arXiv AI

arXiv:2602.04943v5 Announce Type: replace-cross Abstract: We study Heisenberg antiferromagnets through a graph-theoretic representation of their Hamiltonians. In the computational basis of a fixed-magnetization sector, the Heisenberg Hamiltonian equals a constant minus the weighted Laplacian of a graph whose vertices are spin configurations and whose edges connect configurations related by exchanging two antiparallel spins on a lattice bond. We call this graph the Hilbert graph (HG) which is isomorphic to the token graph of the lattice over which the Hamiltonian is defined. The exact ground-state energy is then determined by the largest eigenvalue of the HG Laplacian, which is the spectral relaxation of weighted Max-Cut on the HG. With the amplitudes fixed, the phase-dependent part of the variational energy defines an antiferromagnetic classical XY model on the HG, with couplings set by the amplitudes. Restricting the variational state to be real, i.e., restricting its phases to $\{0,\pi\}$, reduces the fixed-amplitude energy minimization to solving an antiferromagnetic Ising model and hence a weighted Max-Cut on the HG. When the weights are generated from non-degenerate ground-state amplitudes, the optimal phases give the ground-state sign structure which can be recovered from the weights in time polynomial in the size of the HG. On the Hamiltonian side, a diagonal sign transformation removes all positive off-diagonal matrix elements if and only if the HG is bipartite, which reproduces the Marshall sign rule on bipartite lattices through the graph two-coloring problem; otherwise, the minimal remaining positive weight equals the sum of HG edge weights left uncut by the Max-Cut. This graph formulation establishes a common framework for understanding wave function sign structure, Hamiltonian stoquasticity, non-convexity of phase optimization in variational Monte Carlo, and the average sign in quantum Monte Carlo.

arXiv:2610.25043v3 Announce Type: replace Abstract: Flow-matching vision-language-action (VLA) models generate an action chunk by iteratively denoising Gaussian noise, but typically execute only a short prefix before replanning with updated observations. Under this receding-horizon paradigm, the unexecuted remainder---the action tail---is discarded, and the next chunk is regenerated from fresh noise. We show that this discarded tail retains transferable denoising progress: action-tail initialization can match or outperform a native 10-step Gaussian baseline using fewer denoising steps. However, the optimal denoising budget varies substantially across samples, indicating that tail reuse should be adapted to the updated environment. Based on this observation, we introduce VLA-Rolling, a lightweight inference framework that reuses action tails through three stages: action-tail inheritance, per-action confidence estimation, and confidence-guided refinement through renoising and denoising budget allocation, while the underlying VLA remains frozen. Across $\pi_{0.5}$, SmolVLA, X-VLA, and MolmoAct2 on LIBERO, MetaWorld, LIBERO-Plus, and RoboTwin 2.0, VLA-Rolling reduces action-chunk inference cost in all 16 model--benchmark pairs, achieving up to a $1.48\times$ speedup, while improving success rate in 14 pairs by up to $15.08$ percentage points. These results show that action tails are not merely discarded predictions, but reusable intermediate states that enable more efficient and accurate VLA inference. These results demonstrate that the action tail can support the generation of better actions with fewer denoising steps. Our project is available at https://chenbao123ww.github.io/VLA-Rolling/.

arXiv:2610.16975v3 Announce Type: replace Abstract: Drug discovery remains a resource-intensive and time-consuming process, involving billions of dollars and a decade of development to advance a drug to market. While many in silico tools have accelerated this process, operating them still demands substantial time, effort, and expertise from medicinal chemists. Autonomous systems built on Large Language Models (LLMs) have emerged as a promising solution, yet current designs limit their performance. Existing single-agent systems scale poorly to long-horizon, multi-step, and realistic tasks, whereas multi-agent systems typically execute predefined workflows that cannot capture the iterative, non-linear nature of a real drug discovery campaign. Here, we present MADDIE, a multi-agent drug discovery engine. It comprises a central agent, Orchestrator, and four specialized worker agents: HitIdentifier, LeadOptimizer, Synthesizer, and Evaluator, each representing a critical step in a drug discovery campaign. Under Orchestrator's orchestration and coordination, these worker agents are composed into flexible workflows, enabling MADDIE to adapt its strategy and navigate the drug discovery pipeline end-to-end. Across 50 protein targets, MADDIE produces molecules satisfying key property requirements and their synthesis routes, outperforming existing agentic systems, generative models, and general-purpose LLMs by a wide margin. Our analysis reveals how these agents collaborate and that MADDIE can employ different strategies across targets to achieve the campaign's goal, while still being efficient in time and tokens. Together, they demonstrate MADDIE as a low-cost, effective, and efficient autonomous engine for accelerating drug discovery. Code and dataset is available via https://github.com/ninglab/MADDIE.

arXiv:2610.28356v2 Announce Type: replace-cross Abstract: Object counting in videos remains a poorly characterized capability of multimodal large language models. Counting questions are included in many existing VideoQA benchmarks, but the ground-truth count distributions in these benchmarks are heavily skewed toward small values. Across the nine benchmarks we survey, the median ground-truth count is at most five, and the three most frequent values together account for between 45% and 93% of the videos. The resulting mean accuracy is then dominated by the most frequent counts; a value-dependent bias at a rare count contributes negligibly to the average and remains invisible. We introduce CountVideoBench, a benchmark of 2,600 synthetic videos covering 26 cardinalities in the interval [5, 50] (100 videos each), grouped into six clusters of consecutive counts that span the range while enabling near-neighbor comparisons. Each video contains a single class of static objects under a controlled camera motion, removing object motion and reducing recognition as confounds. We evaluate sixteen video-language models from nine architecture families in a zero-shot setting. No model exceeds 27.6% Exact Match. The dependence of accuracy on cardinality varies across models, ranging from monotonic decline to a non-monotonic peak-and-collapse pattern, which rules out increasing difficulty with cardinality as the dominant explanation of counting failure. Every model further concentrates its predictions on its own set of preferred integers, with accuracy peaks coinciding with these values and collapsing at adjacent counts. These findings highlight the need for balanced, diagnostic counting benchmarks to reliably assess this fundamental visual capability.

arXiv:2610.28351v2 Announce Type: replace-cross Abstract: Reconstructing dynamic 3D scenes from monocular video requires inferring motion from noisy and intermittently visible observations. Long-range tracks provide valuable geometric constraints, but integrating their fragmented temporal coverage into shared, continuous motion remains challenging. We introduce RayCo4D, a ray-conditioned continuous motion model for monocular 4D reconstruction that explicitly separates visual measurements from latent 3D motion states. Each track is associated with a reference-time 3D query constrained to its camera ray, and its image and depth observations constrain shared latent motion nodes through local many-to-many associations. Each node maintains an $\mathrm{SE}(3)$ pose and body-frame velocity at sparse support times. A white-noise-on-acceleration process prior couples neighboring states and defines continuous-time interpolation, allowing observations across visibility intervals to jointly constrain the same latent state sequence. The inferred shared motion is transferred to Gaussian primitives through dual-quaternion blending, while reference-anchored local $\mathrm{SE}(3)$ residuals capture fine-scale non-rigid deformation beyond the shared scaffold. Experiments on diverse monocular dynamic scenes show that RayCo4D achieves competitive novel-view synthesis quality, improves structural and temporal consistency under rapid motion and incomplete tracks, and supports continuous-time rendering.

arXiv:2610.27264v2 Announce Type: replace-cross Abstract: This paper is an exposition of the theorem prover Arend developed at JetBrains Research. Arend language has been designed to facilitate the formalization of mathematics within the framework of univalent foundations and with the focus on constructive mathematics. It is based on a variant of homotopy type theory with cubical syntax that is more closely aligned with Martin-L\"of Type Theory (MLTT) than fully computational cubical type theories, while still retaining some of their computational properties useful in practice. Among the most notable features of the Arend language is its powerful system of classes and records supporting subsumptive subtyping, partial implementations and anonymous extensions, which provides extensive flexibility for constructing hierarchies of definitions. Formalization in Arend is streamlined by the IntelliJ Arend plugin, which transforms IntelliJ IDEA into a full-fledged integrated development environment (IDE) for the Arend language. The main Arend library arend-lib includes formalizations in constructive algebra, topology and synthetic homotopy theory.

arXiv:2610.26950v2 Announce Type: replace-cross Abstract: Multi-teacher on-policy distillation (MOPD) integrates domain specialists into a shared student, but determining how strongly each teacher should supervise remains challenging. Existing discrepancy-based allocation can assign strong supervision even when the student already matches or exceeds the teacher's task performance, since behavioral mismatch does not necessarily imply a remaining capability deficit. We propose Capability-Aware Multi-Teacher On-Policy Distillation (CA-MOPD), which combines specialist merging with capability-guided allocation to account for what the student has already learned. CA-MOPD first merges reinforcement-learning specialists into a strong student initialization, then uses verifier-estimated teacher--student capability gaps to adjust domain-level distillation strength. Supervision decreases as capability gaps close and increases when estimated student capability regresses, while dense token-level guidance remains provided by the teachers. Across six benchmarks spanning mathematics, code generation, and instruction following, CA-MOPD achieves an average score of 32.22, outperforming naive MOPD, Open-MOPD, and the merged initialization by 0.86, 0.83, and 0.74 points, respectively. Controlled comparisons further support the benefits of merged initialization and capability-gap guidance under matched training budgets.

arXiv:2610.27888v2 Announce Type: replace Abstract: Approximate solutions of partial differential equations (PDEs) on unstructured grids can be represented on a graph. Numerical optimization involving stiff evolutionary and static PDEs often requires solving a large system of equations, which can be treated as a constraint. In this work, we present a fully differentiable graph-based implicit solver that incorporates this constraint. We evaluate its performance across four key tasks: a) linear and nonlinear forward modeling of evolutionary and static problems, b) solving inverse problems to estimate equation coefficients, c) solving inverse problems to estimate the right-hand side, and d) learnable graph coarsening to accelerate forward modeling. The stability and differentiability of our solver enable significant reductions in the complexity of forward modeling while efficiently addressing related inverse problems. These capabilities make it a powerful tool for different physics and engineering applications, in particular for geophysics, where inverse problems are commonly solved in order to reduce the model uncertainty.

arXiv:2610.27548v2 Announce Type: replace Abstract: When an LLM agent acts on behalf of a user, it is expected to act within the authorization scope the user grants. Existing agent evaluations largely measure task completion or harmful consequences and can therefore overlook actions that violate this delegation without producing conventional safety or privacy harms. We introduce AuthorizationBench, a benchmark of authorization alignment grounded in documented real-world cases. A scalable construction pipeline produces 286 executable tasks spanning situational triggers, the presence or absence of direct harmful consequences, and ten application domains. We execute every task with four models at two reasoning-effort settings across three agent harnesses in an authorization-aware sandbox that keeps authorized and out-of-authorization paths executable and observable, yielding 6,864 trajectories. Agents act out of authorization in 19.2% of trajectories, with rates ranging from 10.5% to 26.6% across the 24 configurations. Task completion does not imply authorization. Increasing reasoning effort leaves the aggregate rate nearly unchanged, with effects varying across models. On controlled pairs, agents act out of authorization at similar rates with (17.9%) and without (20.8%) direct harmful consequences, and more often under benign pressures than malicious injections (23.5% versus 17.6%, p=0.002). Our results show that task capability, additional reasoning, and consequence-oriented safety evaluation do not by themselves ensure authorization alignment. Moreover, agents that consult the principal before completing a task exhibit lower rates of out-of-authorization behavior (14.0% versus 21.6%, p<0.001), pointing to a tension between agent autonomy and preserving users' decision authority that calls for further human-centered study. Dataset and code are available at https://github.com/PEACH-Research-Lab/AuthorizationBench .

arXiv:2610.27307v2 Announce Type: replace Abstract: For AI assistants to move beyond simple chat interfaces and reliably assist users with applications like Gmail, Venmo, and Slack, we need to improve their tool-use capabilities. However, existing tool use benchmarks are still limited and difficult to scale because they rely on human supervision or are too domain-specific. To make data generation scalable, we propose, TURTLE (Tool Use Related Tasks with Long-Horizon Evolution), an Unsupervised Environment Design (UED) approach to evolve existing tasks using a proposer, a solver, and a feedback generator large language model agents. The proposer is rewarded for difficult yet solvable tasks based on the solver's empirical performance, and the feedback generator summarizes the solver's execution traces for the proposer to exploit. TURTLE produces evolving, self-tuning test suites adaptable to different environment requirements, from supporting user simulators and dense document retrieval to interacting across multiple apps. Empirical results on AppWorld, $\tau$-Bench, and AutomationBench using Gemma 4 31B-it show that the evolved tasks target the desired difficulty range (e.g., a 165% increase in the percentage of hard tasks on AppWorld), increase task diversity (in terms of reasoning and simultaneous tool interactions), and elicit a broader range of failure modes than the original tasks.

arXiv:2610.27746v2 Announce Type: cross Abstract: Simulating economic responses at society scale requires agents whose decisions reflect household circumstances and the effects of earlier actions. We introduce S$^2$-MAS, a society-scale multi-agent simulation framework built on 500 million synthetic household personas grounded in real-survey data. Its Genese engine separates decisions from state updates, while reusable financial scenarios and application ledgers track consumption, cash, debt and payments. Sharp-421m-mlx, a compact decision model trained with SFT + RLCD on 2.93 million examples, achieves 74.55% accuracy and 38.37% question-macro F1 in consumer financial-choice scenarios, outperforming Jev 1.13 and GLM-5.3-Flash on both measures. We evaluate eight financial task families and simulate 12 million distinct household agents in paired purchase-funding conditions. Jointly raising purchase goals and approved credit limits increases consumption, with responses differing across age and income groups. Education, employment and household-size differences persist after age--income standardization and mainly reflect transitions from deferral to purchase. Asset and debt groups differ in cash drawdown, repayment and closing debt. A 24-month panel varies purchase goals under a common credit product, with repayment and arrears updating subsequent offers. S$^2$-MAS links heterogeneous household decisions to evolving consumption, cash and repayment paths, supporting economic experiments across household groups, population scales and time horizons.

arXiv:2610.26847v2 Announce Type: replace-cross Abstract: Long-horizon agents must learn heterogeneous capabilities from interleaved trajectories. Updating shared parameters to learn new capabilities can degrade previously acquired ones, resulting in catastrophic forgetting. As a trajectory unfolds, different stages may require different capabilities, yet conventional joint training and static adapter merging maintain a fixed parameter configuration throughout execution. We introduce WeAct (Weight-level Internal Actions), which trains independent capability-specific LoRA adapters over a frozen backbone and adds adapter selection to the agent's action space. These internal actions use the model's native tool-calling interface for on-demand capability composition in a shared context. Across eight deep-research benchmarks, Qwen3-32B with WeAct improves average accuracy by 6.2% relative to full fine-tuning counterparts despite using less compute, and by 27.5% relative to the strongest static LoRA-merging method. WeAct also supports modular continual adaptation, by adding a new code computation adapter to expand the agent's capabilities and updating the existing writing adapter to improve report quality. Both updates leave the backbone and other adapters unchanged, supporting modular continual adaptation in agents.

arXiv:2610.26443v2 Announce Type: replace-cross Abstract: Fine-tuning large language models (LLMs) on downstream tasks often weakens their previously aligned safety behavior, creating an inherent trade-off between task adaptation and safety preservation. Existing approaches attempt to mitigate this issue by identifying safety-relevant neurons, layers, or update directions in the original parameter space. However, safety-related information is often distributed across many directions in this space, causing downstream updates to overwrite parameters that encode safety behavior. We propose WSR-Tune, a Weight Space Reparameterization-based fine-tuning framework that preserves safety during downstream adaptation. Our approach constructs a safety-conditioned basis and reparameterizes the weight matrices such that safety-relevant information becomes concentrated in a small subset of directions. We then identify safety-critical directions and freeze them in the reparameterized space, while updating the remaining complementary directions for downstream adaptation. By explicitly structuring the parameter space to disentangle safety and task information, our method reduces interference between objectives and enables simultaneous preservation of safety and improvement in downstream performance. Experimental results show that our method achieves a more favorable trade-off between downstream performance and safety retention, demonstrating its effectiveness for reliable LLM fine-tuning.

arXiv:2610.26025v2 Announce Type: replace-cross Abstract: Diffusion Transformers (DiTs) deliver high-fidelity image and video generation, but inference requires many sequential model evaluations. Two acceleration strategies are increasingly important: model compression makes each evaluation cheaper, while adaptive inference avoids selected teacher computation through reuse, forecasting, or speculative execution. Their combination, however, is brittle: directly applying the evaluated adaptive methods to a compressed student can degrade quality, an observed failure mode we call the \textbf{Combination Gap}. We link this gap to a mismatch between pointwise distillation and short-horizon execution: a student trained at teacher states need not remain reliable when its own predictions are chained. We propose \textbf{TamedFlow}, which trains a compressed DiT for this deployed role through cross-architecture feature alignment, a near-identity Velocity Alignment Head, and randomized rollout supervision. At inference, a lightweight Learnable Trajectory Estimator routes completed drafts: accepted drafts bypass the teacher, while rejected drafts roll back and receive one teacher rescue step. Distilling DiT-XL/2 into DiT-B/2, TamedFlow reaches FID $2.58$ at $2.25\times$ measured speedup over DDIM-50 on ImageNet $256\times256$. Ablations support trajectory supervision, and routing controls favor LTE over random decisions at nearly matched latency. Evaluations on ImageNet $512\times512$, MS-COCO, and Latte/FaceForensics extend the empirical scope.

arXiv:2610.25946v2 Announce Type: replace-cross Abstract: Developing coordination policies for complex multi-agent systems relies on either labor-intensive algorithm design or opaque task-specific reinforcement learning. With recent advances in autonomous coding agents, we show that policy search directly in code space offers a compelling third path that combines automated optimization with explicit interpretability. We investigate a human-directed workflow in which coding agents iteratively propose, implement, evaluate, diagnose, and eventually refine algorithms guided by simulation feedback and explicit correctness verification. We conducted two case studies and found that this workflow robustly outperformed any manually engineered solutions. On a challenging map in the 2024 League of Robot Runners competition, a two-day search discovered a policy that exceeds the stronger locally reproduced competition entry by 35.0% on the densest instance and generalizes to unseen map instances. In simulated real-world warehouses with irregular lanes, continuous robot geometry, and asynchronous motion, a week-long search discovered an entirely new class of multi-agent pathfinding algorithm that outperforms a calibrated proprietary solution in throughput by 58.9%. Under stated assumptions, we further prove that the new algorithm is collision-free and completes, in finite time, every accepted goal that is not withdrawn or replaced. Together, the studies show that policy search in code space powered by state-of-the-art coding agents offers a highly competitive path to building real engineering solutions that are both effective and analytically tractable.

arXiv:2610.25916v2 Announce Type: replace-cross Abstract: As coding models and agent harnesses become more capable, reliable security verification is becoming a central bottleneck. Improving secure code generation requires a signal whose reported progress remains aligned with actual program behavior under optimization; otherwise, an optimizer can improve the signal's verdict without removing the underlying vulnerability. Existing model-based approaches require models to either infer program behavior from source code or specify correct outcomes for adversarial tests, placing substantial reasoning demands on the security signal. We introduce \falcon{}, a counterexample-grounded verification framework that separates attack exploration from behavioral verification and connects them through execution traces of the program under test. In test-time repair, \falcon{} yields substantially stronger held-out functional-security gains than alternative security signals across secure code generation benchmarks, while preserving or improving functionality. As an RL reward, \falcon{} also outperforms static-analysis and learned rewards on held-out functional-security, even when all policies successfully optimize their respective training rewards. Combining \falcon{} with either proxy reward further improves held-out performance, suggesting that execution-grounded feedback can mitigate reward overoptimization while preserving useful guidance from existing security signals.

arXiv:2610.25481v2 Announce Type: replace-cross Abstract: Spatiotemporal forecasting of 3D anatomical changes is a critical generative vision challenge for modeling Alzheimer's Disease (AD) progression. While brain MRI forecasting from single-modality data has advanced, other key complementary multimodal biomarkers remain underutilized. In this work, we propose the Multimodal-Conditioned Latent Diffusion Model (MC-LDM), a novel framework for patient-specific brain MRI synthesis. MC-LDM leverages multimodal biomarkers---MRI, tau-PET, Clinical Dementia Rating (CDR), and APOE4---during training, but relies only on baseline MRI, APOE4, and patient metadata at inference, reflecting realistic clinical availability. Our contributions are threefold: (1) a Latent Diffusion Model (LDM) fine-tuned via Low-Rank Adaptation (LoRA) for data-efficient learning; (2) a multimodal conditioning that integrates molecular and clinical signals to model heterogeneous disease trajectories; and (3) auxiliary predictors estimating unobserved multimodal biomarkers from MRI features and patient covariates to condition the diffusion model, removing the need for these assessments at inference. Trained on 1,355 visits from 852 subjects in the Alzheimer's Disease Neuroimaging Initiative (ADNI), MC-LDM reduces average regional volumetric MAE by 18% over the second-best baseline on an independent test set of 664 visits. To our knowledge, MC-LDM represents the first diffusion-based framework to leverage multimodal priors for MRI forecasting. This conceptual advancement enables patient-specific trajectory generation that captures aspects of AD heterogeneity not observable from structural anatomy alone, bridging the gap between rich multimodal supervision and the strict constraints of routine clinical deployment. Code is available at: https://github.com/antonioscardace/MC-LDM.

arXiv:2610.24926v2 Announce Type: replace-cross Abstract: We present Stable Signer V3, an interactive high-resolution sign language avatar system built on 4D Deformable Primitive Splatting. It addresses three limitations of existing avatars: restricted facial expression, inaccurate identity-specific body deformation, and loss of fine appearance details. Shared Face Primitive Splatting adds transferable superquadric primitives for richer expression control; Test-Time Body Primitive Splatting learns an identity-specific virtual muscle layer for more faithful motion; and Test-Time Tunneling Super-Resolution uses TunnelingNet to recover identity-specific high-resolution details. Both test-time modules are optimized once per signer identity; inference then runs entirely from the stored identity parameters. Together, they reduce facial geometry error by 71.4%, body-boundary error by 35.1% across ten identities, and high-resolution RGB reconstruction error by 24.2% on held-out evaluations, while retaining interactive streaming.

arXiv:2610.24628v2 Announce Type: replace-cross Abstract: We introduce Muse Glimmer, an open-source 30B parameter causal language model with perception encoder, purpose-built for autonomous agentic tasks on consumer hardware. Muse Glimmer integrates multi-step reasoning, reliable tool use and failure recovery into a single model that runs locally on consumer devices without requiring cloud infrastructure. The model accepts text and image inputs and produces text outputs, was trained on data from over a hundred languages, and is quantized to approximately 4-bit precision for efficient single-GPU inference. Muse Glimmer achieves state-of-the-art performance for its size class on agentic benchmarks, setting a new standard compared to the models of its size: Gemma4-31B and Qwen3.6-27B on tool use, multi-step planning, and agentic task completion. We release the model under the Apache 2.0 license to foster open-source development of capable, safe, local AI agents.

arXiv:2610.24452v2 Announce Type: replace-cross Abstract: We introduce avatar referring segmentation, which selects regions of animatable Gaussian avatars from language queries. A query can also specify a pose or motion to select matching intervals. This lets users interact with avatars for local editing and motion inspection. However, making these selections with existing language Gaussian splatting methods poses two challenges: adjacent parts and garments are hard to separate and may be referred to indirectly (region ambiguity), while fine-grained motions can look alike in RGB (motion ambiguity). We address these challenges with HumanSkill-4D, a training-free framework that shares a multimodal large language model (MLLM) and geometric operators across avatars. For each avatar, a semantic memory links body-part and garment categories to persistent Gaussian regions and appearance descriptions. The MLLM uses category names and descriptions to select categories by appearance, relation, or function. To find matching intervals, it composes operators into programs that check query conditions on driving joint trajectories stored in a motion memory. These category choices and operator outputs make selections traceable, while composing or adding operators supports new motion conditions. To evaluate this task, we introduce three human-annotated benchmarks and show that HumanSkill-4D outperforms the baselines in part segmentation and 3D and 4D referring segmentation, with compact memories and only minutes of setup per avatar.