Environment

Frontier AI models are rapidly gaining the ability to exploit vulnerabilities in complex pieces of software. The risk is not theoretical, as evidenced by recent sandbox escapes performed by frontier models at OpenAI and Anthropic. Discussions of how to sandbox inference stack components often focus on components other than the inference engine itself (e.g., network proxies or code execution environments). However, the inference engine is an attractive target for a misaligned model. For example, if a model can trigger exploits in that engine merely by generating specially-crafted output tokens, the model can initiate a multi-step, to-the-bare-metal exploit chain in the engine, without relying on vulnerabilities in other components of the inference stack, and without assistance from externally-provided, maliciously-crafted input tokens. In this paper, we show that a misaligned model can perform inference engine fingerprinting to determine the specific engine (e.g., vLLM, SGLang) which executes the model. Once the engine has been fingerprinted, the model can leverage engine-specific exploits to take control of the engine using only carefully-selected output tokens. We provide concrete examples of model fingerprints in five popular engines, and demonstrate how realistic agentic harnesses allow a model to leverage those fingerprints to identify the local engine. We also describe a proof-of-concept, to-the-bare-metal exploit chain that originates from a fingerprinted (and subsequently compromised) inference engine. We conclude by discussing several ways that inference engines could be changed to make fingerprinting attacks more difficult.

Iris presentation attack detection (PAD) is security-critical when a subsystem that appears reliable during development encounters presentation attack instruments (PAIs) or acquisition conditions absent from validation data. We benchmark three compact scratch-trained computer-vision models, each with at most approximately 0.26 million trainable parameters, on the Notre Dame subset of LivDet-Iris 2017 under PAI-driven domain shift and environmental degradation. All models are trained without external pretraining or data augmentation and evaluated over five seeds. A validation-selected threshold is transferred unchanged to the known-attack, unknown-attack, corrupted, and pooled test partitions. From known to unknown attack presentations, Attack Presentation Classification Error Rate (APCER) increases by 17.11-30.47 percentage points and Detection Equal Error Rate (D-EER) increases by 7.38-12.73 percentage points. At the validation-selected threshold, ZACH-ViT obtains the lowest unknown-attack APCER (47.69 +/- 4.84%) and D-EER (38.87 +/- 0.93%), while Compact-TransMIL obtains the lowest Bona Fide Presentation Classification Error Rate (BPCER). ZACH-ViT also gives the lowest unknown-attack BPCER at an APCER limit of 10% (81.29 +/- 1.95%). The high absolute errors show that the comparative advantage of the best compact model does not constitute deployment readiness under unknown PAIs.

Scientific code repositories encode decades of human knowledge in executable models, methods, and tools. Yet fragmented toolchains, implicit domain conventions, and specialized correctness criteria make this knowledge difficult to convert into reliable learning experience-a challenge we call the scientific experience bottleneck. We introduce ScienceIDE, infrastructure for turning the world's scientific code into programmable environments for scientific agents. Guided by expert-defined scientific cases and acceptance criteria, agents transform repositories into executable environments that support task generation, execution, and scientific verification. These environments provide a shared foundation for supervised fine-tuning, reinforcement learning, and evaluation. Using verified interaction trajectories, we train PhAI-IDE-72B, PhAI-IDE-9B, and PhAI-IDE-4B. The model family shows gains in held-out scientific-code repair and across selected general-purpose benchmarks in code, reasoning, and knowledge, providing evidence of positive transfer from scientific experience to broader capabilities. ScienceIDE lays the foundation for an integrated workspace for agent learning and scientific practice, making humanity's scientific software a shared substrate for developing scientific intelligence. Code: https://github.com/aitofound/ScienceIDE

In multi-agent environments, coordinating agents to prevent interference and ensure robust individual performance is a critical challenge. Previous research on social laws for multi-agent systems has primarily focused on deterministic, goal-based settings. This paper extends the concept of social laws to stochastic, reward-based environments, proposing a formalism for defining and verifying their robustness under various conditions. We introduce the notion of $α$-robustness, a measure of the guaranteed utility each agent retains while pursuing its optimal single agent policy, assuming all agents obey the social law. We then present an approach for robustness verification of social laws in stochastic settings, based on a reduction to solving a series of Markov decision processes. Empirical evaluations on toy environments illustrate the potential of our framework.

Humanoid robots can step over, squeeze past, and duck under obstacles, but learning to select and coordinate these behaviors from onboard perception remains challenging. Many existing approaches rely on task-specific reinforcement-learning objectives or curated motion libraries, making broad behavioral coverage costly. We present PASSAGE, a perception-conditioned planner--tracker framework for humanoid traversal. Using virtual reality and inertial motion capture, we collect 100 h of scene-aligned human motion across 1,500 cluttered scenes. A conditional flow-matching planner generates short-horizon references from motion history, a local destination, and a robot-centric multi-layer elevation map, while a perceptive whole-body tracker executes them at 50 Hz with geometric feedback. Real-time chunking promotes inter-chunk consistency, and planner-side RL post-training under the frozen tracker further improves closed-loop performance. Without skill annotations or obstacle-specific policies, one planner--tracker pair selects and composes traversal behaviors across unseen geometries. In simulation, component ablations quantify the contribution of each stage. Across three independent training seeds, scaling captured data from 6 to 100 h increases mean contact-free success from 48.1% to 68.9% on held-out scenes, while the final model with validated scene augmentation reaches 70.3%. The fully onboard system integrates egocentric 3D LiDAR perception, online occupancy mapping, 6.25 Hz planning, and 50 Hz control on a Jetson AGX Orin; tests across 50 unseen physical layouts demonstrate traversal without prebuilt maps or offboard computation.

Robots that leave structured, static environments must plan motions that are kinodynamically feasible and safe among moving obstacles. However, there are no dedicated benchmark frameworks that combine both aspects. To overcome this, we present DynoFluxBench, a framework to compare kinodynamic planners in known, dynamic environments with unbounded arrival time. To demonstrate its utility and establish strong baselines, we develop three dedicated planners, named ST-Db-RRT, ST-GBRRT, and KIST, that fuse kinodynamic and space-time methods, covering different kinodynamic search paradigms: ST-Db-RRT expands with randomly selected discontinuity-bounded motion primitives using trajectory optimization, whereas KIST and ST-GBRRT maintain a kinodynamically feasible tree with different heuristic guidance. We analyze the probabilistic completeness guarantees of those new planners in dynamic environments. Finally, we evaluate ST-Db-RRT, ST-GBRRT, and KIST using DynoFluxBench, showing that ST-Db-RRT reaches a first solution up to 32 times faster, while KIST and ST-GBRRT remain valuable where trajectory optimization is fragile. Videos and further analysis can be found at https://dynofluxbench.github.io/dynofluxbench/.

We present SAiFE_gym, a Python module that provides a collection of simulation environments for studying trading problems in Constant Product Markets (CPMs) with Concentrated Liquidity (CL). These markets give Liquidity Providers (LPs) granular control over how their capital is allocated and enable them to adjust their range of liquidity provision dynamically based on market conditions, which in turn, dictates how they earn fees. We decompose the microstructure of CPMs with CL in interactive components that allow researchers and practitioners to capture various economic settings. We employ a vectorized approach to optimize our environments, making them scalable for high dimensional Reinforcement Learning (RL) workflows that best describe sequential decision problems. We demonstrate the benefits of our environments by evaluating the performance of RL agents in CPMs with CL under uncertainty in market parameters.

Quantifying organizational environmental action from publicly available web content remains a challenging environmental data science problem because relevant information can be dispersed across multiple webpages and is primarily communicated through unstructured text. We present a scalable computational framework for transforming organizational web content into structured measures of environmental action and demonstrate the approach using Jewish congregations in the United States. We constructed a national database of 4,964 congregations by integrating multiple geospatial, knowledge-base, directory, and manually reviewed sources. Of these, 2,657 had active websites that were successfully crawled, producing a corpus of 154,454 webpages. We compared three approaches for detecting environmental actions: keyword retrieval followed by large language model (LLM) classification, semantic vector retrieval followed by LLM classification, and direct LLM classification classification without preliminary retrieval. Agreement with an expert human reviewer was lowest for keyword retrieval ($κ$ = 0.26), higher for semantic vector retrieval ($κ$ = 0.42), and similar for direct LLM classification ($κ$ = 0.40). Although semantic retrieval achieved the highest agreement, its retrieval recall was 0.87, indicating loss of relevant content before classification. Applied to the complete corpus, direct LLM classification identified at least one environmental action at 1,398 congregations (53%), providing greater coverage than either retrieval-based approach. These results demonstrate that preliminary retrieval can reduce computational cost but may exclude relevant information before it reaches the classifier. The framework provides a reproducible approach for extracting organization-level environmental information from unstructured web content that can be adapted to other institutions.

Large brains are metabolically costly, and associations with changing environments do not imply they evolved there, as the Cognitive Buffer Hypothesis (CBH) would suggest. They may instead evolve in stable conditions and later facilitate colonization of changing environments. Using neuro-evolution in an artificial seasonal foraging task, we compared agents evolving exclusively in changing environments to agents first evolved in static environments before transitioning. Results show that larger neural networks in dynamic environments arise mainly from prior static evolution, achieving superior performance under unpredictable changes. Our results challenge strict CBH predictions, provide agent-based (computational) support for a colonization-based account and highlight the role of evolutionary history in brain size evolution.

Environmental, Social, and Governance (ESG) reporting is critical for corporate accountability, with Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) offering strong potential to automate KPI extraction. However, open-source LLM performance in domain-specific ESG tasks remains insufficiently understood. This paper evaluates open-source LLMs in ESG contexts using a structured framework and evaluation resource based on 498 real-world ESG reports from EU-listed companies (2010-2024). We evaluate seven open-source models (2B to 30B parameters) -- glm-4.7-flash, nemotron-3-nano:4b, qwen3:4b-instruct, gemma3:4b, gemma4:e4b, gemma4:e2b, and ministral-3:8b -- using 100 persona-based synthetic QA pairs covering ESG information needs. System performance is assessed via RAGAS metrics, including contextual recall, precision, relevance, faithfulness, answer relevancy, and factual correctness. Results show notable performance variations across architectures. Retrieval performance is strong across models (context recall around 0.58-0.61, context precision around 0.78-0.81, context relevance 0.965-0.985). Generation diverges most on faithfulness (0.607-0.822) and least on answer relevancy (0.760-0.881): glm-4.7-flash leads in faithfulness (0.822), qwen3 in factual correctness (0.449), and ministral-3 in answer relevancy (0.881). Low overall factual correctness (0.387-0.449) highlights the need for domain-specific fine-tuning. This work provides data-driven guidance for deploying open-source models in ESG reporting.

This paper presents an online coverage path planning algorithm for unknown environments. During navigation, the initially unknown search area is progressively decomposed into disconnected subareas as new obstacle information is acquired and coverage proceeds. These subareas are organized in an incrementally constructed decomposition tree that preserves their hierarchical parent-child relationships. Based on this tree, a global coverage tour is maintained and updated online by prioritizing newly generated child subareas according to their exploration states and distances from the robot. A local planner then generates coverage motions within each selected subarea, allowing the robot to adapt its trajectory as the environment is gradually revealed. Its performance is evaluated via high-fidelity simulations in complex scenarios. The results show improved coverage efficiency in terms of path length and overlap ratio in comparison to three baseline algorithms.

The rapid diffusion of generative artificial intelligence raises privacy, latency, and performance concerns that motivate a shift toward "local-first" AI, where inferences are performed on the user's device instead of on remote cloud servers. This paradigm also places a significant computational load on battery-powered smartphones, potentially shortening battery life and increasing the overall replacement rate of mobile devices. This paper presents a systematic study of the energy consumption, performance, and accuracy of on-device large language model (LLM) inference. We evaluate 18 models from different model families, sizes, and quantization levels, on two modern smartphones and on a server, using the respective state-of-the-art for such deployments. We measure the energy per generated token, inter-token latency, model accuracy, and battery-cycle consumption. Our results show that (i) on-device inference is on average 3 times less energy-efficient than batched server inference; (ii) the relationship between quantization bit-width and energy per token is non-monotonic, with energy sweet spots on both tested smartphones; (iii) eight out of 18 model configurations lie on the Pareto front of accuracy and energy-efficiency, allowing practitioners to build battery-aware model routers; and (iv) realistic modeling assumptions do not allow local inference to be less environmentally impacting per token than batched server inference, with 88--90% of that impact attributable to device embodied carbon rather than electricity consumption. These findings challenge the premise that local AI is more sustainable than cloud inference, and motivate the need for context-aware and life-cycle-aware model selection when deploying edge AI on battery-powered mobile platforms.

Environmental controversies in global supply chains pose significant risks for global buyers. This study examines whether overseas suppliers' exposure to buyers' artificial intelligence (AI)-enabled environmental governance reduces supplier environmental controversies. Drawing on organizational information processing theory and signaling theory, we investigate how suppliers' exposure to AI-enabled governance influences their environmental controversies and the institutional contingencies under which this effect varies. Using text analysis to measure buyer AI-enabled environmental governance, we analyze panel data on 2,505 suppliers of U.S.-listed firms across 41 countries from 2020 to 2024 with multidimensional fixed-effects models. We find that suppliers' exposure to buyer AI-enabled environmental governance is negatively associated with supplier environmental controversies in the following year. This negative relationship is stronger in supplier countries with higher AI readiness and regulatory quality. The study contributes to research on AI-enabled sustainability governance and sustainable supply chain risk management.

Before an LLM agent tackles tasks in a new environment, it can inspect available corpora and tools and construct reusable resources such as indices, scripts, or procedural guidance. Most automated adaptation methods, however, rely on task examples, trajectories, or evaluation feedback to decide what to build. Existing task-agnostic approaches avoid this supervision but commit in advance to a preparation strategy for a particular type of environment. We study a more open-ended setting: can an agent study an unfamiliar environment without a syllabus, i.e. before test time and without knowledge of the downstream task distribution, and choose how to prepare it? We formalize task-agnostic environment preprocessing, in which a studying system explores an environment under a budget and produces artifacts for a frozen solver. We compare unaided and archive-equipped meta-agents with fixed synthetic-practice and corpus-processing methods across six heterogeneous benchmarks. A meta-agent variant achieves the highest Avg@3 reward on five benchmarks, while fixed corpus processing remains best on the largest corpus benchmark. Larger study budgets do not reliably improve downstream reward. Nevertheless, studied artifacts reduce the test-time sampling needed to reach a given score, demonstrating how reusable preparation can shift computation from repeated test-time attempts to a pre-task study phase.

Skill adaptation frameworks based on reinforcement learning often require restrictive assumptions to maintain stability, such as fixed observations or tightly controlled exploration schedules. In cluttered and dynamic environments, however, unrestricted exploration can lead to unsafe behaviour and unstable learning, particularly when task-relevant observations lie near obstacles or involve moving objects. In this work, we present Dist-GPRL, a distance-aware and safety-guided reinforcement learning framework for structured robot skill adaptation. Building upon Gaussian Process (GP)-based skill parameterisation, our framework sequentially adapts overlapping local windows of sparse trajectory via-points rather than modifying the complete skill at every policy step. Raw policy outputs are correlated through the GP covariance structure, producing temporally coherent trajectory updates while reducing the action-space and credit-assignment difficulties associated with global trajectory adaptation. Safety is incorporated through two complementary forms of guidance. A safe-subspace prior derived from the Hausdorff Approximation Planner (HAP) biases policy exploration toward feasible regions, while dynamically updated distance field clearance and gradient rewards provide local obstacle awareness. A trajectory-kinematics similarity regulariser further preserves the demonstrated velocity and acceleration characteristics during adaptation. We evaluate the framework on two dynamic object-manipulation tasks in simulation and transfer the learned policy to real-world robot execution. Experimental results demonstrate higher task success, lower collision frequency, and more stable learning than the baselines, while preserving the kinematic characteristics of the demonstrated skill.

Vision-language models (VLMs) enable robotic per- ception by associating visual observations with natural-language concepts. Yet their performance in coastal environments remains largely unexplored. We introduce a densely labeled coastal dataset containing more than 1,000 images collected across seven missions in three regions of Oahu, Hawaii, with 18 semantic classes and over 7,400 annotated instances. We evaluate seven modern VLMs through three complementary experiments mea- suring text-to-mask, mask-to-mask, and mask-to-text alignment. Broad landscape classes are generally recognized more accurately than conventional object and coastal classes, with coastal con- cepts presenting the greatest challenge. However, comparisons of shared conventional classes across coastal and terrestrial datasets reveal no consistent performance difference attributable solely to environmental context. Mask-to-mask matching also remains similar across conventional and coastal classes, while alternative textual labels substantially improve recognition of several coastal concepts. These results suggest that lower performance on coastal classes (at least on the objects/query categories evaluated) is heavily influenced by segmentation and linguistic representation.

This paper presents an end-to-end evaluation framework for image-triggered command injection against computer-use agents (CUAs). The goal is to test whether a local visual patch can induce verifiable environmental consequences along the full chain of screenshot input, VLM generation, action parsing, and environment execution. We train and deploy patches on author-controlled GitHub Pages pages and a locally deployed CSDN clone, and evaluate them in real environments across five open-source or publicly available GUI-agent or vision-language-model (VLM) backends. Our experiment aggregates 600 instance-level online cases, with T-ASR, TAPR, and E2E-ASR reaching 84.5%, 47.0%, and 20.3%, respectively. Trajectory analysis further shows that in some successful cases the agent first executes a malicious terminal command and then continues the original benign task. These results indicate that optimized local visual signals can affect not only VLM outputs but also propagate through the execution pipeline of open CUAs and create real environmental risk.

Marine robotic simulation provides a safe and inexpensive method of developing and testing algorithms for unmanned underwater vehicle (UUV) and unmanned surface vessel (USV) autonomy and perception before full field deployment. However, these simulations are often limited by the availability of simulated environments. Current marine robotics simulation suites offer manual ways to edit or create environments, but they require existing data or specialized knowledge of the environment system. To address these issues, we introduce a novel Unreal Engine 5 level generation pipeline that enables automatic creation of coastal environments for HoloOcean. Our pipeline relies on a user-provided overhead image of a coastal scene. The pipeline then uses the image to generate height map data, as well as automatically select assets and place them in the environment.

Robust speech-to-text translation systems should perform reliably across diverse acoustic conditions, yet practical pipelines lack controllable tools for systematic environment exploration. Large speech models remain sensitive to unseen acoustic conditions, as training data rarely cover the full range of real environments.We present NOPEHYPE, a structured training workflow that combines a controllable environment simulator, coverage-optimal environment reduction on Power Spectral Density (PSD) templates, and a small, interpretable hyperparameter search over simulator knobs. We show that simulator-generated noise achieves performance comparable to balanced realnoise training across Whisper and SeamlessM4T models, provide principled environment prototype sets, and identify practical default simulator configurations from a structured 27-run hyperparameter sweep.

Large Language Models demonstrate remarkable proficiency in static reasoning, yet training them as autonomous agents through Reinforcement Learning (RL) for long-horizon tasks is often hindered by severe reward sparsity. While conventional \textit{agent-side warming} up via supervised fine-tuning (SFT) can alleviate this, it is frequently limited by data scarcity and constrained exploration. To address this, we propose a paradigm shift to \textit{environment-side adaptation} by constructing \textbf{F}eedback-\textbf{E}nriched \textbf{E}nvironments (\textbf{FEEs}). Through a pilot study, we establish a feedback design strategy that reformulates environments by transitioning from action guidance to observation enrichment during the later stages of both intra-episode exploration and inter-episode evolution. Large-scale experiments on SciWorld and BFCL benchmarks using various Qwen3 model scales and RL algorithms such as GRPO, GSPO, and DAPO demonstrate that FEEs consistently yield performance improvements over standard settings. Furthermore, our analysis reveals that training with FEEs \textbf{(1)} stabilizes training dynamics by reducing entropy volatility, \textbf{(2)} facilitates proactive state-space exploration in difficult tasks, \textbf{(3) }ensures the internalization of environmental guidance into policy weights rather than acting as a mere inference-time prior, and \textbf{(4) }identifies intra-group feedback consistency as a critical boundary for stable optimization.

Lifelong navigation (LN) requires an embodied agent to solve a sequence of navigation subtasks in the same environment. Since solving each subtask from scratch incurs redundant exploration, an LN agent must consolidate experience from earlier stages and reuse it in later stages, often through persistent scene representations such as scene graphs or visual snapshots. However, existing approaches typically assume a stationary environment, whereas in real-world LN settings, human activities can cause the environment to evolve. With the stationary assumption violated, existing methods may fuse outdated prior observations with new observations, yet current benchmarks cannot reveal this failure mode. In this paper, we present EvoNav-Bench, which extends the GOAT-Bench style LN formulation in the context of evolving environments. Built on the ProcTHOR framework, EvoNav-Bench introduces environment modifications between navigation tasks, making prior experience useful but not fully reliable. This design enables controlled evaluation of how environment evolution affects LN agents that reuse prior scene observations. Using EvoNav-Bench, we benchmark three recent methods that build and reuse scene representations for navigation. We also compare three simple heuristic strategies for handling environment evolution: Frontier-Update, Fail-then-Update, and Stage-Reset. Our results show that existing methods are brittle under environment evolution, while the heuristic strategies enable a controlled analysis of how agents can adapt to scene changes and mitigate their impact.

Long-horizon target navigation requires a robot to sustain task execution across evolving observations, decisions, and physical interactions. This requires three coupled capabilities: maintaining valid scene memory, revising target beliefs under partial observability, and selecting interaction-feasible navigation endpoints. However, the state underlying each capability is only conditionally valid: scene representations become stale when objects move or disappear, unsuccessful searches alter beliefs over target locations, and geometrically convenient endpoints may still be infeasible for manipulation. To address these challenges, we present OmniNav, which formulates long-horizon navigation as continual inference over a factorized task state posterior coupling scene validity, target belief, and interaction feasibility. For representation, OmniNav incrementally constructs an updatable 3D object scene memory, preventing stale scene evidence from propagating to subsequent decisions. For exploration, it introduces an evidence-aware Bayesian belief-revision mechanism that derives dependency-aware region priors from semantic context, incorporates unsuccessful searches as negative evidence, and updates them for posterior-guided frontier selection. For interaction, OmniNav incorporates manipulation reachability and collision constraints into navigation-endpoint selection and propagates execution feedback through hierarchical closed-loop recovery. Extensive experiments demonstrate that OmniNav achieves the highest success rates among the compared methods on semantic ObjectNav and fine-grained instance navigation benchmarks, remains robust to target relocation, and improves real-world pick-and-place success from 53.3% to 71.7% over an adapted open-loop baseline. The project page of OmniNav is available at https://omni-nav.github.io/.

LLM agents are rapidly becoming production software, deployed to handle customer service, adjudicate disputes, and operate internal systems. Notably, the work of building them is increasingly handed to coding agents, yet existing benchmarks say little about whether an AI system can deliver one under the conditions of a real client engagement. We introduce $\tau^\tau$-bench (pronounced hyper-tau-bench), a benchmark that makes agent construction the task. A developer agent is given the records a business actually keeps, a client who holds requirements, a production API that operations must run through, a codebase to inherit, and limits on serving cost and models: the same starting point a real engagement provides. From these it must deliver a complete customer-service agent, scored by deploying that agent against held-out simulated users. Across 53 tasks spanning four domains, the strongest configuration, Claude Opus 5 under Claude Code, passes just 23.9% of evaluation simulations. Meanwhile, an expert-authored reference ceiling scores 82.2%. The failures mirror ones human agent developers see: models issue shallow queries in place of deep comprehension of the records, communicate almost nothing to the client, and experiment too little with agent architecture and serving spend, shipping the first design that runs. We aim for $\tau^\tau$-bench to turn the work of cooperative agent building into a measurable target for coding agents.

As terminal-based code agents become prevalent, agent trajectories have accumulated at scale, while realistic, executable environments remain scarce. However, environments are what agent post-training actually requires: each can be re-queried into many verifiable tasks and provides execution feedback, whereas a trajectory is a single frozen demonstration. Rather than generating environments from scratch, we observe that the tool-execution history in existing trajectories exposes the structure and contents of the environments in which they ran, making it possible to reconstruct those environments from the trajectories themselves. Thus, we introduce Terminal-Universe, a framework which turns each trajectory into a reusable environment and explores it for synthesizing new tasks and continued interactions. Specifically, Terminal-Universe replays the file operations recorded in a trajectory to restore each file before the agent modified it, yielding a partial workspace; a completion agent then supplies the missing files and dependencies. On this recovered workspace, we both reconstruct the original intent task and synthesize entirely new ones. Besides, we also scale the tasks along two complementary axes: breadth and depth. For breadth, we mine directional dependency relations between related environments and synthesize cross-workspace queries spanning multiple codebases, as developers routinely do in real-world development. For depth, we extend the initial single-turn query into a multi-round session that captures iterative user feedback and requirement refinement via a user agent. Applied to public terminal agent trajectories, Terminal-Universe produces 37.3k task-sufficient environments. Supervised fine-tuning of Qwen3.5-27B on this corpus improves single-round performance on Terminal-Bench 2.1 by 11.9 points and multi-round performance on EvoCode-Bench v2 MT@4 by 13.8 points.

For robots to operate reliably in real-world environments, they need to perceive their surroundings, act, and reason about the consequences of those actions. Rapid progress in the domains of representation learning, VLA models, and world models has significantly enhanced the capabilities of robot learning systems, enabling robots to work in increasingly complex environments. However, these paradigms are typically developed in isolation, resulting in fragmented systems that struggle with generalization, long-horizon temporal reasoning and planning, and deployment in unstructured environments. In this survey, we present a unified perspective on robot learning by organizing the existing methods along three complementary axes: understanding through representation learning, acting through VLA models, and reasoning through world models. We introduce a structured taxonomy that captures key design choices in environment representation, policy learning, and predictive modeling, and summarize the recent progress in these domains. Beyond classifying the existing works, we analyze how these components interact, discuss common limitations, and highlight emerging trends towards more integrated systems. Through this lens, we identify the challenges in the domain of robot learning, including uncertainty quantification, out-of-distribution generalization, cross-embodiment transfer, long-context understanding, and long-horizon planning. We argue that these challenges arise not only from limitations within individual components but also from the lack of integration across perception, action, and reasoning. Building on this analysis, we outline future directions towards unified, physically grounded, and probabilistic robot learning to develop robust robotic systems that maintain consistent internal representations and support decision making over extended interactions in real-world environments.

Dust in agriculture presents a significant challenge for autonomous agricultural machinery. Dust can impair the performance of sensors and algorithms. This work, therefore, presents a concept for a proving ground consisting of an indoor and outdoor area. The indoor area comprises a laboratory test bench where dust circulates in a closed system and a test hall where life-size objects can be placed. The outdoor area features dedicated test setups that enable reproducible data to be recorded with and without dust during real-world agriculture work. The proving ground and the setups are visualized in 3D.

Cooperation in multi-UAV systems requires reliable relative perception so that follower vehicles can maintain formation and continue their mission safely even when absolute positioning sensors degrade or fail. This paper presents a vision-based cooperative formation framework running on a follower UAV that uses a front-facing RGB-D camera to detect, track, and localize a leader UAV in real-time. A lightweight YOLO-based detector is trained on a dedicated drone dataset and deployed onboard to predict leader bounding boxes, which are then fused with depth information via a pinhole camera model to estimate the leader's relative pose. These estimates provide a leader-follower position controller and can also be used as a backup when GPS or external localization is unavailable. This framework is implemented as a set of ROS nodes and evaluated in a physics-based multi-UAV simulation built on XTDrone, with sensor noise and communication dropouts. We evaluate detection accuracy, runtime, and formation-keeping error under nominal conditions and under simulated failures of the positioning sensors. The results show that the proposed framework maintains stable leader-follower formations with reasonable computational cost and provides a practical basis for extending vision-based cooperative formation control to real-world multi-UAV systems.

We study autonomous mathematical discovery in the Station, an open-world multi-agent environment in which AI agents from different model families pursue a shared research goal without a central coordinator or scripted pipeline. Agents choose their own research directions, conduct experiments, collaborate and publish papers. These papers accumulate into a shared body of knowledge that later agents can read, cite and extend. We evaluated the Station on 12 mathematical construction problems from the AlphaEvolve study and two additional case studies. Five of the 12 problems yielded results novel relative to the prior literature: a new infinite family of finite field Kakeya sets, new exact 604-point kissing configurations in eleven dimensions, improved bounds for the discretized Kakeya needle and sign uncertainty problems, and a substantially improved lower bound for Erdős's minimum overlap problem. Agents also discovered novel infinite families for Book Ramsey numbers. Their research extended beyond searching for high-scoring constructions: agents developed explanations of their findings and proved theorems outside the assigned tasks. These explanations guided further discoveries and were preserved in the agents' papers, making the underlying insights easier for external researchers to understand and build upon. All presented discoveries are supported by exact constructions or proofs formally verified in Lean. We release the source code, full agent dialogues, papers and verification code, providing a transparent record of how these discoveries emerged.

Continuous self-improvement requires an ever-expanding pool of self-generated, diverse, adaptive goals. For language agents, existing training environment pools (hand-curated, statically synthesized, or frozen-verifier) keep the goal distribution fixed as the learner scales. We introduce SPADE (Self-Play in Adaptive Synthetic Executable Environments), a self-play RL framework in which a single LLM plays two roles: an Environment Designer that writes complete, long-horizon training environments as executable code with an OpenAI Gym-style reset()/step() interface, and a Reasoning Agent that learns to act in them. Each is a stateful, multi-turn environment (state transitions, reward functions, and verification code), so one interface spans reasoning problems and multi-step agentic tool use. The Reasoning Agent's regret is estimated using the gap between its reward with and without privileged hints; in optimizing this regret signal the Environment Designer learns to target environments at the edge of the agent's capabilities while keeping them feasible. Through extensive experimentation, we find several components critical to success: grounding the Environment Designer on documents sampled from a large pretraining corpus, and giving it an accumulated environment memory. Scaling to 30B-parameter models, SPADE improves over the strongest fixed-environment baseline by +5.3 on average across eight held-out math, science, code, and reasoning benchmarks, and lifts the tool-use setting by +5.7 on BFCL-v4 multi-turn and +13.9 on ACEBench-Agent; on the games setting, the margin over the strongest baseline grows with model scale. By making environment design itself a learnable component, SPADE takes a concrete step toward open-ended self-improvement.

General-purpose motion trackers enable humanoid robots to follow diverse whole-body motions while maintaining balance, but are trained only on flat ground, failing to exploit bipedal mobility over complex terrain. Cross-terrain controllers, meanwhile, are task-specific or accept only low-dimensional locomotion commands. We introduce InterTrack, the first behavior world model (BWM) for robust whole-body tracking with environment interaction. Its Transformer jointly predicts the next action, state, and behavior distribution, learning environment-conditioned dynamics. To scale interaction training data, an automatic annotation pipeline reconstructs 3D support geometry from retargeted motions. At deployment, the policy handles commands implausible in the current environment in a "best-effort" manner. Quantitatively, InterTrack achieves an 81.3% success rate on terrain interaction (4.3 times the best evaluated baseline) and a 99.3% fall-recovery rate, while also improving free-space tracking and outperforming three leading tracking baselines across all of these regimes. To our knowledge, we provide the first demonstration of real-time cross-terrain whole-body teleoperation on a humanoid robot, alongside object interaction, stable responses to missing supports, and robust recovery from falls.

Social robots are expected to operate across diverse environments, where similar arrangements can imply different socially appropriate actions, e.g., starting a conversation may be acceptable in a crowded home but disruptive in an office meeting. Because such norms and environments cannot all be anticipated in advance, robots require continual learning (CL) to adapt from sequential experience while retaining previously acquired knowledge. Prior work has studied CL for generating socially appropriate robot actions, but it has not addressed domain-incremental settings in which the robot incrementally encounters diverse contexts (e.g., living room, meeting room, office, hallway), where both environmental (e.g., whether the space is open or cluttered with furniture) and social cues (e.g., how people or other agents are positioned around the robot) jointly shape the appropriateness of robot actions. We address this gap with the Explicit Disentanglement Dual-Branch (EDD) framework. EDD explicitly separates environmental and social-agent related knowledge and uses replay-based rehearsal to mitigate forgetting while learning the appropriateness of robot actions (e.g., cleaning, serving, starting a conversation) across several indoor domains. Experiments show that EDD outperforms several state-of-the-art baselines, and ablation studies further evaluate different disentanglement strategies and the sensitivity to domain ordering. Our code is publicly available at https://github.com/Cambridge-AFAR/Mind-the-Context.git.

The deployment of large language models (LLMs) in mental health contexts raises questions about the relationship between clinical safety and environmental cost. In this paper, we examine this relationship by combining K-Bench clinical safety scores with EcoLogits life-cycle assessment estimates across 47 supported model configurations. We evaluate model performance and environmental impact across four dimensions: energy use, carbon emissions, water consumption, and abiotic depletion. The results indicate a non-linear trade-off at the upper end of the safety distribution: a 2.61 percentage-point increase in clinical safety score corresponded to an approximately 60-fold increase in estimated energy use per million output tokens. Row-level analyses further suggest that additional test-time compute did not consistently improve clinical safety and, in some configurations, was associated with lower clinical safety scores. These findings suggest that relying solely on larger models or additional inference-time computation may be an inefficient strategy for improving safety in therapeutic AI systems. We discuss the implications for sustainable deployment and highlight dynamic model selection, including model cascading, as a potential approach for reducing environmental impact while preserving clinical performance in higher-risk cases.

In real pigsty environments, pig point clouds often come into close contact with background structures, resulting in blurred target boundaries, local adhesion, and background mis-segmentation. This reduces the accuracy of subsequent point cloud completion and body size measurement. To address these challenges, this study proposes a pig point cloud segmentation method based on boundary feature analysis. The proposed method adopts Octree Transformer as the backbone network and integrates local geometric details with global semantic context through octree convolution, self-attention encoding, and multi-scale feature fusion. Furthermore, soft-distance boundary pseudo-labels are generated to provide continuous boundary supervision, and a bidirectional cross-boundary semantic module is designed to enable explicit interaction between boundary and semantic features. Experiments conducted on a comprehensive dataset demonstrate that the proposed method significantly outperforms various state-of-the-art models in terms of segmentation accuracy, mean intersection over union, and boundary delineation. The results indicate that the method effectively alleviates boundary adhesion, providing reliable point cloud inputs for downstream precision livestock farming tasks.

Apollo did not reach the Moon merely because its engineers could solve difficult equations. It succeeded by turning a distant ambition into a mission architecture of explicit objectives, simulation, verification, and repeated correction. AI now faces a similar transition: frontier models can solve difficult tasks once the problem, tools, and success criteria are specified, yet consequential real-world challenges rarely arrive in an executable or verifiable form. We introduce Apodex Discovery, a framework for building and evaluating discoverative AI through the heavy-duty solver, a system comprising a foundation model, harness, tools, and control policies that pursues extended, stateful, verifiable investigations. It has three core components. First, a problem-scouting process surveyed 561 industries across 16 sectors, assembled 423 high-value real-world problems, and selected 20 for the initial release. Second, a common environment-task-episode abstraction provides data, tools, constraints, feedback, trajectory recording, and verification of intermediate artifacts and final submissions. Third, HDS6 evaluates Tools, Repair, Alternatives, Coherence, Evidence, and Scope independently of final-task success. In AAV capsid design, Apodex surpassed the published state of the art by 7% across viability, tropism, structure prediction, and generative design. In drug repurposing and reformulation, a task-specific biomedical environment improved the mean normalized prediction score of GPT-5.5 and GPT-5.6-sol by 2.5 and 7.6 points over the same closed-book backbone. Controlled ablations show that the fixed TRACES episode interface enables attribution of performance differences to specific solver components. Apodex Discovery moves AI evaluation beyond predefined benchmarks toward verifiable investigations aimed at genuine discovery.

Robust navigation policies for autonomous agents must generalize across continuously varying environmental conditions such as turn rates, obstacles, friction, pits, and slopes. Curriculum generation provides a principled mechanism for improving generalization by progressively adapting training environments, but designing such curricula in a sample-efficient and automated manner remains challenging. This paper proposes a reparameterized curriculum generation framework for structured continuous environment parameters using unidirectional gradient-based optimization. To improve robustness in multimodal observation spaces consisting of image-based and scalar inputs, a distribution-shift regularization objective is incorporated to encourage the learning of finer-grained latent representations. The proposed method is evaluated across two continuous-control OpenAI Gym environments: a 2D obstacle-based Car Racing variant and Bipedal Walker variant, where coupled environment parameters jointly influence policy performance. Across five random seeds, our method consistently outperforms vanilla policy training, random parameter sampling, manual curricula, frontier-based methods, Self-Paced Reinforcement Learning (SPRL), Absolute Learning Progress with Gaussian Mixture Models (ALP-GMM), and reverse curriculum learning baselines. Ablation studies further demonstrate the effectiveness of the reparameterized curriculum mechanism across both environments, while highlighting environment-dependent benefits of the auxiliary regularization objective.

Agentic reinforcement learning (RL) often suffers from delayed and sparse rewards in real-world environments. A promising solution to this challenge is credit assignment, which aims to decompose trajectory-level rewards and provide more fine-grained supervision for intermediate decisions. However, existing credit assignment approaches ignore the rich process information naturally generated during environment interaction, e.g., interaction history. We argue that such information provides valuable supervision for identifying the contribution of individual actions. To this end, we propose Environmental Feedback-based Credit Assignment (EFCA), a multi-timescale credit assignment approach for long-horizon agentic RL. EFCA complements the long-term outcome signal with two environment-grounded process signals: a short-term feedback signal that captures the immediate effect of the current action and a medium-term state-history signal that identifies ineffective patterns from recent interactions. Both signals are directly extracted from environment feedback and integrated through a return reweighting mechanism. Experiments on ALFWorld and WebShop demonstrate that EFCA consistently improves both task success and task quality over strong baselines, highlighting the effectiveness of environment-grounded multi-timescale credit assignment for long-horizon agentic RL.

Embodied agents using LLM-based planners often struggle with physical hallucinations, poor generalization to long-horizon tasks, and lack of environmental awareness. We propose GraphThink, a novel framework that integrates a task graph to provide structured knowledge for robust planning and a scene graph to maintain environmental memory for event-driven replanning. Specifically, the task graph guides LLM thinking through contextual prompting and iterative refinement, effectively mitigating planning hallucinations. Furthermore, within the GRPO framework, the task graph offers delicate reward design to train the LLM planner, enhancing long-horizon planning capabilities and improving generalization. Finally, an event-driven replanning module, powered by the scene graph, enables closed-loop environment awareness and error correction. GraphThink achieves state-of-the-art performance on the ALFRED benchmark. In particular, our high-level planner surpasses leading API-based LLMs on both the validation set and held-out long-horizon tasks, underscoring its robust zero-shot and few-shot capabilities. Additional evaluations further demonstrate strong out-of-distribution generalization to novel tasks and environments.

Today, we improve models by training and evaluating them on problems at the frontier of their abilities. Creating such problems is itself a demanding task, requiring the ability to probe model limits and generalize beyond existing question distributions. It also means placing problems at a precise difficulty level, which requires understanding what it takes to solve them. In short, generating problems calibrated to a model's current frontier demands capability beyond it, an increasingly burdensome constraint as models improve. Our key insight is that we can leverage this constraint to our advantage: a model that can generate problems consistently calibrated to a given frontier must possess capability beyond it. Accordingly, we present Ask-E, an environment that benchmarks and trains models on their ability to write questions at a given skill level, rather than answer them. Concretely, we define target skill levels as ranges bounded by the capabilities of two existing language models. A generated question is successfully calibrated if exactly one of the two models can solve it, placing it precisely within the target range and differentiating the capabilities of these models. Ask-E serves both as a benchmark and a training environment, where models generate problems calibrated to a variety of skill levels. We find that even frontier models achieve below 50% calibration on the benchmark, leaving significant headroom to measure future progress. We also show that training on this environment leads to improvements across a number of downstream math benchmarks even with no new math data, no interaction with stronger models, and no correctness-based reward.

In vibe coding, people describe software in natural language and delegate implementation to AI agents. By analogy, vibe commerce allows people to express buying or selling goals in natural language and delegate the corresponding tasks to agents. Commerce, however, requires independently controlled Buyer and Merchant agents to interact in a shared market while preserving their private objectives and distinct authority. We introduce Agentic Commerce World (ACWorld), an environment for evaluating such agents across ongoing transactions. Through its Vibe Commerce Protocol (VCP), ACWorld validates agent actions before updating shared transaction state and records the resulting interactions, making agent behavior auditable and evaluation reproducible. The ACWorld Benchmark contains a 200-task capability-coverage track and a 60-task large-catalog track that searches 785,022 transactable listings. Across ten models, mean scores range from 65.9% to 85.6% and from 56.1% to 91.4%, respectively. Our analysis shows that process-level evidence is necessary: final state alone can miss evaluated errors, incomplete trajectories still retain useful process signals, and large-catalog tasks expose bottlenecks across stages.

Maintaining a stable pose during physical interaction is a significant challenge for aerial robots, often limiting their use in contact-based tasks. This paper presents a novel uncrewed aerial vehicle (UAV) platform designed to transition from unconstrained flight to a stable, constrained work platform via environmental anchoring. Our system comprises: 1) a multirotor with a tilt-rotor mechanism that decouples pitch from forward motion, enabling stable hover at non-zero pitch angles, and 2) a novel underactuated, cable-driven, prismatic gripper featuring compliance to adapt to irregular geometries, designed to stabilize the UAV by anchoring it to its environment. We present the design and prototyping of the complete system and validate its performance through a series of real-robot flight tests. Results demonstrate that anchoring significantly improves stability for interaction tasks, reducing positional drift RMSE by over 95% compared to a free-flight baseline, even under windy conditions. The anchored system can withstand longitudinal reaction forces up to 75N while maintaining a stable pose. Furthermore, across a range of target geometries and orientations, the system demonstrated consistent stability with a positional drift RMSE that never exceeded 3mm. These results establish the viability of our approach for complex physical interaction tasks, such as sampling tree health by drilling or sensor installation in hard-to-reach locations. Watch our UAV at: https://youtu.be/HDQ8S4ZW3Ls

Multi-robot systems, particularly heterogeneous robot swarms, can improve the efficiency of complex task execution through parallel collaboration and complementary capabilities. However, conventional rule-based methods rely on predefined task models and specialized decision making programs, making it difficult to understand complex semantic instructions and coordinate heterogeneous robots. LLMs introduce strong language understanding and task reasoning capabilities, allowing multi-robot systems to interpret instructions, decompose tasks, and assign roles according to task semantics. VLMs further incorporate visual perception, enabling robots to reason about objects, regions, and spatial relationships in physical environments. Nevertheless, existing LLM/VLM based methods often depend on known maps, centralized and synchronized decision making, limiting their generalization to heterogeneous robots and unseen tasks. We therefore propose a framework that combines decentralized asynchronous reasoning, lightweight information sharing, capability aware collaboration, and a unified action interface, enabling general purpose VLMs to generate robot specific actions executed by learning free experts without task or robot specific training. Experiments across diverse scenarios and multiple VLMs show success rates above 70%, with completion time reduced by up to 55.8% relative to the geometric greedy baseline.

Large language model agents have shown promising capabilities in data-driven scientific discovery tasks, where an agent interacts with an execution environment and produces a statistical claim. Long-horizon scientific analysis remains constrained by the lack of process supervised environments over real-world scientific data. This paper introduces SciDisco, a scalable framework for training Scientific Discovery agents in process-verifiable environments. SciThèque compiles hypotheses, datasets, hidden evidence graphs, and verifiers into task environments where analytical progress can be checked during interaction. DAG-grounded trajectory synthesis uses these environments to construct verifier-filtered multi-turn demonstrations. DiscoPO then uses the environment as the source of training signal, assigning turn-level credit to actions that produce verifiable analytical evidence. Experiments show that SciDisco-14B reaches state-of-the-art on hypothesis-driven scientific data analysis benchmarks.

Student engagement (SE) is a critical predictor of academic performance and retention in STEM education, yet existing measurement approaches are often intrusive, manually intensive, or unsuitable for real-time classroom use. This thesis proposes a novel $\textit{Biometric Sensor Network}$ (BSN) designed to enable real-time measurement and continuous tracking of individual student engagement in STEM classroom environments. The system enables capturing of behavioral, emotional, and cognitive indicators through camera-based sensing while preserving ethical and privacy constraints. To measure these indicators unobtrusively and ethically, we propose a BSN composed of $\textit{Student Processing Units}$ (SPUs) that function as distributed sensing nodes. The network is explicitly designed to satisfy five objectives: it must be $\textbf{non-intrusive}, \textbf{non-invasive}, \textbf{non-stigmatizing}, \textbf{real-time}$, and $\textbf{automatic}$, while ensuring rigorous protection of student data security and privacy. Each SPU supports two operational modes: (i) a $\textit{dataset-collection mode}$, in which raw student video is temporarily recorded to construct a private SE dataset for model training and validation, and (ii) an $\textit{analysis mode}$, in which the SPU performs real-time inference on 10-second video segments without storing or transmitting raw frames. In this analysis role, each SPU enables fully on-device processing---including face detection, gaze estimation, and affective analysis---ensuring that no identifiable video data leaves the device. A secure backend infrastructure manages device authentication, session orchestration, and encrypted data ingestion. The full system integrates hardware design, computer-vision pipelines, wireless networking, security protocols, and session-level data management.

Physical learning rules such as equilibrium propagation (EP), coupled learning (CL), and adjoint coupled learning (AL) train resistive networks through local measurements. In the small-nudge limit EP and CL exactly conserve the conductance mass K = (1/2) sum_e kappa_e^2, a property that stabilizes training. We show that conservation also governs the inductive bias of these rules. For a single output we prove that EP and CL are trajectory equivalent, so single-output experiments cannot distinguish what the two rules learn. We prove that AL does not conserve the mass but dissipates it at exactly twice its own loss. In linear circuits we prove that the conserved mass has no functional consequence: all three vector fields are homogeneous in the conductances, so the selected solution is independent of the initialization scale. Fixed nonlinear elements break this protection. In diode circuits the learned input-output function depends on the initialization scale by up to about forty percent, an effect absent in linear controls, and the conservative rules retain this memory permanently while the dissipative rule partially erases it. At matched training loss the dissipative rule typically generalizes worse than the conservative rules, although it reaches low training loss faster; the penalty correlates with the mass dissipated en route and fades in larger circuits, where little mass is lost. The conservation structure of a local learning rule thus sets its initialization memory, its training speed, and, where dissipation is appreciable, its generalization; it should be treated as a design parameter of physical learning machines.

Scaling coding agents requires a continuing supply of executable data for training, benchmarking, and continuous evaluation. Each task must couple a realistic software state with a specification, development tools, and reliable verification. To expand this supply, we present Change2Task, a system grounded in repository history that converts merged pull requests into verified tasks on healthy modern revisions of the same repository. It aligns historical evidence with evolved code, reconstructs task states through Patch Reversal, Code Mapping, or Agent Reconstruction, and validates the lifecycle from a healthy base to a task state and a restored state. By deriving multiple tasks grounded in developer evidence from maintained environments, Change2Task provides executable data for coding agent training and evaluation while reducing repeated environment setup, storage, and task construction effort. We evaluate the system through five common and widely adopted coding agent task families: Bug Fix, Feature Addition, Test Generation, Application Programming Interface Migration, and Security Repair. Starting from 1,130 source changes eligible for construction, Change2Task achieves 79.6% verified task construction success across these task families. On a matched candidate set, it recovers 29.2% more verified tasks than a construction baseline based on pull requests. Historical and reconstructed cases achieve up to 98.0% matched outcome agreement under agent evaluation, while reuse of modern bases reduces measured expenditure across the complete pipeline by 10.8%.

Wind turbine blade defect detection remains highly challenging in real-world inspection scenarios due to limited on-site data and the subtle visual characteristics of defects. In practice, blade defects are often small-scale, low-contrast, and difficult to distinguish from complex backgrounds, which significantly limits the robustness of existing detectors. To address these challenges, we propose BladeYOLO, a defect detection framework for wind turbine blades. Specifically, we integrate a Vision Transformer (ViT) backbone initialized with DINOv3 self-supervised pre-trained weights into YOLOv12-L, enabling the transfer of large-scale generic visual priors to blade defect detection and improving feature representation under limited training annotations. To enhance the perception of subtle defects, we further develop a Mamba-guided Weak-Defect Enhancement module, which consists of a Detail-Enhanced Multi-scale Branch for preserving high-frequency structural cues and a Cross-Mamba module for progressively propagating high-level semantic guidance to shallow features. In addition, we introduce a lightweight Style-Injector module that captures environment-related style information via Fourier decomposition and injects it into selected ViT self-attention layers, thereby improving robustness against environment-induced appearance variations. Extensive experiments demonstrate that BladeYOLO achieves superior performance on the WTBlade-Defect dataset, with additional annotation-budget experiments showing its favorable performance under reduced training annotations. Evaluation on the public Wind Surface Defect dataset further provides supportive evidence for the cross-dataset robustness of BladeYOLO. In particular, on this public dataset, BladeYOLO outperforms the best competing method by 3.5% in mAP$_{50}$ and 2.5% in mAP$_{50-95}$.

Reflections from shiny objects and glass facades naturally extend the field of view of a camera, capturing the surrounding environment without the need to pan the camera or acquire a full panorama. We propose PanoLess, a Gaussian-splat-based framework that reconstructs the surrounding environment as a distant illumination map from images captured on only one side of a reflective surface. PanoLess leverages surface-aligned 2D Gaussian splats with deferred shading to recover accurate per-pixel normals and reflection cues, which are fused into a neural cubemap representation of the environment. In addition, PanoLess produces a visibility map that explicitly denotes which regions of the environment are supported by the partial reflective observations. Unlike existing inverse-rendering and reflection-aware Gaussian-splatting approaches, which typically require full 360-degree coverage and struggle under incomplete views, PanoLess enables consistent, physically grounded illumination estimation from partial-view input. We show that PanoLess achieves high-fidelity and geometrically consistent environment reconstruction, outperforming reflection-aware baselines on a new custom synthetic benchmark and publicly available datasets, and demonstrating generalization to real-world reflective captures.

Federated learning has emerged as a promising paradigm for spatio-temporal forecasting (STF), enabling collaborative model training without sharing raw observations. Existing federated STF methods primarily regard cross-client heterogeneity as an optimization challenge and mitigate it through personalized approaches. However, such heterogeneity fundamentally stems from diverse \emph{environmental conditions}, and these methods capture environment-specific forecasting patterns, hardly generalizing under environmental shifts. Our key insight is that the environmental diversity across federated clients should be exploited, as they provide \emph{complementary observations of the same underlying spatio-temporal system}. Based on this insight, we propose \method, a novel federated de-confounding framework that \textbf{treats clients as distinct causal environments}. \method leverages the client heterogeneity as distributed environmental evidence and learns a global prototype codebook to capture shared environmental regimes. We further derive a theoretical federated de-confounding bound that is linearly controlled by the averaged confounding strength. Extensive experiments demonstrate that \method consistently outperforms federated baselines, while providing transferable, interpretable, and communication-efficient environmental representations.

We introduce time-reversed imaging, a new paradigm that infers what just happened in a scene from fading multimodal traces. Instead of extrapolating or interpolating video frames, our goal is to infer past human-environment interactions from residual physical imprints observable in thermal, ultraviolet, and visible spectra. To study this problem, we present TRACE-HEI, the first proof-of-concept dataset for time-reversed imaging, containing synchronized tri-modal video sequences of actions such as sitting, touching, moving objects, and liquid spills, captured across diverse materials and recorded up to three minutes after contact. To establish the benchmark, we propose a multimodal inference approach that extracts structured textual descriptions of detected traces and uses them to constrain a vision-language-guided diffusion model for reconstructing plausible past frames. Experiments show that inferring recent events from fading traces is challenging but feasible when complementary modalities reduce solution ambiguity. This work defines the first computational and experimental foundation for time-reversed imaging, bridging vision, physics, and generative reasoning, and opening new directions for scene understanding beyond instantaneous observation.

Multi-stream robot manipulation policies achieve unparalleled sample efficiency and generalization by modeling actions relative to environmental reference frames. However, existing approaches typically assume these frames to be strictly exogenous. This causal assumption collapses in dynamic settings, such as when a single robot arm manipulates a moving object or when two arms coordinate, where each arm effectively becomes part of the dynamic environment of the other. We propose DynaMAC, a lightweight, policy-agnostic framework that resolves this causal limitation while preserving the sample efficiency, computational speed, and flexibility of multi-stream policies, DynaMAC treats the opposite arm as a dynamic task parameter, thereby providing a unified formulation for dynamic manipulation and bimanual coordination without requiring an explicit leader-follower relationship. To rigorously evaluate these capabilities, we introduce DynaBench, a novel benchmark for robot manipulation in dynamic environments. Across both dynamic environments and bimanual manipulation tasks, DynaMAC outperforms leading probabilistic and generative baselines by over 35 percentage points while requiring 20 times fewer samples. Crucially, DynaMAC generalizes zero-shot from static demonstrations to dynamic environments, substantially simplifying data collection and establishing an elegant bridge toward human-robot collaboration.

Teachers, conference chairs, and public readers all judge writing from limited evidence, seeing only a finished document and not the process that produced it. Final text alone cannot reveal whether a document was produced through human typing, AI generation, or mixed human-AI collaboration. Existing process-tracking tools help, but many are tied to host-document histories, provide coarse activity records, and offer limited control over the writing environment. Humanly is a writing platform that makes the writing process itself the evidence. Users configure writing environments for personal documents or assigned tasks and draft in a workspace that records writing activity and in-platform AI assistance. Humanly can package a completed session into a sealed writing certificate with configuration-aware anomaly behavior review. It can support writing scenarios such as course assignments, peer review, and personal certification. Our user study shows that Humanly is helpful across roles, and a red-teaming study shows that the Humanly Typing Detector distinguishes human hand typing from automated typing.

Modern AI agents rely on elaborate inference harnesses such as Claude Code, Codex, and OpenClaw to drive multi-turn reasoning, tool use, and access to external systems. While powerful, these complex harnesses also make agents hard to train end-to-end with open infrastructure, whose SFT/RL stacks cannot natively express stateful, multi-process harness inference. To address this, we present OpenForgeRL, an open-source framework for training harness-based agents end-to-end in diverse environments. OpenForgeRL achieves this with a lightweight proxy that serves the harness's model calls while recording them as training data for a standard RL codebase (e.g., veRL), and a Kubernetes orchestrator that runs each rollout in its own remote container, together enabling training on any harness in any environment at scale. By decoupling training and inference, OpenForgeRL allows researchers to easily train, study, and improve agents directly in the real harnesses and environments they are deployed with. We validate our framework across diverse, complex harnesses and environments, spanning tool/claw-based agents and multimodal GUI browser- and computer-use agents. Using only hundreds to a few thousand tasks, OpenForgeClaw reaches 31.7 pass^3 and 55.9 pass@3 on ClawEval and 33.7 on QwenClawBench. OpenForgeGUI reaches 37.7 on OSWorld-Verified, 63.0 on Online-Mind2Web, and 72.3 on WebVoyager. Both outperform open baselines of similar size on nearly all benchmarks, and in the GUI setting match or surpass models several times larger. Beyond benchmarks, we analyze how harness choice (e.g., ZeroClaw, OpenClaw, Codex) and RL shape agent behavior. We find that some harnesses are substantially harder to learn than others, and that RL improves agentic reliability, such as self-verification, tool coverage, and completing multi-step plans, though critical abilities such as error recovery remain weak.

The presence of UAVs in military operations has recently increased, also increasing the demand for defense systems against UAV attacks. UAVs can also be used as countermeasures. Most available methods rely on UAV-to-UAV communication and global positioning. However, such resources may not be available in modern warfare scenarios. To address these limitations, we propose a pipeline for ground-target protection against UAV attacks that employs autonomous swarms of UAVs. We assume a communication- and GPS-denied environment in which the UAVs use onboard sensors to track the target and coordinate as a swarm. We developed Kalman filters to estimate the states of unknown targets and the positions of UAVs in the swarm using only relative measurements. Also, our strategy is to encircle the target of interest to maximize coverage. To achieve that, we propose a decentralized swarm encirclement technique that adapts to the target's motion. Our approach was extensively validated using real robots, demonstrating its effectiveness in detecting, encircling, and intercepting hostile UAVs.

Estimating traversability in unstructured environments requires conditioning on robot embodiment, as the same terrain can be traversable for one platform and unsafe for another. Existing methods often transfer predictions across morphologies through late-stage trajectory filtering rather than encoding platform constraints in the learned representation. We propose Capability-Aware Traversability (CAT), a framework that embeds physical limits directly into the spatial feature space. CAT grounds dense supervision masks in physical trajectories through an interactive annotation pipeline and modulates semantic terrain maps with robot-specific traversability vectors through Spatially-Adaptive Denormalization (SPADE) blocks. Across human-annotated and trajectory-aligned datasets, CAT leads all ranking-based metrics, improving AUROC by 11.0% on physically executed trajectories and AUPRC by 15.8% on human traces over the strongest baseline. Ablations show that spatial conditioning and per-robot prototypes produce capability sensitivity beyond generic path prediction. Deployments on a legged quadruped and a wheeled skid-steer demonstrate embodiment-aware obstacle avoidance on embedded hardware at 4.8 Hz.

We consider a task planning scenario in which robots sharing a persistent environment are assigned tasks one at a time from a held-out sequence. Standard task planners, lacking foresight of future tasks and inconsiderate of others' constraints, solve each task in isolation, leaving terminal states that increase future cost for all, side effects that compound over lengthy task sequences. To reduce cost over the sequence, a robot must anticipate how its actions now may impact performance on future tasks for all robots sharing the environment. Therefore, we present courteous anticipatory planning, wherein a model-based planner proposes candidate plans and selects the one that jointly minimizes immediate cost and aggregated expected future cost across all robots, estimated via independent per-robot learned estimators. This factored formulation avoids combinatorial joint rollouts and supports modular deployment: adding a robot requires only training its own estimator. We evaluate in two persistent PDDL domains, a home environment with robots that have similar capabilities but different responsibilities, and a restaurant environment where robots' distinct capabilities create states that other robots lack the capability to resolve. During lengthy task sequences, our planner reduces total cost by 10.43% versus myopic and 4.03% versus selfish anticipatory planning in a two-robot home environment and by 17.41% and 13.24%, respectively, in a three-robot restaurant.

Spatio-temporal machine-learning modelling is an important tool in environmental research. However, machine-learning models are highly sensitive to both the characteristics of the training data, such as its distribution, and methodological choices, including the cross-validation strategy. Each decision has impact and implications on the model itself as well as the estimation of the model quality and applicability for certain purposes. Taking into account the large role of machine-learning based maps of the environment in science and their transfer into practice, transparent reporting of spatio-temporal models, ideally using standardized model protocols, is essential to enable trust, transparency and comparability. However, such protocols are currently lacking for spatio-temporal modelling. We propose STeMP (Spatio-Temporal Modelling Protocol) to fill this gap by serving two purposes: standardized reporting to understand the model functioning as well as providing guidance during the modelling process by pointing at critical decisions and parameters. The protocol is structured in three sections: Overview, Model and Prediction. The Overview section contains metadata, while the Model and Prediction sections go into detail, describing predictors, evaluation and software, and further relevant elements of the modelling workflow. The protocol definition is hosted on GitHub and accompanied by an R-package (https://github.com/LOEK-RS/STeMP). The R-package contains a web application that can be used to fill the protocol either manually or in a semi-automated way from provided modelling objects. Warnings are returned from the protocol when common pitfalls are encountered, which may help authors as a guide through the modelling process but also support reviewers in the assessment of modelling studies. Via GitHub, incorporation of contributions and feedback from the community is encouraged.

Accurate modeling of environmental systems is fundamental to scientific understanding and decision-making, yet remains challenging because observations are limited and physical dynamics vary across systems. Retrieval-augmented approaches offer a natural path to transfer knowledge across systems, but standard embedding-based retrieval does not guarantee consistency of underlying physical processes, since scenarios with similar embeddings may arise from different underlying mechanisms. We propose Physics-Informed Environmental Retrieval (PIER), a model-agnostic framework that augments embedding-based retrieval with a physics-aware stream that scores candidates by flux-response consistency with the target, using local verifiers trained on physics-derived flux features. A weight adjustment mechanism then learns per-scenario weights that adaptively balance the two retrieval streams based on diagnostic features summarizing physics-stream reliability. Experiments on 356 lakes across the Midwestern United States spanning 41 years show that PIER consistently outperforms baselines for water temperature and dissolved oxygen prediction, and serves as a general augmentation strategy across diverse backbones.

Multi-Camera People Tracking (MCPT) traditionally relies on precise intrinsic and extrinsic camera calibration to project 2D detections into a unified 3D world coordinate system.However, manual calibration constitutes a major bottleneck in large-scale dataset generation from unconstrained video archives. This work proposes a unified calibration-free 3D MCPT framework that infers geometric structure directly from visual data using deep foundation models. The system integrates anchor-free detection (YOLOX), robust tracking (BoT-SORT), omni-scale appearance embedding (OsNet), pose estimation (HRNet via MMPose), and transformer-based geometric reconstruction using the Visual Geometry Grounded Transformer (VGGT). A pose-guided 3D lifting strategy projects head keypoints onto a reconstructed manifold, eliminating dependence on ground-plane homography. Global identity association is formulated as hierarchical agglomerative clustering under a joint appearance-geometry cost with strict velocity gating. Evaluation on the AI City Challenge 2024 demonstrates a HOTA score of 53.13% without access to ground-truth calibration matrices, establishing a strong baseline for purely vision-based 3D tracking.

Standard methods for autonomous navigation in unstructured terrain are prone to myopic behaviors in long-horizon scenarios. The use of metric maps built from LiDAR or cameras provides necessary local geometry and semantic information but is strictly limited by depth sensing range. By discarding data beyond the mapping horizon robots suffer from suboptimal, short-sighted decisions. To recover this lost information, we focus on extracting long-range traversability-aware frontiers directly from first-person-view (FPV) images. By leveraging satellite imagery, we compute the set of feasible navigation paths for a dataset of image/pose pairs and use them to supervise our network, reducing the need for extensive human demonstration data. We demonstrate that this approach improves performance in long-range off-road navigation over existing methods by more than 10% in various offline benchmarks and reduces the number of human interventions incurred in a set of real-world experiments. More details can be found at https://theairlab.org/ss_frontiers_iros .

Throughput prediction is foundational for artificial intelligence-driven 6G resource orchestration. Conventional monolithic machine learning models struggle to generalize across diverse operators, mobility modes, and traffic types, leaving a critical stochasticity gap between signal conditions and achievable throughput. To overcome these constraints in heterogeneous urban environments, we propose a Tiered Multi-Agent System (TMAS) that dynamically routes edge telemetry to context-aware Domain Micro-Agents, validated on a dataset of 48,618 samples collected in Sunway City, Malaysia, with Nemo Handy drive test software, spanning three Tier-1 mobile network operators, three mobility modes, namely (i) elevated pedestrian walkway, (ii) ground-level shuttle bus, and (iii) elevated bus rapid transit; and three traffic profiles, namely (i) persistent download, (ii) persistent upload, and (iii) adaptive video streaming. Our evaluations reveal that TMAS overcomes predictability bottlenecks, achieving a coefficient of determination (R2) of up to 0.931 and a Mean Absolute Error (MAE) as low as 0.53 Mbps. The system demonstrates high operational efficiency, with rapid micro-agent training times, low inference latencies, and agentic routing overhead of 0.004 to 0.126 ms. These latency characteristics indicate the architecture is a promising candidate for the response times required by next-generation wireless networks.