass in ground-based and drone-assisted scenarios within diverse unseen environments covering an area of over 80km^2. It has demonstrated high success rate (>90%) in locating the tag within 100m proximity (a 40% improvement over existing methods) and high efficiency with a search path length (in hops) that scales linearly with the initial distance.

Searches are conducted to find missing persons and/or objects given uncertain information, imperfect observers and large search areas in Search and Rescue (SAR). In many scenarios, such as Maritime SAR, expected survival times are short and optimal search could increase the likelihood of success. This optimization problem is complex for nontrivial problems given its probabilistic nature. Stochastic optimization methods search large problems by nondeterministically sampling the space to reduce the effective size of the problem. This has been used in SAR planning to search otherwise intractably large problems but the stochastic nature provides no formal guarantees on the quality of solutions found in finite time. This paper instead presents $\rm{A}^{\rm{SAR}}$, an $\varepsilon$-optimal search algorithm for SAR planning. It calculates a heuristic to bound the search space and uses graph-search methods to find solutions that are formally guaranteed to be within a user-specified factor, $\varepsilon$, of the optimal solution. It finds better solutions faster than existing optimization approaches in operational simulations. It is also demonstrated with a real-world field trial on Lake Ontario, Canada, where it was used to locate a drifting manikin in only 150s.

Graphical User Interface (GUI) task automation constitutes a critical frontier in artificial intelligence research. While effective GUI agents synergistically integrate planning and grounding capabilities, current methodologies exhibit two fundamental limitations: (1) insufficient exploitation of cross-model synergies, and (2) over-reliance on synthetic data generation without sufficient utilization. To address these challenges, we propose Co-EPG, a self-iterative training framework for Co -E volution of P lanning and G rounding. Co-EPG establishes an iterative positive feedback loop: through this loop, the planning model explores superior strategies under grounding-based reward guidance via Group Relative Policy Optimization (GRPO), generating diverse data to optimize the grounding model. Concurrently, the optimized Grounding model provides more effective rewards for subsequent GRPO training of the planning model, fostering continuous improvement. Co-EPG thus enables iterative enhancement of agent capabilities through self-play optimization and training data distillation. On the Multimodal-Mind2Web and AndroidControl benchmarks, our framework outperforms existing state-of-the-art methods after just three iterations without requiring external data. The agent consistently improves with each iteration, demonstrating robust self-enhancement capabilities. This work establishes a novel training paradigm for GUI agents, shifting from isolated optimization to an integrated, self-driven co-evolution approach.

As large language models (LLMs) are adopted in an increasingly wide range of applications, user-model interactions have grown in both frequency and scale. Consequently, research has focused on evaluating the robustness of LLMs, an essential quality for real-world tasks. In this paper, we employ simple multi-turn follow-up prompts to evaluate models' answer changes, model accuracy dynamics across turns with Markov chains, and examine whether linear probes can predict these changes. Our results show significant vulnerabilities in LLM robustness: a simple "Think again" prompt led to an approximate 10% accuracy drop for Gemini 1.5 Flash over nine turns, while combining this prompt with a semantically equivalent reworded question caused a 7.5% drop for Claude 3.5 Haiku. Additionally, we find that model accuracy across turns can be effectively modeled using Markov chains, enabling the prediction of accuracy probabilities over time. This allows for estimation of the model's stationary (long-run) accuracy, which we find to be on average approximately 8% lower than its first-turn accuracy for Gemini 1.5 Flash. Our results from a model's hidden states also reveal evidence that linear probes can help predict future answer changes. Together, these results establish stationary accuracy as a principled robustness metric for interactive settings and expose the fragility of models under repeated questioning. Addressing this instability will be essential for deploying LLMs in high-stakes and interactive settings where consistent reasoning is as important as initial accuracy.

Malware detection in real-world settings must deal with evolving threats, limited labeling budgets, and uncertain predictions. Traditional classifiers, without additional mechanisms, struggle to maintain performance under concept drift in malware domains, as their supervised learning formulation cannot optimize when to defer decisions to manual labeling and adaptation. Modern malware detection pipelines combine classifiers with monthly active learning (AL) and rejection mechanisms to mitigate the impact of concept drift. In this work, we develop a novel formulation of malware detection as a one-step Markov Decision Process and train a deep reinforcement learning (DRL) agent, simultaneously optimizing sample classification performance and rejecting high-risk samples for manual labeling. We evaluated the joint detection and drift mitigation policy learned by the DRL-based Malware Detection (DRMD) agent through time-aware evaluations on Android malware datasets subject to realistic drift requiring multi-year performance stability. The policies learned under these conditions achieve a higher Area Under Time (AUT) performance compared to standard classification approaches used in the domain, showing improved resilience to concept drift. Specifically, the DRMD agent achieved an average AUT improvement of 8.66 and 10.90 for the classification-only and classification-rejection policies, respectively. Our results demonstrate for the first time that DRL can facilitate effective malware detection and improved resiliency to concept drift in the dynamic setting of Android malware detection.

When language model (LM) users aim to improve the quality of its generations, it is crucial to specify concrete behavioral attributes that the model should strive to reflect. However, curating such principles across many domains, even non-exhaustively, requires a labor-intensive annotation process. To automate this process, we propose eliciting these latent attributes that guide model reasoning toward human-preferred responses by explicitly modeling them in a self-correction setting. Our approach mines new principles from the LM itself and compresses the discovered elements to an interpretable set via clustering. Specifically, we employ a form of posterior-regularized Monte Carlo Expectation-Maximization to both identify a condensed set of the most effective latent principles and teach the LM to strategically invoke them in order to intrinsically refine its responses. We demonstrate that bootstrapping our algorithm over multiple iterations enables smaller language models (7-8B parameters) to self-improve, achieving +8-10% in AlpacaEval win-rate, an average of +0.3 on MT-Bench, and +19-23% in principle-following win-rate on IFEval. We also show that clustering the principles yields interpretable and diverse model-generated constitutions while retaining model performance. The gains that our method achieves highlight the potential of automated, principle-driven post-training recipes toward continual self-improvement.

We study the problem of learning episodic Markov Decision Processes (MDPs).

Continual learning agents experience a stream of (related) tasks.