让下一篇重要论文，不再错过。

Reconstructing full flow fields from sparse sensors requires prior assumptions about unmeasured regions and physical variables. Yet it remains unclear when learned models outperform classical estimators and which aspects of their predictions can be trusted. FlowReconBench evaluates ten learned and five classical methods on three regimes: a laminar cylinder wake across Reynolds numbers, two-dimensional Kolmogorov turbulence and a large-scale three-dimensional (3D) isotropic turbulence. Methods share leakage-controlled splits and sensor draws and are scored on per-channel error, ensemble spread, calibration, spectra and cost. The leading method changes for each regime. Classical methods perform strongly in low-order and dense-sensing regimes. On the cylinder wake, linear stochastic estimation and gappy proper orthogonal decomposition lead, including for unobserved pressure. In 3D, inverse-distance weighting matches the best learned methods on observed channels. Data-driven methods become superior at decreasing sensor density or poor sensor observability. On Kolmogorov flow, continuous ranked probability score and error yield different method rankings: generative models offer broader but underdispersed ensembles, while deterministic models prioritize pointwise error. Generative models balance this tradeoff through their sampler budget, with a larger budget improving ensemble quality at higher computational cost. In 3D, scaling tests demonstrate that queryable methods are flat in memory, while full-grid construction methods run out of memory. Observing only 2 of 4 fields leaves the problem kinematically underconstrained, yet a latent model can reproduce structural similarities to the ground truth.

Self-Driving Chemical Laboratories (SDCLs) are moving chemical experimentation toward embodied automation, where machines must perceive laboratory scenes, reason about experimental states, and act under physical, procedural, and safety constraints. Although Multimodal Large Language Models (MLLMs) are increasingly considered as embodied brains for such systems, existing laboratory benchmarks mainly focus on safety, anomaly detection, or general scientific understanding, leaving their execution-oriented embodied capabilities underexplored. To fill this gap, we introduce BEAKER, a Benchmark for evaluating Embodied Actionability, Knowledge, Experimentation, and Reasoning in SDCLs. BEAKER contains 1,000 expert-curated question-answer samples across 11 image and video task types, covering key judgments required for chemical laboratory execution, including affordance grounding, trajectory planning, equipment, state, and safety recognition, apparatus setup, operation and step reasoning, and temporal procedure reasoning. All questions and annotations are manually created and reviewed by chemistry and embodied Artificial Intelligence (AI) experts, without AI-assisted generation or annotation. We evaluate 28 general-purpose, science-oriented, chemistry-specialized, and embodied MLLMs in an offline, single-turn setting. Results show that current models can follow coarse experimental procedures in videos, but still struggle to ground actions into operable regions and feasible trajectories, to recognize fine-grained laboratory apparatus, states, and safety norms, and to order steps in mid-length procedures. BEAKER thus reveals a clear gap between coarse procedural understanding and the precise, action-grounded perception required for laboratory execution, providing a diagnostic benchmark for future MLLMs in SDCLs.

AI agents are playing an increasingly important role in physics research. However, existing physics benchmarks only evaluate fixed questions, isolated sub-tasks, or paper reproduction with given solutions, and rarely check research quality alongside correctness. We introduce FrontierPhysics, an end-to-end benchmark with 56 tasks made by 42 physicists based on their own research, covering nine domains across theoretical, computational, and experimental physics. Each task requires agents to review the literature, develop a research plan, conduct research and experiments, and produce structured outputs and scientific manuscripts. Combining deterministic verifiers with expert-authored rubrics, FrontierPhysics evaluates whether agents' research is correct and publishable. Across 22 models in 26 configurations, no configuration passes more than 46 of its 168 rollouts. Manual review of agent trajectories shows that frontier agents' main weaknesses are insufficiently rigorous reasoning and limited expert intuition, rather than gaps in physics knowledge or execution errors.

Humanoid robots have the potential to automate a wide range of physical tasks. Progress toward generalist humanoid autonomy, however, remains constrained by a data bottleneck: mapping pixels and free-form language to low-level joint commands requires paired supervision, and no corpus of such data exists at sufficiently large scale. Some approaches rely on human teleoperation and wearable capture devices, which require at least an hour of human time to produce an hour of data. We present HALO, a humanoid autonomy system powered by a pipeline that synthesizes vision-language-motion data across a thousand procedurally generated homes. The corpus scales with compute rather than human labor. HALO acquires a repertoire of physical skills, including sitting on chairs, navigating to named objects, stepping sideways through half-open doors, crouching and crawling beneath tables, and pushing boxes. It orchestrates these skills to solve composite, long-horizon tasks. Without ever seeing a real home during training, HALO transfers zero-shot to the physical world, achieving a 91% success rate across 360 trials in six unmapped real-world environments. See https://apple-aiml-research.github.io/ml-halo/ for code and videos.

We study $s$--$t$ reachability in an unweighted directed graph on $n$ vertices, accessed through a directed cut oracle: given $S\subseteq V$, the oracle returns the number of edges directed from $S$ to $V\setminus S$. Directed cut functions are submodular, and reachability asks whether the minimum $s$--$t$ cut has positive value. This connects the problem to the query complexity of submodular function minimisation. Whether or not reachability can be solved in truly subquadratic query complexity has been an outstanding open question for a decade. We give a simple algorithmic blueprint with two randomised implementations. The first uses $\widetilde O(n^{9/5})$ outgoing-cut queries; the second improves this bound to $\widetilde O(n^{5/3})$. The common idea is to construct an alternative orientation with the same underlying undirected graph and vertex-wise degree imbalances, thereby preserving reachability. We first approximate the target imbalances using an averaging and rounding procedure, then correct the remaining error with a flow. An earlier manuscript, made available in August 2026 in an online AI repository, reports an $\widetilde O(n^{3/2})$ query bound. Our contribution is a simple and comprehensible alternative approach that already achieves a polynomial saving over quadratic query complexity.

The introduction of generalist robot policies has enabled a single, large model to learn to perform a variety of tasks from a vast pre-training corpus. While these models often exhibit powerful zero-shot generalization capabilities, they typically require an adaptation phase to achieve sufficient performance in deployment. Iterated self-improvement via reinforcement learning (RL) has demonstrated promise in enabling this adaptation, yet such approaches have been largely explored in single-task settings - where the goal is to simply improve on a narrow deployment task - which lies in stark contrast to the multi-task capabilities of the base policy. In this work we ask whether generalist robot policies are capable of multi-task, generalist improvement in deployment - targeting many diverse tasks simultaneously - and what algorithmic recipe enables this. To answer this question, we first develop a set of structured evaluations to test generalist improvement capabilities, and systematically evaluate algorithmic and practical design choices regarding value estimation, policy extraction and resource allocation. We show that not only can generalist policies be improved online across diverse tasks, but that the right recipe can enable generalization and increase performance on tasks not considered during online training. We characterize when this generalization occurs and show that both the training task distribution and the use of value-based RL are critical. To the best of our knowledge, this is among the first evidence for online generalist improvement for robot foundation models.

Large language models (LLMs) achieve remarkable performance across a wide range of tasks, but their autoregressive decoding process incurs substantial inference costs due to inherently sequential token generation. Speculative decoding addresses this bottleneck by employing a lightweight draft model to propose multiple future tokens that are subsequently verified in parallel by a larger target model. Recent work has demonstrated that diffusion language models are well suited for this setting, as they can generate entire blocks of draft tokens in parallel and thereby alleviate the sequential constraints of autoregressive drafting. A subtlety of this regime is that block-diffusion drafters generate tokens bidirectionally within a block, whereas verification is performed by an autoregressive target model that evaluates tokens in a strictly left-to-right manner, leaving a gap between the symmetric training-time objective and the asymmetric verification-time reward. In this work, we offer an empirical analysis of three training-time interventions that narrow this gap: token positional weighting, a first-error focal loss that targets the position that breaks the accepted prefix within each block, and a chain loss term that substitutes a differentiable surrogate for the expected accepted length. The three interventions act along orthogonal axes (position, block-conditional first error, joint prefix) and compose additively; they are likewise orthogonal to test-time alignment mechanisms such as multi-draft self-selection, with which they can in principle be combined. Across four target models and six reasoning, code, and dialogue benchmarks, the three interventions raise accepted draft length by 21-76% per benchmark over a position-uniform baseline, without adding additional forward passes and without changing the inference pipeline or the rejection-sampling exactness contract.

JEPA-style world models learn action-conditioned latent dynamics without reconstructing observations, but distributional regularization alone does not ensure that their representations preserve information needed for control. We identify static collapse, a failure mode in which the encoder preserves episode-specific static content while suppressing manipulation-relevant state changes. Because static content is temporally predictable yet diverse across episodes, this failure can persist despite regularizers such as SIGReg. A controlled study on OGBench-Cube shows that introducing randomized backgrounds substantially degrades planning performance while leaving the underlying manipulation task unchanged. To address this problem, we propose motion-guided contrastive regularization. Our approach compares predicted latent transitions with transitions to candidate observations from the same episode, reducing the usefulness of static background identity for distinguishing action outcomes. Optical-flow similarities provide soft contrastive targets, allowing candidates with similar motion to receive similar supervision. Combined with latent prediction and SIGReg, our objective encourages representations to preserve within-episode state distinctions and similarities between related transitions. Our method improves planning success over LeWorldModel (LeWM) from 52% to 78% on OGBench-Cube with randomized backgrounds and from 14% to 54% on LIBERO-Object, while maintaining comparable performance on four other visual-control benchmarks.

Knowing that a pedestrian is occluded is useful to a robot even when the detector cannot recover the hidden pixels, but occlusion estimators are normally trained on occlusion annotations that deployment settings rarely have. We show that occlusion can be read off two distance estimates a camera-only pipeline already computes. Apparent height is largely unchanged by occlusion, because the detected box still spans the whole person; monocular metric depth is pulled toward the occluder, because the nearest surface inside the box is what a depth map reports. Only their ordering matters, so no focal length, stature, or depth scale is needed, provided the depth model's error is close to a pure gain, a condition that can be checked without labels. The score detects heavy occlusion on KITTI with AUC 0.909 (0.888 over all annotated pedestrians, including those the detector misses), requires no training and no occlusion labels, and is not a proxy for range: within fixed distance bands it holds AUC 0.894-0.925 while true distance alone sits near chance. On synthetic CARLA scenes with measured visibility it reaches 0.819, against 0.644 for distance alone. We arrived here after measuring three standard architectural responses to occlusion, depth fusion, occlusion-simulating augmentation, and attention, none of which improved detection outside its training distribution in the configurations we tested, and after finding that a detector trained on German roads loses half its accuracy on self-annotated street scenes in Lagos, Nigeria. Signals that need no local annotation are worth more in settings that benchmarks do not represent.

The Model Context Protocol (MCP) enables LLM agents to access external tools and data. Studying its software ecosystem requires connecting server interfaces, the projects that configure these servers, and their development activity. However, this information is scattered across directories, package registries, configuration files, and repository histories. We present MCP-Eco, a relational dataset that integrates these sources and links consumer configuration declarations to candidate server projects. Its frozen release contains 16,880,899 records across 19 Parquet tables, covering 78,302 candidate server projects, 16,165 candidate consuming repositories, and 9,200 configuration declarations. Of these declarations, 5,975 resolve to 5,138 distinct repository-server pairs. The dataset also includes tool, resource, and prompt descriptions, declared dependencies, and associated development records, including pull requests, reviews, issues, and commits. Provenance fields distinguish directory-reported capabilities from those observed through live probing and document discovery sources and declaration-matching methods. These connections support research on MCP interface design, configuration practices, and repository maintenance, while enabling practitioners to inspect tool schemas and existing integration configurations. The dataset and accompanying analysis scripts are publicly available at https://huggingface.co/datasets/mcp-research-alliance/mcp-ecosystem Demo video: https://www.youtube.com/watch?v=N7TqnNneSfU

We give a $0.556195$-competitive randomized algorithm for edge-weighted online bipartite matching with free disposal, improving the $0.5368$ guarantee of Blanc and Charikar. The result holds for arbitrary nonnegative edge weights and any input sequence fixed independently of the algorithm's randomness. Our algorithm builds on online correlated selection, introduced by Fahrbach, Huang, Tao, and Zadimoghaddam, and its multiway extension due to Blanc and Charikar. Our main contribution is a state-dependent primal--dual analysis of correlated selection. At each weight threshold, we track the state of the selection process jointly with an auxiliary failure event. The analysis accounts for arrivals below the threshold, which change the state without improving the matching value at that threshold. A potential function bounds the dual increase in both cases. We instantiate the analysis with an explicit win map that assigns a common score to an initial range of states. Its selection inequalities are verified by a finite computer-assisted proof covering every required candidate multiplicity and every real threshold; the verifiers are available in an accompanying repository. Triangular unit-weight inputs asymptotically attain the guarantee of the underlying ideal algorithm, proving that its analysis is tight.

Neural circuits must maintain functionality to drive effective behavior while their size, topology, geometry, and intrinsic dynamics change across development. To model developing visuomotor circuits and behavior, we investigated whether a single compact generative encoding could produce functional recurrent controllers across such changes. Building on the HyperNEAT algorithm, we represented this program as a compositional pattern-producing network that received developmental time as an input to generate age-specific connectivity. The developmental substrate prescribed neuronal birth, position, sensory organization, and intrinsic time constants. We tested this approach using two geometrically distinct developmental substrates and two visuomotor tasks: optomotor responses and phototaxis. Controllers optimized at only the initial or mature substrate generally failed when evaluated at other ages. In contrast, controllers optimized across multiple developmental snapshots maintained substantially higher and more consistent performance across trained and unseen ages. Optimization at only three developmental snapshots was often sufficient to produce effective behavior across the tested developmental interval. The resulting connectomes changed substantially with age and did not converge on a single trajectory of sparsity or connection-weight statistics. Controllers also differed in whether they relied on neurons born later in development. These results demonstrate that a shared spatiotemporal time-varying connectivity program can produce recurrent neural networks that preserve behavior across substantial developmental changes. Together, these results provide a framework for studying how functional stability can emerge without requiring structural or dynamical stability.

In nonuniform buy-at-bulk network design, we are given an undirected graph and $h$ terminal pairs with positive demands, and we must route every demand at minimum total cost when each network resource has two independent parameters: a fixed buying price paid once if the resource is used, and a per-unit rental cost (or physical length) paid proportionally to the traffic it carries. Unlike the uniform-cost or single-sink variants, the general multicommodity problem allows unrelated buying and rental metrics across arbitrary source--sink pairs, arbitrary demands, and both edge and node resources. We give a deterministic polynomial-time $O(\log^2 h / (\log\log h)^2)$-approximation algorithm for undirected nonuniform buy-at-bulk network design. The guarantee holds for edge costs, node costs, and their combination, and applies to arbitrary positive rational demands with no dependence on the number of vertices or the numerical demand ratio. This improves upon the $O(\log^4 h)$ bound of Chekuri, Hajiaghayi, Kortsarz, and Salavatipour (2010) for unrestricted instances. Our result also establishes the same $O(\log^2 h / (\log\log h)^2)$ upper bound on the integrality gap of the natural affine multicommodity flow LP, bounding integral buying and rental costs separately against their fractional counterparts and preserving zero rental budgets exactly.

We study the problem of sampling weighted partial triangulations of a convex polygon with $n+2$ sides. We consider the distribution $π_{n,λ}$ under which each partial triangulation $σ$ is assigned probability proportional to $λ^{|σ|}$, where $λ>0$ is a model parameter and $|σ| \in \{0,\dots,n-1\}$ denotes the number of diagonals in $σ$. This model belongs to a broad class of weighted geometric partition problems that include lattice triangulations and dyadic tilings, and is closely related to several classical combinatorial structures, including the full triangulations of a convex polygon and the associated Catalan structures. Our main result is a simple exact sampling algorithm for $π_{n,λ}$ with expected running time $O\big((\min\{n,n\sqrtλ\}+1)\log n\big)$, which is optimal up to the logarithmic factor.

The matroid prophet-secretary problem asks an online algorithm to select an independent set of elements whose nonnegative values are drawn independently and revealed in uniformly random order. Its combinatorial-auction counterpart asks the algorithm to allocate disjoint bundles to arriving buyers with independently drawn XOS valuation functions. In both problems the distributions are known, and the benchmark is the expected offline optimum. Ehsani, Hajiaghayi, Kesselheim, and Singla (SODA 2018) give $(1-1/e)$-competitive algorithms for both settings. In this work we show that these two guarantees have different limits. For every matroid, we give a randomized $(1-1/e+\varepsilon_0)$-competitive algorithm, where $\varepsilon_0=10^{-6}$. The guarantee holds for independent nonnegative values with finite expected optimum. For explicitly given finite distributions with rational values and probabilities, the algorithm has polynomial worst-case running time in the matroid independence-oracle model. The oracle tests whether a queried set is independent. The algorithm makes $O(N^4)$ such queries in expectation and $O(N^4\log(N+2))$ in the worst case, where $N$ is the number of elements. For combinatorial auctions with XOS valuations, however, we show that $1-1/e$ is the optimal competitive ratio. We give an explicit family of finite instances showing that no online algorithm can guarantee a larger competitive ratio than $1-1/e$, even when the buyers' valuations are independent and identically distributed, every additive clause has coefficients in $\{0,1\}$, and computation is unrestricted. Thus the matroid improvement exploits structure absent from general allocation with XOS valuations.

Preference-based reinforcement learning (PbRL) is the dominant framework for aligning AI systems to human preferences. However, evaluation protocols for such data were designed for text and have not been validated for speech. We present the first intraclass correlation coefficient (ICC)-based, controlled cross-modal study of human and synthetic preference annotations, comparing text and audio evaluations of identical semantic content across 100 prompts. We show that achieving \textit{good} (audio) to \textit{near good} (text) agreement within either modality (ICC(2,$k$) $\approx$ .81 audio, .74 text) requires $\sim$9 raters and modalities show marked differences in how people report preferences: audio raters exhibit narrower decision thresholds, reduced length bias, and more user-oriented evaluation criteria, with near-chance cross-modality agreement. We demonstrate that synthetic ratings can be used to effectively predict inter-rater agreement, thus serving as an early signal for stimulus selection and proxy for human annotations. Together, these findings argue that evaluation protocols for audio preference data require modality-specific design rather than direct adaptation from text. Code, data, and the audio corpus are available at: https://huggingface.co/datasets/sciminds/same-words-different-judgements

Conventional robot arms can be extremely heavy compared with the everyday objects they manipulate, creating a significant inertia mismatch at contact. Even a small accidental bump from a heavy arm can knock a light object out of place. Modern learning methods have nevertheless demonstrated a wide range of successful manipulation behaviors on these platforms, suggesting that even extreme inertia mismatch can be overcome with sufficient data. However, it remains unclear whether high inertia imposes a hidden cost on learning, potentially worsening scaling with data or lowering the performance ceiling of modern robot learning methods. We investigate this question through controlled simulation experiments that vary robot and object masses. We find that reinforcement learning succeeds across a broad range of mass combinations, while behavior cloning learns more reliable policies when a lighter robot manipulates a heavier object. Heavier robots require more demonstrations to attain the same performance as lighter robots. Finally, because new hardware is rarely an option, we explore ways to lower an existing arm's inertia at contact with existing hardware, either by choosing a lower-inertia workspace before collecting data or by steering the demonstrator toward lower-inertia configurations during the task. In both cases, the lower-inertia demonstrations are imitated more reliably. Project website: https://younghyopark.me/inertia-mismatch/

For many computer vision tasks, neural networks can be trained to produce a low average error, yet they still fail on seemingly simple scenes. Reducing these failures requires first finding them, but they may not be in a fixed dataset. We study procedural adversarial learning (PAL), a framework of minimax training and adversarial evaluation which searches the input space of a procedural generator for difficult instances. The procedural generator is an interpretable program mapping a low-dimensional vector of control parameters (e.g. layout, lighting, pose) to a rendered image and its label. We introduce the Simple-PAT algorithm, which uses zeroth-order optimization in the procedural generator's parameter space to propose adversarial training samples that are generated on demand. We also create PAL-Dojo, a collection of efficient procedural generators for surface normal estimation, image segmentation, and human pose estimation. Against a cross-model black-box adversary with 50M aggregate queries, Simple-PAT reduces worst-case error by a geometric mean of 3.15x compared to standard training and 2.63x compared to the strongest robust training baseline. Code is available at https://github.com/princeton-vl/procedural-adversarial-learning.

In recent years, generative artificial intelligence (GenAI) has demonstrated remarkable capabilities in high-stakes domains such as molecular science. However, challenges related to the verifiability and structural privacy of its outputs remain largely unresolved. This paper focuses on the task of molecular toxicity repair. It proposes a structure-private verification framework - ToxiEval-ZKP - which, for the first time, introduces zero-knowledge proof (ZKP) mechanisms into the evaluation process of this task. The system enables model developers to demonstrate to external verifiers that the generated molecules meet multidimensional toxicity repair criteria, without revealing the molecular structures themselves. To this end, we design a general-purpose circuit compatible with both classification and regression tasks, incorporating evaluation logic, Poseidon-based commitment hashing, and a nullifier-based replay prevention mechanism to build a complete end-to-end ZK verification system. Experimental results demonstrate that ToxiEval-ZKP facilitates adequate validation under complete structural invisibility, offering strong circuit efficiency, security, and adaptability, thereby opening up a novel paradigm for trustworthy evaluation in generative scientific tasks.

Automation is often justified as relief from dull, dirty, and dangerous work. I examine how these conditions relate to occupational AI exposure using 21 O*NET items across 754 US occupations. Higher exposure is associated with lower condition scores under a large language model (LLM) measure and AI Occupational Exposure (AIOE), with equal occupation weights and employment weights. Adjustment for physical demands, required education, training and experience, and wages reduces the composite association. The adjusted confidence intervals include zero for LLM exposure and remain below zero for AIOE. Separating repetition from restricted discretion also changes what the combined Dull score conveys. These comparisons show how item groupings and occupational characteristics shape the interpretation of exposure estimates. Occupational profiles offer a starting point for selecting contrasting research settings. Establishing desired automation or realized relief requires evidence about workers' preferences and specific interventions.

This paper presents GSCV++, a lightweight pipeline for 3D {G}aussian {S}platting (GS) sequences {C}ompression with standard {V}ideo codecs. To meet the requirements of low-complexity and hardware compatibility from the industry, GSCV++ jointly improves preprocessing, 3D-to-2D mapping, and practical video compression configuration of GS compression. First, for preprocessing, energy-adaptive inter-frame spherical harmonic (SH) alternative current (AC) dimensionality reduction (EA-SHDR) is proposed to produces a compact and stable temporal SH AC feature space. It can reduce the data volume of following mapping and practical compression, as well as less complexity while eliminating redundant information. Second, for 3D-to-2D mapping, prior-based Inter-MiniPLAS (P-MiniPLAS) is designed to generate smooth 2D feature maps through prior-based weighting factor inference and small scale remapping. Compared with vanilla Parallel Linear Assignment Sorting (PLAS) and Morton scan, P-MiniPLAS ensures the generated 2D maps are more suitable for the video codec while maintaining a low level of computational complexity. Third, for practical compression, content-aware generalized compression (CA-GC) is developed to use a non-uniform bit-depth split for coordinate map generation, and a coding unit size selection is introduced for efficient compression complexity control, which fully exploits the performance of video codecs without involving normative changes. Experiments demonstrate that GSCV++ reports over 20\% in intra- and 60\% in inter-prediction rate-distortion gains compared with state-of-the-art (SOTA) methods. GSCV++ also achieves faster 2D map generation, encoding, and decoding than other SOTA methods using the same type of video codecs. Ablation studies verify the effectiveness and robustness of the proposed modules and provide insights for subsequent research.

For robots to operate reliably in commercial and industrial applications, they must persistently perform specific tasks with known variations in object shape and pose. We call this Variational Automation (VA) to differentiate these settings from fixed automation. Inspired by recent papers on Agentic Robotics, where pretrained LLM and VLM coding agents combine interpretable robot programming with the open-world adaptability of model free policies, we propose a general set of agentic robotics benchmark design criteria that includes accessibility, repeatability, diversity, relevance to agentic robotics and practical applications, physical realizability, resistance to benchmark saturation, and computational efficiency. We instantiate these principles in six manipulation task classes spanning industrial, medical, and infrastructure applications: tool sorting, tool hanging, gear meshing, syringe packing, cable insertion, and cable routing. We introduce the Variational Automation Benchmark for Agentic Robotics (VABAR), an open, easily replicable, simulation-based manipulation benchmark to systematically evaluating agentic robotics systems. Built fully on open-source tools, VABAR features detailed implementations using the Newton physics engine, standardized task variations, difficulty tiers, success metrics, and a library of 33 generalizable skills with human-authored programmatic reference solutions. We provide initial baseline evaluations using an open agentic manipulation harness, Graph-as-Policy (GaP), and Isaac Lab Arena.

Toxicity remains a leading cause of early-stage drug development failure. Despite advances in molecular design and property prediction, the task of molecular toxicity repair, generating structurally valid molecular alternatives with reduced toxicity, has not yet been systematically defined or benchmarked. To fill this gap, we introduce ToxiMol, the first benchmark task for general-purpose Multimodal Large Language Models (MLLMs) focused on molecular toxicity repair. We construct a standardized dataset covering 11 primary tasks and 660 representative toxic molecules spanning diverse mechanisms and granularities. We design a prompt annotation pipeline with mechanism-aware and task-adaptive capabilities, informed by expert toxicological knowledge. In parallel, we propose an automated evaluation framework, ToxiEval, which integrates toxicity endpoint prediction, synthetic accessibility, drug-likeness, and structural similarity into a high-throughput evaluation chain for repair success. We systematically assess 43 mainstream general-purpose MLLMs and conduct multiple ablation studies to analyze key issues, including evaluation metrics, candidate diversity, and failure attribution. Experimental results show that although current MLLMs still face significant challenges on this task, they begin to demonstrate promising capabilities in toxicity understanding, semantic constraint adherence, and structure-aware editing.

The best classical optimizer for a continuous black-box problem depends on its budget and landscape. Existing routers decide from the dimension and budget, past improvement or features fitted to one benchmark, and few test an optimizer's implicit assumptions online. AMM (Adaptive Multi Mode) routes a known budget among quasi-Newton, trust-region, coordinate, multistart and evolution-strategy optimization engines with online probes of curvature, plateaus, separability, kinks, basins and fractal structure. Each probe has a default, a dimension-by-budget validity range and a cost charged to the budget. In its pre-registered development loop on bbob, 32 of 36 predictions held over the last 16 confirmations. AMM was then tested once on held-out bbob instances 101-110 (D=2-40, 10*D-1000*D) against up to seven competitors. It has the highest target share in 382 of 600 function-dimension-budget cells (236 outright, 146 tied) and, by a descriptive posterior rule, is credibly behind in 35, mostly at 10*D and 30*D. At every budget it also leads the controls built from its own engines (the best engine alone, the best engine per dimension and budget, and a greedy schedule), narrowly at 10*D and 30*D, and nevergrad's NgIohTuned. In pre-registered runs its lead over IPOP-CMA-ES holds under affine and box transformations, on box-constrained bbob and, pooled, on rotated f2-f4, but rotating the separable f3 and f4 removes most of the lead there. On held-out MA-BBOB its final share at 2000*D is level with IPOP-CMA-ES's and its anytime area lower. We published AMM as an open-source Python package (pip install amm-optimizer; https://github.com/BjBodner/amm-optimizer).

Decentralized air traffic management systems offer a scalable alternative to centralized control, but often assume high levels of cooperation. In practice, such assumptions frequently break down since agents, each representing an airspace sector, may operate independently and prioritize local objectives. We address the problem of sector overload in decentralized air traffic management by proposing a regulated decentralized protocol that models self-interested behaviors based on best response dynamics. Each agent adjusts the departure times of its assigned flights to reduce its own congestion, without requiring centralized joint optimization. A tunable cooperativeness factor models the degree to which each agent accounts for overload in other sectors, while a minimal admissibility rule prevents local updates from creating new overloads. We show that this regulatory restriction is sufficient to guarantee finite-time convergence of best response dynamics to a pure Nash equilibrium under partial cooperation. In addition, we identify a sufficient condition under which an overload-free solution corresponds to a global minimizer of the potential function. Numerical experiments using one month of European flight data demonstrate that the proposed algorithm substantially reduces overload even with only minimal cooperation, achieving performance close to a centralized global mixed-integer optimizer and exceeding a centralized first-come-first-served baseline while requiring substantially less computation than centralized optimization. We further evaluate departure delay and fairness to quantify the operational cost of overload mitigation.

LLM agents use context compaction to manage growing interaction histories, but summarizing long histories with large models can introduce substantial delays. Compaction therefore requires balancing information retention against latency. We observe that structured summary slots can retain information when generated independently. Based on this observation, we present SpecCompact, a framework that accelerates compaction through slot-parallel semantic speculation. SpecCompact fine-tunes a small drafter and generates slots in parallel. The target model verifies each proposed line and repairs rejected content, while subsequent drafting uses the updated slot prefix. System optimizations further reduce repeated context processing and model calls. Across AppWorld and $τ^3$ benchmarks with two target models, SpecCompact achieves $2.04$--$5.63\times$ compaction speedups over Hermes-style summarization. Separate downstream evaluations reveal model- and task-dependent performance trade-offs. A user study within Hermes further shows an $8.68\times$ median compaction speedup.

General-purpose generative AI (GenAI) models are being rapidly adopted in healthcare, but they are challenging to assess with traditional evaluation frameworks. These conceptual, methodological, and practical challenges parallel decades of work in evaluating clinician and health system quality and safety. We describe the adaptation of methods from several fields, combined with emerging technical approaches, into a structured, multi-method evaluation framework designed to give well-rounded assessments of GenAI in health at scale. The approach first anchors evaluation to Critical User Journeys (CUJs) to help prioritize out of a large choice space, and maps these to a phased AI system lifecycle (base model development, product development, and post-deployment monitoring), since evaluation at each stage requires different methodological approaches. In this context, the approach then integrates three distinct evaluation methods (closed-question benchmarks, LLM-as-a-judge autoraters, and expert human review) across three core domains: accuracy, safety, and usefulness. Taken together, this approach provides a strategic framework for bridging the gap between benchmarking results and performance in the real world with the goal of supporting decision-making and accountability across development, procurement, and deployment for product teams, health systems, and regulators.

Error correcting codes are a fundamental component of communication systems, enabling reliable data transmission over noisy channels. Recently, neural decoders have demonstrated notable performance gains over classical iterative algorithms. In this paper, we propose a Generalized Belief Propagation Network (GBPNet) that preserves message-passing symmetry while enhancing the decoder's learning capability. The architecture uses cascaded variable-node updates and learned element-wise message scaling while retaining the Tanner graph structure. We also introduce two training strategies, progressive training and high-SNR training, that improve decoding accuracy. Experimental results on several linear codes show that GBPNet achieves lower bit error rates than conventional belief propagation and the evaluated state-of-the-art neural decoders.