Environment

The development on robust perception systems for Maritime Autonomous Surface Ships (MASS) is heavily constrained by the scarcity of diverse training data, particularly for adverse weather and low-light conditions. Because collecting paired images in dynamic maritime environments is physically impossible, synthetic data generation via unpaired image-to-image translation offers a critical solution. However, existing generative models suffer from failing to preserve the fine structural details of small navigational objects due to latent compression bottlenecks. In this paper, we introduce a framework for generating synthetic maritime data using CycleGAN-turbo, a one-step unpaired translation architecture. By incorporating zero-convolution skip connections to bypass the Variational Autoencoder (VAE) bottleneck, our approach explicitly preserves small object details (e.g., distant vessels and sea marks) during translation. We compiled a dataset of 7,000 maritime images to train and evaluate models for Day-to-Foggy, Day-to-Sunset, and Day-to-Night domain translations. Qualitative evaluations and variable-strength inference studies demonstrate that our method effectively synthesizes realistic atmospheric conditions while maintaining the underlying semantic structure of the scene. The Day-to-Foggy and Day-to-Sunset models exhibit great structural retention, whereas the Day-to-Night model highlights the challenge of semantic hallucination, such as generating artificial coastal lights, induced by unbalanced training distributions. Ultimately, this work establishes an efficient, structure-aware data synthesis pipeline that directly addresses the data scarcity bottleneck in autonomous maritime navigation.

Large language models (LLMs) are increasingly used in sustainability-related decision support, reporting, and public communication, yet little systematic evidence exists on the environmental attitudes embedded in their outputs. This paper develops a benchmark for evaluating environmental cognition, affect, and behavioural recommendations in LLMs and applies it to 31 widely used proprietary and open-weight models. Drawing on questions from established environmental awareness surveys and additional sustainability-related behavioural measures, we compare LLM responses 1) among models and 2) between models and human survey benchmarks from Germany. We assess their robustness across prompting conditions. We find that many LLMs align more closely with environmentally progressive attitudes than the average survey respondent, exhibiting higher levels of environmental affect and cognition and recommending behaviours associated with substantial potential CO2 reductions. At the same time, we observe no systematic relationship between sustainability-oriented responses and model origin, size, or release context. However, models exhibit contextual sensitivity, controlled by persona-based prompting and show sycophantic shifts mirroring user-specified ideological positions, which raises concerns about steerability and normative reliability in real-world deployments. Our findings provide a reusable evaluation framework for assessing sustainability-related value alignment in LLMs and highlight the importance of governance, transparency, and critical oversight as AI systems become increasingly embedded in sustainability transformations and public decision-making.

Causal discovery aims to recover directed causal relations from observational and interventional data, providing a basis for mechanistic understanding and reliable decision-making. Causal discovery foundation models (CDFMs) seek to amortize this problem by mapping a dataset directly to a causal graph in a single forward pass, avoiding per-dataset testing, search, or optimization. However, existing CDFMs remain limited, often failing to consistently match strong classical methods, and we find that a key bottleneck is how causal pretraining tasks are constructed. Based on this observation, we propose TabCausal, a data-driven CDFM trained with broad causal pretraining over diverse graph priors, structural mechanisms, noise models, dimensions, sample sizes, and intervention regimes. A dynamic task construction strategy composes these causal environments into varied discovery tasks, enabling more transferable structural learning from observational and mixed-interventional data. On large-scale synthetic benchmarks, TabCausal achieves better macro-averaged performance than a diverse set of causal discovery baselines. To further bridge abstract synthetic generators and realistic causal reasoning scenarios, we introduce a protocol-guided and LLM-audited semantic causal environment benchmark, where domain-grounded SCMs generate interpretable observational and interventional datasets for out-of-distribution analysis. Across both synthetic and semantic environments, TabCausal demonstrates robust structure recovery, especially under interventional evidence, highlighting broad causal pretraining as a key ingredient for transferable amortized causal discovery.

Embodied intelligence is often studied through specialized models for individual tasks such as manipulation or navigation, resulting in fragmented capabilities and limited generalization across tasks, environments, and robot embodiments. In this work, we study whether heterogeneous embodied decision-making problems can be unified within a single vision-language-action model. We present Qwen-VLA, a unified embodied foundation model that extends Qwen's vision-language modeling stack from perception, understanding, and reasoning to continuous action and trajectory generation through a DiT-based action decoder. Qwen-VLA is trained with a large-scale joint pretraining recipe over diverse data sources, including robotics manipulation trajectories, human egocentric demonstrations, synthetic simulation data, vision-and-language navigation data, trajectory-centric supervision, and auxiliary vision-language data. To support multiple robot platforms, we introduce embodiment-aware prompt conditioning, where robot-specific textual descriptions specify the current embodiment and control convention. We further cast manipulation, navigation, and trajectory prediction into a unified action-and-trajectory prediction framework, enabling transferable visual grounding, spatial reasoning, and continuous action generation across robot morphologies, task families, and environments. Experiments on manipulation, navigation, and trajectory-centric benchmarks show consistent multi-task performance and out-of-distribution generalization under variations in scene layout, background, lighting, object configuration, and robot embodiment. Qwen-VLA-Instruct achieves 97.9% on LIBERO, 73.7% on Simpler-WidowX, 86.1%/87.2% on RoboTwin-Easy/Hard, 69.0% OSR on R2R, 59.6% SR on RxR, 76.9% average OOD success in real-world ALOHA experiments, and 26.6% zero-shot success on DOMINO dynamic manipulation.

As autonomous language model agents proliferate, forming an emerging agentic web with real-world consequences, what credibility signals can you use to decide whether to trust an unfamiliar agent in the wild and delegate to it? A natural governance intuition is to extend human identity verification and reputation mechanisms, from "Know Your Customer" and credit scores to "Know Your Agent" regimes. However, we argue that this analogy is fundamentally incomplete. Reputation mechanisms function both as social signals and as corrective feedback that sustain an equilibrium of trustworthy behavior, presuming a persistent identity associated with behavioral continuity, sanction sensitivity, and costly non-fungibility. Yet language model agents are ontologically dissociative: they are essentially an assemblage of mutable modules--foundation models, system prompts, tool-access policies, external memory, and, in some cases, a multi-agent system as a whole--any of which may change agent behavior--with a fluid persona that is also vulnerable to adversarial attack and may not internalize sanctions. Drawing on dissociative identity disorder jurisprudence, this dissociativity leaves agents without grounding for identifiability, predictability, credibility, and rehabilitability--the very properties that reputation mechanisms aim to sustain--thereby collapsing trust. We argue that identity-based, ex post, regulative, sanction-based governance, such as reputation, is structurally inapplicable to dissociative agents, and we suggest a shift to observability-based, ex ante, constitutive, protocol-based behavioral harnesses.

Semantic segmentation is crucial for autonomous navigation in off-road environments, enabling precise classification of surroundings to identify traversable regions. However, distinctive factors inherent to off-road conditions, such as source-target domain discrepancies and sensor corruption from rough terrain, can result in distribution shifts that alter the data differently from the trained conditions. This often leads to inaccurate semantic label predictions and subsequent failures in navigation tasks. To address this, we propose ST-Seg, a novel framework that expands the source distribution through style expansion (SE) and texture regularization (TR). Unlike prior methods that implicitly apply generalization within a fixed source distribution, ST-Seg offers an intuitive approach for distribution shift. Specifically, SE broadens domain coverage by generating diverse realistic styles, augmenting the limited style information of the source domain. TR stabilizes local texture representation affected by style-augmented learning through a deep texture manifold. Experiments across various distribution-shifted target domains demonstrate the effectiveness of ST-Seg, with substantial improvements over existing methods. These results highlight the robustness of ST-Seg, enhancing the real-world applicability of semantic segmentation for off-road navigation.

Mastering terminal environments requires language agents capable of multi-step planning, feedback-grounded execution, and dynamic state adaptation. However, training such agents is currently bottlenecked by a reliance on scraped external repositories, which limits domain diversity, environment controllability, and the targeting of specific capability deficits. We introduce LiteCoder-Terminal-Gen, a zero-dependency synthesis pipeline that autonomously generates executable and verifiable terminal training environments directly from domain specifications. Using this framework, we construct two large-scale resources: LiteCoder-Terminal-SFT, comprising 11,255 expert trajectories across 10 domains, and LiteCoder-Terminal-RL, featuring 602 verifiable environments for trajectory-level preference optimization. Supervised fine-tuning of Qwen-family models on our SFT dataset yields agents that significantly outperform their base counterparts. Notably, our 32B variant achieves 29.06%, 18.54%, and 34.00% pass@1 on Terminal Bench 1.0, 2.0, and Pro, respectively. Furthermore, applying Direct Multi-turn Preference Optimization (DMPO) on our RL environments yields additional performance gains. These results systematically demonstrate that fully synthetic, executable environments offer a scalable and verifiable supervision signal for mastering complex, real-world command-line workflows.

A central bottleneck for phone-use agents is that controllable, reproducible environments covering real mobile behavior are hard to build at scale. Existing mobile-agent benchmarks have made important progress on evaluation, but they do not by themselves provide a scalable way to construct many new phone-use environments. We present PhoneWorld, a reusable pipeline that converts real GUI trajectories and screenshots into controllable phone-use environments, executable tasks, automatic verifiers, and training rollouts. Rather than hand-building one mobile benchmark at a time, PhoneWorld uses real trajectories to recover which screens matter, how screens connect, which interactions must change environment state, and which user goals admit automatic verification. From these signals, it builds runnable mock Android apps backed by read-only app content and mutable state, then derives executable tasks, rule-based verifiers, and training rollouts from the same environments. In its current instantiation, PhoneWorld covers 34 apps across 16 domains, spanning common consumer mobile behaviors such as search, browsing, shopping, booking, media, and social interaction. Under a fixed training budget, replacing 10K steps from an auxiliary AndroidWorld corpus in an AndroidWorld-based baseline with broad PhoneWorld supervision improves all four evaluation benchmarks at once, raising HYMobileBench by 17.7 points, AndroidControl by 6.0 points, AndroidWorld by 14.7 points, and PhoneWorld by 52.5 points. We then study two additional scaling questions: increasing the amount of PhoneWorld supervision strongly improves PhoneWorld performance, and under a fixed PhoneWorld budget, expanding app coverage yields even larger gains. Overall, PhoneWorld shifts the focus from building one mobile benchmark at a time to scaling the supply of phone-use environments themselves.

Unix competence is the ability to use shell and operating-system primitives as first-class tools, not merely to write programs through a terminal. Current terminal benchmarks tend to blur this distinction: a solver fluent in Python but weak in Unix can pass a substantial fraction of Terminal-Bench 2.0, while the reverse skill profile is rarely exercised. We make the distinction operational and build a training surface for the Unix component. unix-ctf is a procedural generator of capture-the-flag tasks for shell agents. Each task hides a short token (a flag of the form flag(a3b1c9...)) inside a fresh Linux container using a single Unix feature, and the agent must recover it. Tasks are produced by an LLM-assisted synthesis pipeline that generates candidate hiding techniques, rewrites them into parameterized hide-and-find script pairs, and filters them with a bidirectional contract: the hide script must leave no plaintext trace of the flag on disk, and the find script must recover the flag in a fresh directory. Because the LLM only writes the planting and recovery steps (the container, layout, and grading harness are fixed), the pipeline lands 656 of 750 raw attempts as portable, reusable variants (87.5%). Our reproduction of Endless Terminals' full-container-generation approach lands only 17.4% under the same checks. The 656 variants canonicalize to 155 distinct techniques. Fine-tuning Qwen3-8B with LoRA using GRPO on this surface lifts solve rate from 11.6% to 43.6% on a 15-skill multi-family holdout (n=225), redistributes which InterCode-CTF tasks the model solves, and produces a +33 pp gain in Forensics while reaching 32/100 on InterCode-CTF. These results suggest that Unix competence is separable, trainable, and best evaluated directly rather than folded into programming-through-a-shell.

World models have enabled interactive exploration of game environments and robotic manipulation, but physical engineering remains beyond their reach: real materials exhibit nonlinear constitutive laws, carry history-dependent internal state, undergo inertial dynamics, and may possess hierarchical structures spanning multiple length scales. We present LEIA (Learned Environment for Interactive Architected materials), a world model that lets engineers apply boundary conditions step by step and observe the resulting deformation and stress fields in real time. LEIA handles large three-dimensional unstructured meshes and generates autoregressive responses to user-specified loading. We introduce MicroPlate, a benchmark of architected plates spanning two regimes of microstructure modeling: architected lattices that resolve microstructure explicitly through three-dimensional geometry, and a homogeneous plate where microstructural change is modeled implicitly through internal degrees of freedom. MicroPlate is used to assess LEIA alongside four baseline methods across both regimes. Finally, we demonstrate that LEIA enables efficient candidate generation and ranking for fast surrogate-guided search for de novo designs of architected materials, with stress-accurate candidate ranking validated by finite element ground truth.

Global biodiversity is declining at unprecedented rates, yet the tools available to monitor and protect ecosystems remain limited by constraints in power, connectivity, and accessibility. We present SPARROW, a hardware and software open-source platform that integrates solar energy, edge artificial intelligence, and satellite communication to enable continuous, autonomous biodiversity monitoring in remote environments. Each SPARROW node combines a low-power Graphics Processing Unit (GPU) with modular visual, acoustic, and environmental sensors, performing on-device deep learning inference and transmitting summarized results through Low-Earth-Orbit (LEO) satellite or Global System for Mobile Communications (GSM) networks. We deployed SPARROW across tropical, temperate, and montane ecosystems in Colombia, Peru, Tanzania, and the United States, where it sustained 24/7 operation under variable environmental conditions and collected more than two million images and acoustic recordings in the first 190 days. The system demonstrated robust real-time classification and adaptive power management, achieving full autonomy without on-site human intervention. By integrating renewable energy, on-edge AI, and open-source design, SPARROW lowers the technical and financial barriers to ecological monitoring and establishes a scalable foundation for a distributed, intelligent network of sensors, an emerging "Internet of Living Things" for planetary biodiversity monitoring.

Information localization within massive repositories is a cornerstone of agentic LLM systems. While synthetic data-driven optimization has proven successful in training LLMs, little attention has been paid to optimizing the agent's working environment (the repository itself) in a data-driven manner. To bridge this gap, we present Libra, a self-evolving framework that introduces mutable "catalogs" (hierarchical Markdown files serving as navigable indices) into the repository. Libra runs an LLM-driven optimization loop where a Prompter generates synthetic queries, a frozen Solver attempts to resolve them by navigating the catalogs, and a Healer rewrites the catalogs in response to the Solver's localization failures. Evaluations across 12 SWE-bench Lite repositories demonstrate that this environmental healing yields continual, logarithmic improvements in code localization accuracy. Furthermore, these environmental improvements transfer zero-shot across different LLMs and problem sets. Although the focus of this paper is to study the general behavior of such a system, we also demonstrate that a minimalist coding agent equipped with Libra-optimized catalogs outperforms state-of-the-art baselines. Code is available at https://github.com/salesforce-misc/Libra and data at https://huggingface.co/datasets/Salesforce/Libra.

AI coding agents are increasingly used to write real-world software, but ensuring that their outputs are correct remains a fundamental challenge. Formal verification offers a promising path: an agent generates code together with a machine-checked proof, guaranteeing that the code satisfies a formal specification. However, there is no guarantee that the formal spec itself matches the user's intent. In this work, we study specification autoformalization: whether LLM agents can translate informal programming problems into faithful formal specifications. We introduce Verus-SpecBench, a benchmark of 581 spec-writing tasks derived from Codeforces problems targeting Verus, a verifier for Rust, and Verus-SpecGym, an agentic environment in which models interact with Verus, bash, & the filesystem to develop these specs. The central challenge is evaluation: expert-written reference specs are expensive to write, & LLM judges can miss subtle mistakes. We address this by (a) extending Verus's exec_spec mechanism so that generated specs can be executed as Rust code, & (b) testing them against official Codeforces tests & adversarial cases extracted from Codeforces "hacks", which are edge cases written by competitors to break incorrect solutions. On Verus-SpecBench, the strongest model, Gemini 3.1 Pro, solves 77.8% of tasks, other frontier models solve 51.1--57.8% & OSS models reach only 21.5--25.5%. Our analysis of failure modes shows that model-generated specs can omit important input assumptions, accept incorrect outputs, & reject valid ones. We also find that LLM-as-a-judge evaluation misses 26% of the failures our evaluator catches. Overall, our results suggest that spec autoformalization is within reach for frontier agents but remains brittle even on problems where they can already generate correct code. The code, data, & logs can be found at https://github.com/formal-verif-is-cool/verus-spec-gym

We consider the challenge of developing agents that efficiently interact with high-dimensional, evolving environments, towards a view of practical reinforcement learning (RL) agents interacting with open worlds, of which they witness and affect only a small part. We argue that canonical fluid mechanics problems, and their simulations, present a compelling testbed for the development of such methods. These problems arise in nonlinear instabilities, where small disturbances can grow to transform the dynamics of a system. Nonlinear instabilities represent several open scientific challenges with industrial applications -- the droplet breakup of a liquid jet, mixing at an interface between two fluids, and the appearance of unusually tall rogue waves in the ocean. In these settings, agents may leverage preserved representations across the changing dynamics to learn efficiently. We present two problem descriptions of agents interacting with a fluid mechanical environment, and describe the state and action spaces, and reward functions, for these agents. For these examples, we specify the aspects of the environment which are nonstationary and the preserved invariances. We note Dedalus and JAX-CFD as open-source simulators that can be used for the development of reinforcement learning methods (Burns et al., 2016; Kochkov et al., 2021)) We demonstrate the use of Dedalus for environment generation by creating RL agents that learn to navigate in a stationary environment that is simulated using Dedalus. This sets the stage for future development of RL agents that learn to meaningfully interact with simulated environments that represent scientific challenges in natural and industrial flows.

Autonomous robot teams navigating partially known environments face costly backtracking when ground robots encounter blocked roads that are only revealed upon physical traversal. We address this with Scout-Assisted Planning, a heterogeneous planning framework in which scouting Unmanned Aerial Vehicles proactively gather environmental information to improve Unmanned Ground Vehicle navigation. To focus scouting on the most consequential edges, we propose Information Gain-based Action Pruning, which scores candidate scouting actions by their expected impact on ground robot behavior. Since exact Information Gain-based Action Pruning computation is prohibitively expensive, we develop a Graph Neural Network based model that predicts information gain values directly from graph structure and belief state, reducing planning time to real-time levels without sacrificing solution quality. Experiments across three environment types show that SAP with Information Gain Action Pruning reduces ground robot travel cost by 31.9--37.7% over the Canadian Traveler Problem baseline, and outperforms proximity-based scouting guidance by an additional 8--14%, confirming that principled information-gain-guided scouting is both more effective and computationally feasible for real-world deployment

Wheeled-legged robots, which have wheels at their feet and achieve high mobility by coordinating wheel drive and leg drive, have been developed. These robots have been developed purely as platforms specialized for locomotion. Therefore, they do not have a means to repurpose their legs for roles other than locomotion, such as object manipulation or tool utilization. In this paper, we address the problem of how to draw out the potential task-execution capability of the legs by freeing them from the roles of locomotion through external body support. To this end, we propose and develop a new robot, WiXus, which fuses a wheeled-legged mechanism with a wire-driven mechanism that utilizes the external environment. The developed WiXus demonstrates not only planar locomotion with wheeled-legged drive, but also three-dimensional mobility such as cliff climbing by coordinating wire-driven and wheeled-legged actuation. Furthermore, by suspending the body with wire-driven actuation, WiXus successfully repurpose its legs as arms to perform object manipulation, (e.g., rescuing a dog (stuffed animal)), and tool utilization (e.g., harvesting an apple (mockup) with loppers). This study demonstrates that the approach of utilizing the environment with wire-driven actuation is a new design principle that extends the operational domain of wheeled-legged robots.

Terminal agents extend Large Language Models with the ability to execute tasks directly in command-line environments, but their progress is bottlenecked by the scarcity of high-quality training data. Existing approaches bootstrap from partial sources such as human-defined seeds or GitHub repositories to instantiate one component and then complete the rest, producing tasks confined to narrow seed distributions, environments misaligned with task semantics, and inefficient trajectories from unguided exploration. To address these limitations, we introduce Terminal-World, a fully automated pipeline that uses agent skills as the central synthesis primitive, which jointly encode what to accomplish, when to apply (preconditions and environment state), and how to execute, enabling task instructions, environments, and teacher trajectories to be co-derived. To further broaden the synthesis space, Terminal-World composes skills into skill teams and skill graphs for multi-role and cross-domain task synthesis. Using this pipeline, we construct 5,723 training environments and train Terminal-World-8B/14B/32B, evaluated across 6 benchmarks where the Terminal-World series consistently outperforms terminal-agent baselines. Notably, using the same teacher model and only 1.2% of the training data, Terminal-World-32B surpasses Nemotron-Terminal-32B on Terminal-Bench 2.0 by +4.5 Pass@1 (31.5) and achieves 43.8 Pass@3.

Advancements at the intersection of computer vision and natural language processing are crucial for applications like assistive tech, multimedia querying, and robotics. This dissertation proposes novel architectures to improve intelligent agents across three key vision-language tasks: image captioning, visual dialog, and interactive instruction following. First, we address limitations in visual representation for image captioning. Traditional models rely on region-based features from CNN detectors, which lack global context and suffer from high computational overhead. We propose GRIT (Grid and Region-based Image captioning Transformer), a transformer-only architecture. By integrating grid and region features using a DETR-based detector, GRIT enables end-to-end training and out-performs prior methods in both inference accuracy and speed. Second, we tackle visual dialog, which requires multi-turn conversation about an image. The challenge lies in efficiently modeling interactions between multiple inputs (image, question, history). We introduce LTMI (Light-weight Transformer for Many Inputs). Utilizing a specialized attention block, an LTMI layer matches the representational power of a standard Transformer extension while utilizing less than one-tenth of its parameters, as validated on the VisDial dataset. Finally, we study interactive instruction-following for embodied AI using the ALFRED dataset. We propose a framework featuring a two-stage instruction interpretation: it first decodes language directives independently of visual context to predict a tentative action-object sequence, which is then fused with visual features for final execution. Using multiple egocentric views and hierarchical attention, our method accurately localizes objects and achieves a state-of-the-art unseen success rate of 8.37%.

Aligning autonomous agents with human intent remains a central challenge in modern AI. A key manifestation of this challenge is reward hacking, whereby agents appear successful under the evaluation signal while violating the intended objective. Reward hacking has been observed across a wide range of settings, yet methods for reliably measuring it at scale remain lacking. In this work, we introduce a new evaluation paradigm for measuring reward hacking. Whereas prior studies have primarily analyzed it post hoc by inspecting agent trajectories, we instead embed detectable reward hacking opportunities directly into environments. This makes their exploitation verifiable by design, enabling deterministic and automated measurement of whether and how agents exploit such vulnerabilities. We instantiate this approach in $\textit{TextArena}$ and release $\textit{Hack-Verifiable TextArena}$, a testbed in which reward hacking can be measured reliably. Using this benchmark, we analyze reward hacking behavior across language models in diverse environments and settings. We open source the code at https://github.com/MajoRoth/hack-verifiable-environments/.

Autonomous navigation in GNSS-denied environments remains a core challenge for legged robots, where exteroceptive sensors such as LiDAR are prone to elevation drift in geometrically sparse or repetitive scenes. We present a factor graph architecture that augments the LIO-SAM framework with a parallel kinematic lane driven by proprioceptive leg odometry, coupled to the main LiDAR-inertial lane via an identity relative pose constraint with a selective noise model. Applied to a Linxai D50 quadruped platform across two outdoor loops totaling over one kilometer, our approach reduces elevation drift from over 30m to under 30cm and enables convergence in a scene where the baseline pipeline fails entirely. These results suggest that proprioceptive data, already computed onboard for gait control, constitutes a lightweight and effective vertical anchor for SLAM in GNSS-denied settings.

The progression of reinforcement learning algorithms have been driven by challenging benchmarks. The rate in which a researcher can iterate on a problem setting directly impacts the speed of algorithm development. Modern machine learning has produced tools that allow for fast and scalable algorithm development like the JAX library. With the availability of these tools, a serious bottleneck in algorithm development is the availability of large and complex domains for experimentation. Most notably, the JAX reinforcement learning ecosystem does not have any benchmarks that test visual first-person tasks; these domains are crucial for testing both exploration and an agent's ability to overcome partial observability. We introduce JAXenstein: an open-source JAX-based benchmark that implements the Wolfenstein 3D rendering engine for fast and scalable experimentation in visual first-person tasks. JAXenstein is several times faster than comparable vision-based benchmarks, and is easily extensible to more complex first-person domains.

Accurate camera viewpoint estimation under sparse-view conditions remains challenging, particularly in two-view scenarios. Recent approaches leverage diffusion models such as Zero123 to synthesize novel views conditioned on relative viewpoint, showing promising results when repurposed for viewpoint estimation via optimization with MSE loss. However, existing methods often suffer from nonconvex loss landscape with numerous local minima, making them sensitive to initialization and reliant on naive multistart strategies. We analyze these optimization challenges and visualize failure cases, showing that geometric ambiguities, such as symmetry and self-similarity, can mislead gradient-based updates toward incorrect viewpoints. To address these limitations, we propose a score-based method that reshapes the optimization landscape to guide updates toward the ground-truth viewpoint, followed by a refinement stage using a viewpoint-conditioned diffusion model. Experiments show that our method improves convergence, reduces reliance on brute-force sampling, and achieves competitive accuracy with higher sample-efficiency.

The simultaneous localization and mapping community has introduced a growing number of systems adapted for multi-session operations where the operational environment features low-dynamic changes that impact mapping, such as surface wear, weather phenomena, or seasonal change. These systems allow for lifelong operations by a robot within these environments. There is also growing interest in operations in environments where the unique ground texture is the only mapping feature available for use. These ground texture systems are not yet targeted for multi-session low-dynamic-change environments though. This work explores the impact of three different techniques on trajectory estimation accuracy in these multi-session low-dynamic ground texture environments. Of the three, the use of Kullback-Leibler Divergence, as a similarity score and a bias influencing loop closure confidence, is found to have the most success. We show an analysis of all three methods and a deeper exploration of the impact of Kullback-Leibler Divergence. We also introduce a dataset for use by the robotics community that contains multi-session images where the ground changes between sessions and also high-accuracy pose information for use in evaluation.

Environmental science plays a pivotal role in safeguarding ecosystems, a domain driven by large-scale, heterogeneous data. In the big data era, artificial intelligence (AI) has emerged as a transformative tool for learning patterns and supporting decision-making. This dissertation develops AI-based approaches tailored to complex environmental science problems to achieve Environmental Intelligence, studying three specific challenges. First, we focus on flood prediction and management in coastal river systems. Conventional physics-based models are computationally intensive, limiting real-time application. To overcome this, we propose a deep learning (DL)-based model, WaLeF, for water level forecasting, and a forecast-informed DL model, FIDLAr, to manage water levels. Evaluated in a flood-prone coastal system in South Florida characterized by extreme rainfall and sea level fluctuations, FIDLAr outperforms baselines in accuracy and efficiency while providing interpretable outputs. Second, we target global weather prediction, which is challenged by massive data scale. Traditional physics methods are deterministic and computationally heavy. We propose CoDiCast, a conditional diffusion model tailored for probabilistic weather forecasting. Adapted from generative AI for predictive tasks, experiments show CoDiCast achieves accurate, efficient forecasts with explicit uncertainty quantification. Lastly, we address scientific question-answering in environmental science. When answering in-domain questions, large language models (LLMs) often suffer from hallucinations due to out-of-date or limited knowledge. While retrieval-augmented generation (RAG) retrieves domain-specific knowledge, existing methods trade off accuracy, efficiency, or explainability. We propose Hypercube-RAG, built on a structured text cube framework, which successfully exhibits all three properties simultaneously.

Safe motion planning in uncertain, time-varying environments is challenging because the safe region can change unpredictably across planning steps, often causing a loss of recursive feasibility. In this work, we present a Probabilistic Recursively Feasible Model Predictive Control (PRF-MPC) framework that guarantees recursive feasibility with a specified probability. We introduce properties that an ideal predictor should satisfy to ensure distributional consistency, and use these properties to derive closed-form expressions for the means and covariances of trajectories predicted at future time steps. Building on this analysis, we construct safety constraints that ensure, with high probability, that the current safe set is contained within the safe sets at future time steps, thereby probabilistically guaranteeing recursive feasibility. Simulation results on a lane-change scenario demonstrate that the proposed method significantly improves recursive feasibility.

Equipping LLMs with tool-use capabilities via Agentic Reinforcement Learning (Agentic RL) is bottlenecked by two challenges: the lack of scalable, robust execution environments and the scarcity of realistic training data that captures implicit human reasoning. Existing approaches depend on costly real-world APIs, hallucination-prone LLM simulators, or synthetic environments that are often single-turn or depend on pre-collected documents. Moreover, synthetic trajectories are frequently over-specified, resembling instruction sequences rather than natural human intents, reducing their effectiveness for RL training. We introduce EnvFactory, a fully automated framework that addresses both challenges. EnvFactory autonomously explores and verifies stateful, executable tool environments from authentic resources, and synthesizes natural multi-turn trajectories through topology-aware sampling and calibrated refinement, producing grounded queries with implicit intents. Using only 85 verified environments across 7 domains, EnvFactory generates 2,575 SFT and RL trajectories. Despite using significantly fewer environments than prior work, which are often 5 times more, EnvFactory achieves superior training efficiency and downstream performance, improving Qwen3-series models by up to +15% on BFCLv3, +8.6% on MCP-Atlas, and +6% on conversational benchmarks including $τ^2$-Bench and VitaBench. By fully automating both environment construction and trajectory synthesis, EnvFactory provides a scalable, extensible, and robust foundation for Agentic RL.

Large language models (LLMs) deployed in real-world agentic applications must be capable of replanning and adapting when mid-task disruptions invalidate their prior decisions. Existing dynamic benchmarks primarily measure whether LLMs can detect temporal changes in a timely manner, leaving the complementary challenge of adaptive replanning under spatio-temporal dynamics largely unexplored. We introduce STT-Arena (Spatio-Temporal Tool-Use Arena), a benchmark of 227 high-quality interactive tasks spanning nine spatio-temporal conflict types and four solvability levels. Each task is grounded in a realistic, executable environment equipped with injected spatio-temporal triggers that can abruptly invalidate an ongoing plan, forcing the model to detect the state shift and construct a revised execution strategy. Extensive evaluation of frontier LLMs reveals that even the SOTA proprietary models, including Claude-4.6-Opus, achieves less than 40% overall accuracies, highlighting the fundamental difficulty of spatio-temporal dynamic reasoning. Systematic analysis of failure trajectories uncovers three recurring error modes of existing models: Stale-State Execution, Misdiagnosis of Dynamic Triggers, and Missing Post-Adaptation Verification. Guided by these findings, we propose an iterative trajectory refinement technique that eliminates these failure patterns from training data, and combine it with online RL to produce STT-Agent-4B which outperforms frontier LLMs on STT-Arena.

ADD in real-world scenarios has evolved from speech-only spoofing to more challenging component-level settings, where speech and environmental sounds may be independently manipulated. To tackle this, we propose EnvTriCascade, an Environment-Aware Tri-Stage Cascaded framework for the ESDD2 Challenge. First, a mix-consistency detector provides a binary prior to distinguish original recordings from manipulated mixtures, which calibrates the final decisions. Next, two complementary five-class detectors, leveraging SSLAM+XLS-R and EAT-large+XLS-R representations, extract robust multi-branch features integrated via a cross-branch attention-gated classifier. To enhance robustness against diverse mixing conditions, we incorporate RawBoost augmentation. Trained exclusively on the official CompSpoofV2 dataset, our system achieves a Macro-F1 score of 0.8266 on the test set, significantly outperforming the official baseline and ranking second in the challenge.

We present UbiSLAM, an innovative solution for real-time mapping and localization in dynamic indoor environments. By deploying a network of fixed RGB-D cameras strategically throughout the workspace, UbiSLAM addresses limitations commonly encountered in traditional SLAM systems, such as sensitivity to environmental changes and reliance on mobile unit sensors. This fixed-sensor approach enables real-time, comprehensive mapping, enhancing the localization accuracy and responsiveness of robots operating within the environment. The centralized map generated by UbiSLAM is continuously updated, providing robots with an accurate global view, which improves navigation, minimizes collisions, and facilitates smoother human-robot interactions in shared spaces. Beyond its advantages, UbiSLAM faces challenges, particularly in ensuring complete spatial coverage and managing blind spots, which necessitate data integration from the robots themselves. In this paper we discuss potential solutions, such as automatic calibration for optimal camera placement and orientation, along with enhanced communication protocols for real-time data sharing. The proposed model reduces the computational load on individual robotic units, allowing less complex robotic platforms to operate effectively while enhancing the robustness of the overall system.

Generalizable agents should adapt to diverse tasks and unseen environments beyond their training distribution. This position paper argues that such generalization requires environment scaling: expanding the distribution of executable rule-sets that agents interact with, rather than only increasing trajectories or tasks within fixed benchmarks. Current scaling practices largely focus on collecting more experience or broader task sets under fixed interaction rules, leaving agents brittle when underlying interfaces, dynamics, observations, or feedback signals change. The core challenge is therefore a world-level distribution shift: agents need systematic exposure to environments with meaningfully different executable rule-sets. To clarify this challenge, we propose a unified taxonomy that separates trajectory scaling, task scaling, and environment scaling by their primary deliverables and by what changes in the executable rule-set. Building on this taxonomy, we synthesize construction paradigms for scalable environments, contrasting programmatic generators that prioritize controllability and verifiability with generative world models that offer broader coverage and open-endedness. We further outline how environment scaling can be coupled with stateful learning mechanisms, emphasizing learned update rules for cross-environment adaptation. We conclude by discussing alternative perspectives and argue that scalable environments provide the essential substrate for measurable and controllable progress toward robust general agents.

Transfer Learning, a technique where a model/agent can use the knowledge/expertise that it gained from one task and exploit that to solve another closely-related task, is often used in tackling problems in deep learning. Through this project, we explore transfer learning in the purview of deep reinforcement learning. Specifically, we want to use transfer learning to achieve the fast lap times in OpenAI's Car racing environment by training the agent on one circuit, and racing it on other customized target environments by zero-shot transfer or by additional fine-tuning. In addition, we compare the performance of model-based and model-free approaches, and observe that model-based approaches dominate in performance and converge faster than model-free approaches in this environment. We observe that transfer learning in most setups not only boosts the performance on the target domain, but also shows high performance ability during learning.

Computer-use agents increasingly operate inside live personal workspaces, where their actions can modify files, applications, GUI state, credentials, and authenticated sessions. This creates a tension between safety and quality: agents need isolation and rollback to avoid damaging user state, but also need fast branching to support speculative execution and parallel search. Existing VMs, containers, and checkpoint/restore systems can isolate or recover workloads, but they do not provide low-latency versioning of a full interactive workspace. We present TClone, a forkable personal workspace system for computer-use agents. TClone enables a live GUI workspace to be snapshotted, forked into isolated branches, rolled back, and selectively committed or merged. Its design separates fast branch creation from durable checkpointing, using sibling containers, copy-on-write memory sharing, filesystem versioning, GUI-local execution, and asynchronous checkpointing. In our end-to-end agent-loop measurement, TClone reduces total task latency by 1.9x and 1.5x over KVM and CRIU. By making workspace versioning a first-class systems primitive, TClone supports safer and higher-quality agent execution over real personal computing environments.

Generating robot simulation environments remains a major bottleneck in simulation-based robot learning. Constructing a training-ready MuJoCo scene typically requires expertise in 3D asset modeling, MJCF specification, spatial layout, collision avoidance, and robot-model integration. We present SR-Platform, a production-deployed agentic system that converts free-form natural language descriptions into executable, physically valid MuJoCo environments. SR-Platform decomposes scene synthesis into four stages: an LLM-based orchestrator that converts user intent into a structured scene plan; an asset forge that retrieves cached assets or generates new 3D geometry through LLM-to-CadQuery synthesis; a layout architect that assigns object poses and verifies industrial constraints; and a bridge layer that assembles the final MJCF scene and merges the selected robot model. The system is deployed as a nine-service Docker stack with WebSocket progress streaming, MinIO-backed mesh storage, Qdrant-based semantic asset retrieval, Redis job state, and InfluxDB telemetry. Using 30 days of production telemetry covering 611 successful LLM calls, SR-Platform generates five-object scenes with a median end-to-end latency of approximately 50 s, while cache-accelerated scenes complete in approximately 30-40 s. The asset forge shows an 11.3% first-attempt retry rate with automatic recovery, and cached asset retrieval removes per-object LLM calls for previously generated object types. These results show that agentic scene synthesis can reduce the manual effort required to create diverse robot training environments, enabling users to produce executable MuJoCo scenes from plain English prompts in under one minute.

Kinematic monitoring plays a critical role in long-term rehabilitation for patients with spinal cord injury (SCI), where multi-view markerless motion capture methods have shown significant potential. However, owing to the reliance on calibration and the difficulty of achieving multi-view synchronization, their deployment in patient self-deployed environments remains challenging. In this work, we propose an agentic pipeline for self-synchronized multi-view joint angle monitoring in uncalibrated environments using two cameras without hardware triggers. The Multimodal large language models enable automatic video synchronization and agent-driven self-verification. State-of-the-art monocular 2D pose estimation models are employed to extract candidate poses, where an agent-based selection mechanism is then applied to automatically identify and track the target subject, thereby producing consistent 2D poses in the presence of multiple individuals and occlusions. Such 2D poses are optimized to estimate joint angles from uncalibrated multi-view pose sequences, ensuring interpretability through explicit geometric modeling. Validation against Vicon system demonstrated the strong performance, achieving an MAE of $5.97^\circ \pm 2.36^\circ$ and a Pearson correlation coefficient of $0.962 \pm 0.014$. The proposed method is expected to provide a practical, patient self-deployable system to perform daily kinematic monitoring in uncalibrated home environments.

Making calibrated online predictions is a central challenge in modern AI systems. Much of the existing literature focuses on fully adversarial environments where outcomes may be arbitrary, leading to conservative algorithms that can perform suboptimally in more benign settings, such as when outcomes are nearly stationary. This gap raises a natural question: can we design online prediction algorithms whose calibration error automatically adapts to the degree of non-stationarity in the environment, smoothly interpolating between i.i.d. and adversarial regimes? We answer this question in the affirmative and develop a suite of algorithms that achieve adaptive calibration guarantees under multiple calibration measures. Specifically, with $T$ being the number of rounds, $K$ being the unknown number of i.i.d. segments of the environment, and $C\in[0,T]$ being another unknown non-stationary measure defined as the minimal $\ell_1$ deviation of the mean outcomes, our algorithms attain $\widetilde{O}(\min\{\sqrt{T}+(TC)^{\frac{1}{3}}, \sqrt{KT}\})$ for $\ell_1$ calibration error and $\widetilde{O}(\min\{(1+C)^{\frac{1}{3}}, K\})$ for both $\ell_2$ and pseudo KL calibration error. These bounds match the optimal rates in the stationary case ($C=0$ and $K=1$) and recover known guarantees in the fully adversarial regime ($C, K=Ω(T)$). Our approach builds on and extends prior work [Hu et al., 2026, Luo et al., 2025], introducing an epoch-based scheduling together with a novel non-uniform partition of the prediction space that allocates finer resolution near the underlying ground truth.

Attributing model behavior to training data is an evolving research field. A common benchmark is data removal, which involves eliminating data instances with either low or high values, then assessing a model's performance trained on the modified dataset. Many existing studies leverage Shapley-based data values for this task. In this paper, we demonstrate that these data values are not optimally suited for pruning low-value data when only a limited amount of data remains. To address this limitation, we introduce the Constraint-Data-Value-Maximization (CDVM) approach, which effectively utilizes data attributions for pruning in low-data scenarios. By casting pruning as a constrained optimization that both maximizes total influence and penalizes excessive per-test contributions, CDVM delivers robust performance when only a small fraction of the data is retained. On the OpenDataVal benchmark, CDVM shows strong performance and competitive runtime.

Scientific discovery is fundamentally a resource-constrained process that requires navigating complex trade-offs between the quality and quantity of measurements due to physical and cost constraints. Measurements drive the scientific process by revealing novel phenomena to improve our understanding. Existing benchmarks for evaluating agents for scientific discovery focus on either static knowledge-based reasoning or unconstrained experimental design tasks, and do not capture the ability to make measurements and plan under constraints. To bridge this gap, we propose Measuring and Discovering Physics (MaD Physics), a benchmark to evaluate the ability of agents to make informative measurements and conclusions subject to constraints on the quality and quantity of measurements. The benchmark consists of three environments, each based on a distinct physical law. To mitigate contamination from existing knowledge, MaD Physics includes altered physical laws. In each trial, the agent makes measurements of the system until it exhausts an allotted budget and then the agent has to infer the underlying physical law to make predictions about the state of the system in the future. MaD Physics evaluates two fundamental capabilities of scientific agents: inferring models from data and planning under constraints. We also demonstrate how MaD Physics can be used to evaluate other capabilities such as multimodality and in-context learning. We benchmark agents on MaD Physics using four Gemini models (2.5 Flash Lite, 2.5 Flash, 2.5 Pro, and 3 Flash), identifying shortcomings in their structured exploration and data collection capabilities and highlighting directions to improve their scientific reasoning.

Nuclear magnetic resonance (NMR) spectroscopy provides an experimental readout of local chemical environments, but its use in molecular representation learning has been constrained by heterogeneous data and incomplete atom-level assignments. Here we construct complementary high-fidelity experimental and computational 13C NMR resources, which reveal a recurrent form of representational collapse: atoms that are equivalent in molecular topology can remain experimentally distinct in their real chemical environments, whereas explicit 3D descriptions are further limited by static conformations in dynamic regimes. To alleviate this bottleneck, we develop CLAIM (Contrastive Learning for Atom-to-molecule Inference of Molecular NMR), a framework that aligns efficient topological molecular inputs with atom-resolved NMR observables. Through hierarchical chemical priors and cross-level contrastive learning, CLAIM restores lost chemical resolution and markedly improves atom-level molecule-spectrum retrieval. CLAIM remains robust in flexible and tautomeric systems for 13C NMR prediction, improves stereoisomer discrimination without explicit 3D modelling, and transfers to broader molecular property tasks including ADMET prediction and fluorescence estimation. These results establish physically grounded spectral alignment as an effective strategy for alleviating chemical-environment collapse and for guiding experimentally grounded molecular representation learning.

Mining operations are of utmost importance to the economy of some nations. However, such operations result in land-use change, very high energy consumption, and negative impacts on the environment, including soil erosion and deforestation. The mining process can impact an area much larger than the mining site itself. Adding to the negative externalities linked to mining is the fact that, in addition to government-sanctioned legal mining operations, illegal mining is widespread, including in various countries of Africa. The ability to monitor remote mining site activities can be useful, e.g., for the detection of illegal artisanal mining activities and their environmental impacts. An important outcome of such monitoring could include a better understanding of the interrelationship between mine facility attributes (e.g., mining types, processing methods, commodities, etc.) and their impact on the natural environment. In this work, we present a data set that contains 150 Large Scale Mining (LSM) sites and 870km^2 annotated area of Artisanal Small-scale Mining (ASM) sites. The metadata includes nine eminent LSM sections and 27 mining site attributes for each LSM site. We also discuss the data set's possible contribution to the research community, social and environmental consequences, and researchers' responsibilities from an ethics perspective.

Scalable AI agents training relies on interactive environments that faithfully simulate the consequences of agent actions. Manually crafted environments are expensive to build, brittle to extend, and fundamentally limited in diversity. A promising direction is to replace manually crafted environments with LLM-simulated counterparts. However, this paradigm hinges on an unexamined core assumption: LLMs can accurately simulate environmental feedback. In practice, LLM-simulated environments suffer from hallucinations, logical inconsistencies, and silent state drift failures that corrupt agent reward signals and compound the construction costs that the paradigm was designed to eliminate. To address this gap, we propose EnvSimBench with four contributions: 1) We provide the first formal definition and operationalization of Environment Simulation Ability (EnvSim Ability) as a quantifiable research objective. 2) We construct EnvSimBench, a rigorous benchmark covering 400 samples across 167 diverse environments, equipped with verifiable labels and fine-grained difficulty stratification along three axes. 3) Systematic evaluations reveal that all state-of-the-art language models suffer from a universal state change cliff: they achieve near-perfect accuracy on tasks when the environment state remains invariant, yet fail catastrophically when multiple states need simultaneous updates. This finding exposes EnvSim Ability as a critical yet largely unaddressed capability gap. 4) We design a constraint-driven simulation pipeline that substantially reduces hallucination, boosts environment synthesis yield by 6.8%, and cuts costs by over 90%. Overall, EnvSimBench serves as both a diagnostic framework and a practical optimization path for reliable LLM-based environment simulation, establishing a foundation for scalable agent training. Code and data are available at https://github.com/cookieApril/EnvSimBench

In model-based learning, the agent learns behaviors by simulating trajectories based on world model predictions. Standard world models typically learn a stationary transition function that maps states and actions to next states, when an action and an outcome frequently co-occur in training data, the model tends to internalize this correlation as a general causal rule while ignoring action preconditions. In interactive environments, however, agent actions can reshape the future affordance space. At each timestep, an action may becomes executable only after its prerequisites are met, or non-executable when they are destroyed. We term such events structure-changing events (SC events). As a result, a conventional world model often fails to determine whether a given action is executable in the current state, especially in multi-step predictions. Each imagined step is conditioned on an incorrect affordance state, and therefore the prediction error compounds over the rollout horizon. In this paper, we propose AGWM (Affordance-Grounded World Model), which learns an abstract affordance structure represented as a DAG of prerequisite dependencies to explicitly track the dynamic executability of actions. Experiments on game-based simulated environments demonstrate the effectiveness of our method by achieving lower multi-step prediction error, better generalization to novel configurations, and improved interpretability.

This paper presents a Vehicle-to-Everything (V2X) communication framework that enables decentralized cooperation among social robots operating in complex urban traffic environments. Building on ETSI Cooperative Awareness and Maneuver Coordination services, the framework introduces two robot-centric facility-layer services: the Robot Awareness Service (RAS) and the Robot Maneuver Coordination Service (RMCS), realized through the Robot Awareness Message (RAM) and the Robot Maneuver Coordination Message (RMCM), respectively. RAS enables role-aware, task-oriented robot awareness while integrating externally detected Vulnerable Road Users (VRUs), including non-V2X pedestrians, into cooperative awareness. RMCS supports event-driven, low-latency coordination of robot maneuvers under explicitly established roles, without centralized infrastructure or prior pairing. A real-world proof of concept demonstrates deterministic multi-robot coordination between a humanoid robot and a quadrupedal robot assisting a pedestrian during a road-crossing scenario, governed by a formally specified finite-state coordination model. Complementary simulations evaluate robot-mediated VRU clustering in mixed V2X environments, showing that RAS-based clustering integrates non-V2X VRUs in safety-critical areas while reducing redundant transmissions from V2X-enabled VRUs, thereby lowering channel load. Together, the proposed services provide a scalable and standards-aligned foundation for integrating cooperative robots into future Connected, Cooperative, and Automated Mobility ecosystems.

This paper describes a submission to the Environment-Aware Speech and Sound Deepfake Detection Challenge (ESDD2) 2026, which addresses component-level deepfake detection using the CompSpoofV2 dataset, where speech and environmental sounds may be independently manipulated. To address this challenge, a dual-branch deepfake detection framework is proposed to jointly model speech and environmental contextual representations from input audio. Two pretrained models, XLS-R for speech and BEATs for environmental sound, are used to extract complementary contextual representations. A Matching Head is introduced to model representation differences through statistical normalization and representation interaction, enabling estimation of the original class. In parallel, multi-head cross-attention enables effective information exchange between speech and environmental components. The refined representations are processed with residual connections and layer normalization, and passed to an AASIST classifier to predict speech-based and environment-based spoofing probabilities. The model outputs original, speech, and environment predictions. On the test set, the proposed system achieves an F1-score of 70.20% and an environmental EER of 16.54%, outperforming the baseline system.

Long-term autonomy requires robust navigation in environments subject to dynamic and static changes, as well as adverse weather conditions. Teach-and-Repeat (T&R) navigation offers a reliable and cost-effective solution by avoiding the need for consistent global mapping; however, existing T&R systems lack a systematic solution to tackle various environmental variations such as weather degradation, ephemeral dynamics, and structural changes. This work proposes LTR$^2$, the first cross-modal, cross-platform LiDAR-Teach-and-Radar-Repeat system that systematically addresses these challenges. LTR$^2$ leverages LiDAR during the teaching phase to capture precise structural information under normal conditions and utilizes 4D millimeter-wave radar during the repeating phase for robust operation under environmental degradations. To align sparse and noisy forward-looking 4D radar with dense and accurate omnidirectional 3D LiDAR data, we introduce a Cross-Modal Registration (CMR) network that jointly exploits Doppler-based motion priors and the physical laws governing LiDAR intensity and radar power density. Furthermore, we propose an adaptive fine-tuning strategy that incrementally updates the CMR network based on localization errors, enabling long-term adaptability to static environmental changes without ground-truth labels. We demonstrate that the proposed CMR network achieves state-of-the-art cross-modal registration performance on the open-access dataset. Then we validate LTR$^2$ across three robot platforms over a large-scale, long-term deployment (40+ km over 6 months), including challenging conditions such as nighttime smoke. Experimental results and ablation studies demonstrate centimeter-level accuracy and strong robustness against diverse environmental disturbances, significantly outperforming existing approaches.

This paper addresses the problem of mobile grasping in dynamic, unknown environments where a robot must operate under a limited field-of-view. The fundamental challenge is the inherent trade-off between seeing'' around to reduce environmental uncertainty and moving'' the body to achieve task progress in a high-dimensional configuration space, subject to visibility constraints. Previous approaches often assume known or static environments and decouple these objectives, failing to guarantee safety when unobserved dynamic obstacles intersect the robot's path during manipulation. In this paper, we propose a unified mobile grasping system comprising two core components: (1) an iterative low-level whole-body planner coupled with velocity-aware active perception to navigate dynamic environments safely; and (2) a hierarchical high-level planner based on behavior trees that adaptively generates subgoals to guide the robot through exploration and runtime failures. We provide experimental results across 400 randomized simulation scenarios and real-world deployment on a Fetch mobile manipulator. Results show that our system achieves a success rate of 68.8% and 58.0% in unknown static and dynamic environments, respectively, significantly boosting success rates by 22.8% and 18.0% over the \nam approach in both unknown static and dynamic environments, with improved collision safety.

Large Language Model (LLM) usage in recent years has become increasingly widespread in the Artificial Intelligence in Education (AIED) community. While LLMs offer unique avenues for learners and educators, using LLMs comes with computational and environmental costs. These costs are mostly hidden due to a lack of standardised procedures to measure and report these impacts. To address this gap, we first conducted a literature review of all papers published as part of the AIED 2025 conference proceedings, determining if and how computational or environmental costs of LLMs are reported. Most projects use LLMs, but few report computational resources used and almost none discuss environmental impacts of LLMs as an ethical concern. To address this lack of standardised reporting practices, we propose an open-source method for systematically measuring and reporting the computational expense of LLMs and environmental impact of running Machine Learning (ML) AIED systems. We provide software solutions to measure the carbon footprint for both local and cloud based hardware. We also provide an easy-to-use formula to calculate the computational expense of frontier LLMs even when the exact number of parameters is not known. Overall, we hope to motivate colleagues to use our method to strive for more transparent reporting of hidden costs of using LLMs in the AIED community.

Unsupervised Environment Design (UED) offers a promising paradigm for improving reinforcement learning generalization by adaptively shaping training environments, but it requires reliable environment evaluation to remain effective. However, existing UED methods evaluate environments using indirect proxy signals such as regret, value-based errors, or Monte Carlo, which suffer from bias, high variance, or substantial computational overhead and fail to reflect agent realized learning progress. To address these limitations, we propose Parameter Change Environment Design (PACE), which evaluates an environment through the policy parameter change induced by training on that environment, directly grounding environment selection in realized learning progress. Specifically, PACE assigns environment value using a first-order approximation of the policy optimization objective, where the improvement induced by an environment is proportional to the squared L2 norm of the corresponding parameter update, enabling low-variance and computation-efficient evaluation without additional rollouts. Experiments on MiniGrid and Craftax show that PACE consistently outperforms established UED baselines, achieving higher IQM and smaller Optimality Gap on OOD evaluations, including an IQM of 96.4% and an Optimality Gap of 17.2% on MiniGrid.

We consider learning from labeled data collected across multiple environments, where the data distribution may vary across these environments. This problem is commonly approached from a causal perspective, seeking invariant representations that retain causal factors while discarding spurious ones. However, this framework assumes that the environment has no direct effect on the target. In contrast, we consider settings in which this assumption fails, but still aim to learn representations that support robust prediction on average across previously unseen environments. To this end, we study representations learned by explicitly modeling variation across environments and then marginalizing that variation out. We analyze the resulting representations and characterize when they are preferable to those learned by causal invariant-representation methods. We propose a concrete method based on generalized random-intercept models, a class of predictors in which such marginalization is possible, and study their generalization properties. Empirically, we show that these models outperform invariant-learning methods across a range of challenging settings.

Heterogeneous multi-robot systems feature significant adaptability for complex environments. However, effective collaboration that fully exploits the robots' potential remains a core challenge. This paper proposes a decentralized collaborative framework for heterogeneous multi-robot systems to autonomously explore indoor and outdoor 3D environments. First, a basic perception map that integrates terrain and observation metrics is designed. Improved supervoxel segmentation is developed to simplify the map structure and form a high-level representation that supports lightweight communication. Second, the traversal and observation capabilities of heterogeneous robots are modeled to evaluate the requirements of task views derived from incomplete supervoxels. These task views are grouped by requirements and clustered to streamline assignment. Subsequently, the view-cluster assignment is formulated as a heterogeneous multi-depot multi-traveling salesman problem (HMDMTSP) that incorporates constraints between view-cluster requirements and robot capabilities. An improved genetic algorithm is developed to efficiently solve this problem while ensuring global consistency. Based on the assignments, redundant views within clusters are eliminated to refine exploration routes. Finally, conflicts between robots' motion paths are resolved. Simulations and field experiments in cluttered indoor and outdoor environments demonstrate that our approach effectively coordinates exploration tasks among heterogeneous robots, achieving superior exploration efficiency and communication savings compared to state-of-the-art approaches.

Videos captured in low-light and underwater conditions often suffer from distortions such as noise, low contrast, color imbalance, and blur. These issues not only limit visibility but also degrade automatic tasks like detection. Post-processing is typically required but can be time-consuming. AI-based tools for video enhancement also demand significantly more computational resources compared to image-based methods. This paper introduces a novel framework, Visual Mamba, designed to reduce memory usage and computational time by leveraging the Visual State Space (VSS) model. The framework consists of two modules: (i) a feature alignment module, where spatio-temporal displacement between input frames is registered in the feature space, and (ii) an enhancement module, where noise removal and brightness adjustment are performed using a UNet-like architecture, with all convolutional layers replaced by VSS blocks. Experimental results show that the Visual Mamba technique outperforms Transformer and convolution-based models in both low-light and underwater video enhancement tasks. Code is available on line at https://github.com/russellllaputa/BVI-Mamba.

Low-cost air quality sensors (LCS) provide a practical alternative to expensive regulatory-grade instruments, making dense urban monitoring networks possible. Yet their adoption is limited by calibration challenges, including sensor drift, environmental cross-sensitivity, and variability in performance from device to device. This work presents a deep learning framework for calibrating LCS measurements of PM$_{2.5}$, PM$_{10}$, and NO$_2$ using a Long Short-Term Memory (LSTM) network, trained on co-located reference data from the OxAria network in Oxford, UK. Unlike the Random Forest (RF) baseline, which treats each observation independently, the proposed approach captures temporal dependencies and delayed environmental effects through sequence-based learning, achieving higher $R^2$ values across training, validation, and test sets for all three pollutants. A feature set is constructed combining time-lagged parameters, harmonic encodings, and interaction terms to improve generalization on unseen temporal windows. Validation of unseen calibrated values against the Equivalence Spreadsheet Tool 3.1 demonstrates regulatory compliance with expanded uncertainties of 22.11% for NO$_2$, 12.42% for PM$_{10}$, and 9.1% for PM$_{2.5}$.

Vision-language-action models (VLAs) have been extensively used in robotics applications, achieving great success in various manipulation problems. More recently, VLAs have been used in long-horizon tasks and evaluated on benchmarks, such as BEHAVIOR1K (B1K), for solving complex household chores. The common metric for measuring progress in such benchmarks is success rate or partial score based on satisfaction of progress-agnostic criteria, meaning only the final states of the objects are considered, regardless of the events that lead to such states. In this paper, we argue that using such evaluation protocols say little about safety aspects of operation and can potentially exaggerate reported performance, undermining core challenges for future real-world deployment. To this end, we conduct a thorough analysis of state-of-the-art models on the B1K Challenge and evaluate policies in terms of robustness via reproducibility and consistency of performance, safety aspects of policies operations, task awareness, and key elements leading to the incompletion of tasks. We then propose evaluation protocols to capture safety violations to better measure the true performance of the policies in more complex and interactive scenarios. At the end, we discuss the limitations of the existing VLAs and motivate future research.

Motivated by loss of control risks from misaligned AI systems, we develop and apply methods for measuring language models' propensity for unsanctioned behaviour. We contribute three methodological improvements: analysing effects of changes to environmental factors on behaviour, quantifying effect sizes via Bayesian generalised linear models, and taking explicit measures against circular analysis. We apply the methodology to measure the effects of 12 environmental factors (6 strategic in nature, 6 non-strategic) and thus the extent to which behaviour is explained by strategic aspects of the environment, a question relevant to risks from misalignment. Across 23 language models and 11 evaluation environments, we find approximately equal contributions from strategic and non-strategic factors for explaining behaviour, do not find strategic factors becoming more or less influential as capabilities improve, and find some evidence for a trend for increased sensitivity to goal conflicts. Finally, we highlight a key direction for future propensity research: the development of theoretical frameworks and cognitive models of AI decision-making into empirically testable forms.

Reinforcement learning (RL) offers a compelling data-driven paradigm for synthesizing controllers for complex systems when accurate physical models are unavailable; however, most existing control-oriented RL methods assume stationarity and, therefore, struggle in real-world non-stationary deployments where system dynamics and operating conditions can change unexpectedly. Moreover, RL controllers acting in physical environments must satisfy safety constraints throughout their learning and execution phases, rendering transient violations during adaptation unacceptable. Although continual RL and safe RL have each addressed non-stationarity and safety, respectively, their intersection remains comparatively unexplored, motivating the study of safe continual RL algorithms that can adapt over the system's lifetime while preserving safety. In this work, we systematically investigate safe continual reinforcement learning by introducing three benchmark environments that capture safety-critical continual adaptation and by evaluating representative approaches from safe RL, continual RL, and their combinations. Our empirical results reveal a fundamental tension between maintaining safety constraints and preventing catastrophic forgetting under non-stationary dynamics, with existing methods generally failing to achieve both objectives simultaneously. To address this shortcoming, we examine regularization-based strategies that partially mitigate this trade-off and characterize their benefits and limitations. Finally, we outline key open challenges and research directions toward developing safe, resilient learning-based controllers capable of sustained autonomous operation in changing environments.

Vision-language models (VLMs) have shown strong perception and reasoning abilities for instruction-following embodied agents. However, despite these abilities and their generalization performance, they still face limitations in environmental understanding, often failing on interactions or relying on environment metadata during execution. To address this challenge, we propose a novel framework named Environmental Understanding Embodied Agent (EUEA), which fine-tunes four core skills: 1) object perception for identifying relevant objects, 2) task planning for generating interaction subgoals, 3) action understanding for judging success likelihood, and 4) goal recognition for determining goal completion. By fine-tuning VLMs with EUEA skills, our framework enables more reliable task execution for instruction-following. We further introduce a recovery step that leverages these core skills and a group relative policy optimization (GRPO) stage that refines inconsistent skill predictions. The recovery step samples alternative actions to correct failure cases, and the GRPO stage refines inconsistent skill predictions. Across ALFRED tasks, our VLM significantly outperforms a behavior-cloning baseline, achieving an 8.86% improvement in average success rate. The recovery and GRPO stages provide an additional 3.03% gain, further enhancing overall performance. Finally, our skill-level analyses reveal key limitations in the environmental understanding of closed- and open-source VLMs and identify the capabilities necessary for effective agent-environment interaction.

Tool-integrated agents are deployed on the premise that external tools ground their outputs in reality. Yet this very reliance creates a critical attack surface. Current evaluations benchmark capability in benign settings, asking "can the agent use tools correctly" but never "what if the tools lie". We identify this Trust Gap: agents are evaluated for performance, not for skepticism. We formalize this vulnerability as Adversarial Environmental Injection (AEI), a threat model where adversaries compromise tool outputs to deceive agents. AEI constitutes environmental deception: constructing a "fake world" of poisoned search results and fabricated reference networks around unsuspecting agents. We operationalize this via POTEMKIN, a Model Context Protocol (MCP)-compatible harness for plug-and-play robustness testing. We identify two orthogonal attack surfaces: The Illusion (breadth attacks) poison retrieval to induce epistemic drift toward false beliefs, while The Maze (depth attacks) exploit structural traps to cause policy collapse into infinite loops. Across 11,000+ runs on five frontier agents, we find a stark robustness gap: resistance to one attack often increases vulnerability to the other, demonstrating that epistemic and navigational robustness are distinct capabilities.

Earth observation foundation models encode land surface information into dense embedding vectors, yet the geometric structure of these representations and its implications for downstream reasoning remain underexplored. We characterize the manifold geometry of Google AlphaEarth's 64-dimensional embeddings across 12.1 million Continental United States samples (2017--2023) and develop an agentic system that leverages this geometric understanding for environmental reasoning. The manifold is non-Euclidean: effective dimensionality is 13.3 (participation ratio) from 64 raw dimensions, with local intrinsic dimensionality of approximately 10. Tangent spaces rotate substantially, with 84% of locations exceeding 60\textdegree{} and local-global alignment (mean$|\cosθ| = 0.17$) approaching the random baseline of 0.125. Supervised linear probes indicate that concept directions rotate across the manifold, and compositional vector arithmetic using both PCA-derived and probe-derived directions yields poor precision. Retrieval instead produces physically coherent results, with local geometry predicting retrieval coherence ($R^2 = 0.32$). Building on this characterization, we introduce an agentic system with nine specialized tools that decomposes environmental queries into reasoning chains over a FAISS-indexed embedding database. A five-condition ablation (120 queries, three complexity tiers) shows that embedding retrieval dominates response quality ($μ= 3.79 \pm 0.90$ vs.\ $3.03 \pm 0.77$ parametric-only; scale 1--5), with peak performance on multi-step comparisons ($μ= 4.28 \pm 0.43$). A cross-model benchmark show that geometric tools reduce Sonnet 4.5's score by 0.12 points but improve Opus 4.6's by 0.07, with Opus achieving higher geometric grounding (3.38 vs.\ 2.64), suggesting that the value of geometric characterization scales with the reasoning capability of the consuming model.

Vision-Language-Action (VLA) models drive next-generation autonomous systems, but training them requires scalable, high-quality annotations from complex environments. Current cloud pipelines rely on generic vision-language models (VLMs) that lack geometric reasoning and domain semantics due to their 2D image-text pretraining. To address this mismatch, we propose XEmbodied, a cloud-side foundation model that endows VLMs with intrinsic 3D geometric awareness and interaction with physical cues (e.g., occupancy grids, 3D boxes). Instead of treating geometry as auxiliary input, XEmbodied integrates geometric representations via a structured 3D Adapter and distills physical signals into context tokens using an Efficient Image-Embodied Adapter. Through progressive domain curriculum and reinforcement learning post-training, XEmbodied preserves general capabilities while demonstrating robust performance across 18 public benchmarks. It significantly improves spatial reasoning, traffic semantics, embodied affordance, and out-of-distribution generalization for large-scale scenario mining and embodied VQA.

As reinforcement learning continues to scale the training of large language model-based agents, reliably verifying agent behaviors in complex environments has become increasingly challenging. Existing approaches rely on rule-based verifiers or LLM-as-a-Judge models, which struggle to generalize beyond narrow domains. Agent-as-a-Judge addresses this limitation by actively interacting with environments and tools to acquire verifiable evidence, yet its capabilities remain underexplored. We introduce a benchmark AJ-Bench to systematically evaluate Agent-as-a-Judge across three domains-search, data systems, and graphical user interfaces-comprising 155 tasks and 516 annotated trajectories. The benchmark comprehensively assesses judge agents' abilities in information acquisition, state verification, and process verification. Experiments demonstrate consistent performance gains over LLM-as-a-Judge baselines, while also revealing substantial open challenges in agent-based verification. Our data and code are available at https://aj-bench.github.io/.

Reinforcement learning (RL) has become a prevalent paradigm for training tool calling agents, which typically requires online interactive environments. Existing approaches either rely on training data with ground truth annotations or require advanced proprietary language models (LMs) to synthesize environments that keep fixed once created. In this work, we propose TRUSTEE, a cost-friendly method for training tool calling agents with dynamic environments fully simulated by free open-source LMs that can be as small as 8B, including task generation, user simulation, tool simulation and trajectory evaluation, paired with an adaptive curriculum learning mechanism that controls task difficulty during training. Our empirical results show that TRUSTEE outperforms baselines which require extra external resources in most cases. These confirm that, with a sufficiently sophisticated design, even simulated environments with a local 8B LM as the backbone could set a strong baseline for tool learning. We hope our proposed paradigm could democratize tool learning and inspire future research on environment scaling with limited resources.