Large language model-based agents show promise for software engineering, but environment configuration remains a bottleneck due to heavy manual effort and scarce large-scale, high-quality datasets. Existing benchmarks assess only end-to-end build/test success, obscuring where and why agents succeed or fail. We introduce the Environment Configuration Diagnosis Benchmark, Enconda-bench, which provides process-level trajectory assessment of fine-grained agent capabilities during environment setup-planning, perception-driven error diagnosis, feedback-driven repair, and action to execute final environment configuration. Our task instances are automatically constructed by injecting realistic README errors and are validated in Docker for scalable, high-quality evaluation. Enconda-bench combines process-level analysis with end-to-end executability to enable capability assessments beyond aggregate success rates. Evaluations across state-of-the-art LLMs and agent frameworks show that while agents can localize errors, they struggle to translate feedback into effective corrections, limiting end-to-end performance. To our knowledge, Enconda-bench is the first framework to provide process-level internal capability assessment for environment configuration, offering actionable insights for improving software engineering agents.

Testing deep reinforcement learning (DRL) agents in safety-critical domains requires discovering diverse failure scenarios. Existing tools such as INDAGO rely on single-objective optimization focused solely on maximizing failure counts, but this does not ensure discovered scenarios are diverse or reveal distinct error types. We introduce INDAGO-Nexus, a multi-objective search approach that jointly optimizes for failure likelihood and test scenario diversity using multi-objective evolutionary algorithms with multiple diversity metrics and Pareto front selection strategies. We evaluated INDAGO-Nexus on three DRL agents: humanoid walker, self-driving car, and parking agent. On average, INDAGO-Nexus discovers up to 83% and 40% more unique failures (test effectiveness) than INDAGO in the SDC and Parking scenarios, respectively, while reducing time-to-failure by up to 67% across all agents.

-- Robots in the real world need to perceive and move to goals in complex environments without collisions. A voiding collisions is especially difficult when relying on sensor perception and when goals are among clutter . Diffusion policies and other generative models have shown strong performance in solving local planning problems, but often struggle at avoiding all of the subtle constraint violations that characterize truly challenging global motion planning problems. In this work, we propose an approach for learning global motion planning using diffusion policies, allowing the robot to generate full trajectories through complex scenes and reasoning about multiple obstacles along the path. Our approach uses cascaded hierarchical models which unify global prediction and local refinement together with online plan repair to ensure the trajectories are collision free. Our method outperforms ( 5%) a wide variety of baselines on challenging tasks in multiple domains including navigation and manipulation. A key requirement for useful robots is that they can generalize motions to new environments. While classical motion planning algorithms often show good generalization [1], they require privileged information (e.g., full scene geometry) about their world; this has led to interest in neural motion planning approaches which can operate off of raw sensor data [2], [3], [4], [5], [6], and leverage large-scale behavior cloning to guide sampling [7], [2], [3]. However, neural motion planning approaches often struggle at generalizing to the challenging, cluttered environments in which traditional motion planners excel. This limitation is because learned approaches fail to satisfy all of the many constraints necessary for a trajectory to be successful for a high-dimensional multi-modal planning problem.

Real-world sequential decision-making tasks often require balancing trade-offs between multiple conflicting objectives, making Multi-Objective Reinforcement Learning (MORL) an increasingly prominent field of research. Despite recent advances, existing MORL literature has narrowly focused on performance within static environments, neglecting the importance of generalizing across diverse settings. Conversely, existing research on generalization in RL has always assumed scalar rewards, overlooking the inherent multi-objectivity of real-world problems. Generalization in the multi-objective context is fundamentally more challenging, as it requires learning a Pareto set of policies addressing varying preferences across multiple objectives. In this paper, we formalize the concept of generalization in MORL and how it can be evaluated. We then contribute a novel benchmark featuring diverse multi-objective domains with parameterized environment configurations to facilitate future studies in this area. Our baseline evaluations of state-of-the-art MORL algorithms on this benchmark reveals limited generalization capabilities, suggesting significant room for improvement. Our empirical findings also expose limitations in the expressivity of scalar rewards, emphasizing the need for multi-objective specifications to achieve effective generalization. We further analyzed the algorithmic complexities within current MORL approaches that could impede the transfer in performance from the single- to multiple-environment settings. This work fills a critical gap and lays the groundwork for future research that brings together two key areas in reinforcement learning: solving multi-objective decision-making problems and generalizing across diverse environments. We make our code available at https://github.com/JaydenTeoh/MORL-Generalization.

Environment configuration is a critical yet time-consuming step in software development, especially when dealing with unfamiliar code repositories. While Large Language Models (LLMs) demonstrate the potential to accomplish software engineering tasks, existing methods for environment configuration often rely on manual efforts or fragile scripts, leading to inefficiencies and unreliable outcomes. We introduce Repo2Run, the first LLM-based agent designed to fully automate environment configuration and generate executable Dockerfiles for arbitrary Python repositories. We address two major challenges: (1) enabling the LLM agent to configure environments within isolated Docker containers, and (2) ensuring the successful configuration process is recorded and accurately transferred to a Dockerfile without error. To achieve this, we propose atomic configuration synthesis, featuring a dual-environment architecture (internal and external environment) with a rollback mechanism to prevent environment "pollution" from failed commands, guaranteeing atomic execution (execute fully or not at all) and a Dockerfile generator to transfer successful configuration steps into runnable Dockerfiles. We evaluate Repo2Run on our proposed benchmark of 420 recent Python repositories with unit tests, where it achieves an 86.0%

In previous work, the IPMSRL environment (Integrated Platform Management System Reinforcement Learning environment) was developed with the aim of training defensive RL agents in a simulator representing a subset of an IPMS on a maritime vessel under a cyber-attack. This paper extends the use of IPMSRL to enhance realism including the additional dynamics of false positive alerts and alert delay. Applying curriculum learning, in the most difficult environment tested, resulted in an episode reward mean increasing from a baseline result of -2.791 to -0.569. Applying action masking, in the most difficult environment tested, resulted in an episode reward mean increasing from a baseline result of -2.791 to -0.743. Importantly, this level of performance was reached in less than 1 million timesteps, which was far more data efficient than vanilla PPO which reached a lower level of performance after 2.5 million timesteps. The training method which resulted in the highest level of performance observed in this paper was a combination of the application of curriculum learning and action masking, with a mean episode reward of 0.137. This paper also introduces a basic hardcoded defensive agent encoding a representation of cyber security best practice, which provides context to the episode reward mean figures reached by the RL agents. The hardcoded agent managed an episode reward mean of -1.895. This paper therefore shows that applications of curriculum learning and action masking, both independently and in tandem, present a way to overcome the complex real-world dynamics that are present in operational technology cyber security threat remediation.

Software systems are inherently complex. In addition, any ML model is, at its core, probabilistic in nature and hence, suffers from the challenge of uncertainty [2, 3, 4]. The complexity of a software system combined with the non-deterministic nature of an ML model can introduce variability - the phenomenon where a piece of software behaves differently when the development or the runtime environment changes although the internal software artifacts such as code, and input data are exactly the same. In practice it is very likely that development and deployment environments are different, hence, understanding how an ML model may behave differently after deployment compared to how it behaved in the development environment is a crucial aspect of AI-based software development. For example, an arbitrary face recognition system achieving an F1-score of, say 0.9, in the development environment does not guarantee that it will on average achieve a similar F1-score once deployed in a different environment configuration.

This work views the multi-agent system and its surrounding environment as a co-evolving system, where the behavior of one affects the other. The goal is to take both agent actions and environment configurations as decision variables, and optimize these two components in a coordinated manner to improve some measure of interest. Towards this end, we consider the problem of decentralized multi-agent navigation in cluttered environments. By introducing two sub-objectives of multi-agent navigation and environment optimization, we propose an $\textit{agent-environment co-optimization}$ problem and develop a $\textit{coordinated algorithm}$ that alternates between these sub-objectives to search for an optimal synthesis of agent actions and obstacle configurations in the environment; ultimately, improving the navigation performance. Due to the challenge of explicitly modeling the relation between agents, environment and performance, we leverage policy gradient to formulate a model-free learning mechanism within the coordinated framework. A formal convergence analysis shows that our coordinated algorithm tracks the local minimum trajectory of an associated time-varying non-convex optimization problem. Extensive numerical results corroborate theoretical findings and show the benefits of co-optimization over baselines. Interestingly, the results also indicate that optimized environment configurations are able to offer structural guidance that is key to de-conflicting agents in motion.

Safety in the face of uncertainty is a key challenge in robotics. We introduce a real-time capable framework to generate safe and task-efficient robot motions for stochastic control problems. We frame this as a chance-constrained optimisation problem constraining the probability of the controlled system to violate a safety constraint to be below a set threshold. To estimate this probability we propose a Monte--Carlo approximation. We suggest several ways to construct the problem given a fixed number of uncertainty samples, such that it is a reliable over-approximation of the original problem, i.e. any solution to the sample-based problem adheres to the original chance-constraint with high confidence. To solve the resulting problem, we integrate it into our motion planner VP-STO and name the enhanced framework Chance-Constrained (CC)-VPSTO. The strengths of our approach lie in i) its generality, without assumptions on the underlying uncertainty distribution, system dynamics, cost function, or the form of inequality constraints; and ii) its applicability to MPC-settings. We demonstrate the validity and efficiency of our approach on both simulation and real-world robot experiments.

A critical goal of autonomy and artificial intelligence is enabling autonomous robots to rapidly adapt in dynamic and uncertain environments. Classic adaptive control and safe control provide stability and safety guarantees but are limited to specific system classes. In contrast, policy adaptation based on reinforcement learning (RL) offers versatility and generalizability but presents safety and robustness challenges. We propose SafeDPA, a novel RL and control framework that simultaneously tackles the problems of policy adaptation and safe reinforcement learning. SafeDPA jointly learns adaptive policy and dynamics models in simulation, predicts environment configurations, and fine-tunes dynamics models with few-shot real-world data. A safety filter based on the Control Barrier Function (CBF) on top of the RL policy is introduced to ensure safety during real-world deployment. We provide theoretical safety guarantees of SafeDPA and show the robustness of SafeDPA against learning errors and extra perturbations. Comprehensive experiments on (1) classic control problems (Inverted Pendulum), (2) simulation benchmarks (Safety Gym), and (3) a real-world agile robotics platform (RC Car) demonstrate great superiority of SafeDPA in both safety and task performance, over state-of-the-art baselines. Particularly, SafeDPA demonstrates notable generalizability, achieving a 300% increase in safety rate compared to the baselines, under unseen disturbances in real-world experiments.