Papers

Interactive chart code generation requires models to reproduce a reference chart's appearance and underlying data and correctly implement the state changes triggered by specified user interactions. Existing chart-to-code benchmarks focus on static outputs and lack task representations or evaluation protocols for interaction specification, browser execution, and post-interaction verification. We introduce IChart2Code, a benchmark comprising 377 tasks across 20 chart forms and 13 data families, with 1209 interaction requirements in six families. Each task provides a reference screenshot, task-local data, and natural-language interaction requirements, with executable HTML/JavaScript code as the target output. We further develop a browser-based evaluation protocol with an Executability gate and three rubric-guided dimensions: Data Fidelity, Static Visual Correctness, and Interaction Correctness. The protocol tests runtime viability, consistency with task-local data, fidelity of the initial rendering to the reference screenshot, and interaction-induced state changes in a sandboxed browser. A rubric-guided MLLM judge evaluates task-specific items for the three scored dimensions using the collected browser observations and achieves an overall item-level F1 score of 0.8844 against adjudicated human labels. We also propose TRAIL, a trajectory-guided dual-agent framework for interactive chart code generation. An Inspector derives task-specific inspection checks, executes them in the browser, and uses the resulting trajectories to diagnose failures and produce structured repair feedback. Averaged across four MLLMs, TRAIL improves the four evaluation dimensions over direct prompting by 7.89, 4.98, 3.45, and 4.47 percentage points, respectively.

Bayesian state estimation for high-dimensional nonlinear dynamical systems entails a fundamental tension between statistical fidelity and computational tractability, as particle weights can collapse, while Gaussian ensemble updates can miss non-Gaussian posterior structure. Score-based diffusion filters offer a sampling-based alternative, but existing training-free score filters often rely on heuristic likelihood corrections, which can compromise posterior accuracy by neglecting uncertainty about the system state associated with each noisy reverse particle. To address these issues, we propose AECSF, a training-free adaptive ensemble conditional score filter. AECSF constructs an analytically tractable score estimator from the conditional Tweedie identity, which recasts noisy posterior score estimation as estimating the conditional mean of the system state given a noisy reverse particle and the observation. To estimate these conditional means efficiently, AECSF employs a shared adaptive weighted proposal ensemble, while particle-specific conditional weights yield an estimate for each noisy reverse particle without separate proposal sampling. The proposal ensemble is updated using reverse-particle information within the same reverse-diffusion run to improve conditional-mean estimation. Theoretically, we characterize when a fixed weighted proposal measure yields the exact noisy posterior score. Under stated assumptions, we establish a bound relating conditional-mean estimation errors to reverse-sampling endpoint error. Numerical experiments demonstrate that AECSF improves the accuracy of posterior sampling and nonlinear filtering in high-dimensional problems with limited forecast ensembles.

Finite-difference discretizations of Laplace operators yield discrete Laplacians whose spectral properties are closely tied to the stability, convergence, and physical fidelity of numerical solvers. While symmetric discretizations are well understood, many high-order finite-difference schemes produce nonsymmetric matrices for which rigorous spectral analysis is overlooked. Surprisingly, we prove that two fourth-order schemes with Dirichlet boundary conditions yield nonsymmetric discrete Laplacians whose spectra are purely real and strictly positive. Computer-assisted computations show that this property does not hold for higher-order extensions of these schemes in general.

Amortized neural likelihoods enable computationally expensive inference for models with analytically intractable or unspecified likelihoods, but their black-box nature limits interpretability. We introduce a symbolic distillation pipeline that converts trained neural likelihoods into explicit, interpretable expressions optimized for efficient parameter estimation. Our approach uses a recovery-directed objective to guide symbolic regression toward expressions that preserve parameter-recovery accuracy rather than merely approximating the likelihood function. Candidate expressions are evaluated on held-out datasets and selected using a criterion that jointly accounts for expression complexity, parameter-recovery performance, and distributional distance from the learned likelihood. We evaluate the pipeline on the diffusion decision model, a classical cognitive model, whose analytically tractable likelihood provides ground truth for controlled evaluation. The proposed recovery-directed objective improves parameter recovery over standard symbolic-regression objectives. The resulting symbolic likelihoods enable over 100 times faster parameter evaluation than both neural likelihoods and, when available, the exact likelihood, while maintaining a manageable loss in precision. We further demonstrate these computational benefits in Bayesian hierarchical inference on empirical data. Our pipeline provides a lightweight interface for integrating symbolic distillation with existing neural-likelihood estimation methods and can be adapted to a range of simulation-based inference settings.

The rapid advancement of Artificial Intelligence (AI) and Natural Language Processing (NLP) has revolutionized the way humans interact with machines. Among the most impactful developments is Automatic Speech Recognition (ASR), which enables computers to convert spoken language into text. Systems such as those built on deep neural networks, transformer architectures, and self-supervised learning have achieved near-human performance for well-resourced languages such as English and French. Yet, these advances have disproportionately benefited a small fraction of the world's languages.

LLM judges are widely used to evaluate model outputs, but their verdicts can be unreliable: a judge may favor the worse answer for its position, length, or other surface features. When a judge is wrong, is the information needed to judge correctly absent from the model, or present in its internal representations but not reflected in the output? We study this across 64 open-weight evaluators and 14 datasets, including causal interventions on 41 judges (editing activations mid-run to see whether the verdict changes). On LLMBar, built so the superficially better answer is the worse one, the verdicts of 50 judges agree with human labels only 0.456 of the time, even after averaging both answer orders. Yet a small probe on the same judges' activations, with no weight updates, reaches 0.846, and 0.686 once surface features such as length and position are residualized out (0.507 with shuffled labels). The gap holds across eight benchmarks and model families, but is not universal: a score of how well surface features alone predict the human label, computed before any probe is trained, predicts the size of the gain (Spearman rho = 0.90). On rubric tasks that score one answer at a time, leaving no surface cue to exploit, reading the internals gives no advantage. The interventions also show that editing activations mid-network already changes the verdict, before it can be read off directly, and locate the pathways carrying position and length bias. At the same label budget, the recovered signal lets a judge flag cases where it is likely wrong and yields better labels for preference learning. A wrong verdict, then, does not mean the judge lacks the information, and a simple diagnostic shows when it is worth recovering.

We develop a structure-preserving locally optimal block preconditioned conjugate gradient(LOBPCG) method for computing several of the largest positive generalized singular values of a matrix pair \((A, B)\), where \(B\) has full column rank, together with the associated generalized singular vectors. The method is derived from the Hermitian-definite Jordan–Wielandt pencil and therefore avoids explicitly forming the normal-equation matrices. By exploiting the block structure and spectral symmetry of this pencil, we construct separate search subspaces for the left and right generalized singular vectors. The resulting Rayleigh–Ritz procedure requires only a singular value decomposition of a small projected cross matrix. We adapt the improved Hetmaniuk–Lehoucq (IHL) trick to construct stable conjugate search directions in the two component spaces. We also establish an explicit correspondence between the coefficient matrices produced by the componentwise and augmented Rayleigh–Ritz procedures. This correspondence permits the componentwise IHL construction to be used in an augmented, structure-preserving LOBPCG formulation without explicitly assembling the augmented basis. Numerical experiments demonstrate the computational advantages of the proposed method over unstructured and Gram-matrix-based LOBPCG implementations.

Event cameras provide low-latency, asynchronous visual sensing for resource-constrained robotics. Spiking neural networks (SNNs) process event streams naturally, but training deep SNNs with backpropagation through time (BPTT) requires substantial memory and remains difficult on neuromorphic hardware. Local learning avoids this by restricting error propagation to local blocks, but existing methods mainly target classification rather than dense prediction. We introduce DELL (Dense Event-driven Local Learning), a block wise scheme for dense event-based vision that replaces global gradient propagation with local dense supervision. Learnable, spatially structured local heads supervise each block at its appropriate resolution while preserving temporal dynamics within blocks. We evaluate DELL on optical-flow regression and semantic segmentation with a fully spiking U-shaped architecture. On DSEC optical flow, DELL reduces peak training memory by 39.6% relative to end-to-end BPTT while improving accuracy, reaching 1.670 px endpoint error on the official test benchmark versus 1.941 px for the same backbone trained end-to-end. Block detachment behaves more like a regularizer than a constraint. DECOLLE, the existing local-learning baseline, relies on fixed random local read-outs poorly suited to dense regression, resulting in a 3.9x higher endpoint error; learnable local heads recover this loss and outperform end-to-end training across all optical-flow metrics. On segmentation, they recover most of the performance gap, although DELL remains a few mIoU points behind end-to-end training. With 2.3M parameters, 24x fewer than the strongest SNN baseline, the backbone remains competitive with the SNN state of the art on DSEC. These results extend local learning to dense event-based prediction while substantially reducing training memory.

A mixed graph $M=(V,E\cup A)$ is acyclic if its directed part $(V,A)$ is an acyclic digraph. In this note we study the so-called orientation completion problem for the class of acyclic mixed graphs. That is, given an acyclic mixed graph $M$ and a property ${\cal P}$; can we orient the edges of $M$ so that the resulting digraph is acyclic and has property ${\cal P}$. We prove that one can decide in polynomial time whether $M$ can be completed to an acyclic digraph with an out-branching from a prescibed vertex $s$, while it is NP-complete to decide whether $M$ has an acyclic orientation which has both an out-branching and an in-branching (a bipolar orientation). We show that it is NP-complete to decide whether $M$ can be oriented so that it contains a directed path between two prescribed vertices. Finally we describe a polynomial algorithm for deciding whether an acyclic digraph $D$ has an out-branching $B^+_s$ such that the digraph $D-A(B^+_s)$ is connected (in the underlying sense). Based on this we pose as an open problem the complexity of deciding whether the edges of an acyclic mixed graph can be oriented so that the result is an acyclic digraph with a non-separating out-branching.

LLM agents that write long-form fiction need an explicit memory of the evolving storyworld to keep new events consistent with established facts. Such memory must keep heterogeneous narrative information distinct, integrate story developments across granularities, and recover dependencies that a writing request leaves implicit. We present NarraWorld, a structured memory system for long-form writing that treats memory construction as world creation. From a shared evidence-grounded graph, NarraWorld derives four connected views: world facts, per-character beliefs, open developments, and hypothetical branches (possible-world continuations). Hierarchical aggregation with atomic closure consolidates events into scenes, plotlines, and plots, keeping each higher-level node traceable to its constituent source spans. For retrieval, planned reconstruction infers a query's dependencies from the current narrative situation and a preview of memory, then assembles the relevant records within a token budget. Across three writing benchmarks, NarraWorld achieves the strongest aggregate results. Its memory also transfers to situated role-playing and largely preserves recall on a general-purpose long-term memory benchmark, paving the way for agents that sustain coherent storyworlds across diverse narrative tasks.

Agent skills package instructions, executable code, and task-specific resources into reusable artifacts that agents can improve using execution feedback. The same mechanism also enables attackers to evolve malicious skills, making them more effective and less detectable. However, a candidate skill may pass pre-execution scanning yet fail to realize its target under runtime defenses, while a revision that repairs execution may introduce new scanner findings. We introduce SkillDRE, a fully automated framework for evolving complete malicious skill packages through a dual-stage feedback loop. Given a benign task and its associated skills, SkillDRE autonomously constructs and validates a task-conditioned malicious objective and a verifiable judge rule. It then holds both fixed while evolving the skill implementation, with preservation of legitimate task capability. SkillDRE combines scanner-guided evolution with runtime-guided refinement informed by execution outcomes observed under runtime defense. Each runtime-guided revision returns to the pre-execution stage for rescanning and further optimization before re-execution, forming a cross-stage closed loop. Evaluated on SkillsBench across four victim models, SkillDRE achieves an average attack success rate of 45.28%, exceeding the strongest baseline by 40.3%, while its final submitted skills receive no SkillScan findings and largely preserve benign-task performance. These results show that two-stage defense feedback can serve as a useful learning signal for adaptive red teaming and that evaluating either defense stage in isolation can miss the resulting attack capability. Codes is available at https://github.com/whfeLingYu/SkillDRE

Endoscopic scene reconstruction requires modeling tissue motion and temporal appearance while recovering fine surface detail. Deformable Gaussian models provide explicit trajectories, but their fixed colour coefficients lack a dedicated temporal representation for photometric changes. We propose Endo-TSR, which augments deformable Gaussian splatting with bounded Fourier colour residuals and independent translation residuals on shared temporal frequencies. The colour residuals capture local appearance changes, while a Matérn spectral prior regularises motion corrections. Multi-scale Laplacian supervision guides tissue-detail recovery during joint image fitting. Extensive experiments on the EndoNeRF and StereoMIS datasets demonstrate state-of-the-art rendering quality, with the highest PSNR across all evaluated sequences. Ablation studies show that temporal appearance yields the largest PSNR gain among the tested component additions, while appearance and detail supervision jointly improve rendering with fixed Gaussian counts.

The scaling of LLMs increasingly relies on MoE architectures to decouple active computation from total parameter count. However, the efficacy of MoE is often constrained by expert collapse and representation redundancy, both leading to underutilization of model capacity. To address these challenges, this paper proposes Distributional Orthogonalization Loss (DO-loss), an auxiliary regularization that shifts the focus from static weight diversity to dynamic routing behavior. By representing each expert's token assignment history as a high-dimensional binary load signature, DO-loss penalizes signature overlap to prevent expert collapse while encouraging functional specialization. To align this algorithmic design with system efficiency, we further introduce the Replica Expert Mechanism (REM), which improves load balancing through a two-tiered strategy: adjusting replica expert placement at the global-batch level and performing real-time token dispatching at the micro-batch level. Empirical evaluations demonstrate that our method outperforms the evaluated routing algorithms on downstream tasks for both 4.8BA0.5B and 30BA3B MoE models, while maintaining comparable training efficiency.

Legal document summarisation in low-resource languages presents significant challenges due to the scarcity of annotated data and the complexity of domain-specific terminology. This paper presents SinBrief, a hybrid abstractive summarisation framework for Sinhala legal documents that does not require human-annotated training data. The proposed framework combines domain-aware word graph construction with neural sentence scoring to generate abstractive summaries from Sinhala legal text. Five sentence scoring models are evaluated within the framework: mBert, Llama 3.1, Falcon 7B, Laser, and a continually pre-trained Llama model domain-adapted to Sinhala legal text. The framework is evaluated on a Sinhala legal corpus using reference-free metrics, including Coverage, Density, Compression Ratio, SummaC, and Self-BertScore. Experimental results demonstrate that SinBrief produces summaries with lower lexical overlap than extractive baselines while maintaining factual consistency, demonstrating the viability of hybrid, largely annotation-free abstractive summarisation for low-resource legal NLP tasks.

Forced alignment estimates the timestamps of each word, phone or character in speech given its transcript. Published comparisons normalize transcripts, split the data and match boundaries differently, so their numbers cannot be read together. We present FA-Bench, an open framework that fixes those choices once and releases the code, splits, phone mapping, text normalization and scoring script, with results published periodically. Track 1 gives every aligner the reference transcript and Track 2 gives it a recognizer's output, on the same audio, clean and degraded four ways, with 21 open models and 9 commercial APIs under a unified protocol. We score every boundary of an utterance and check the two labels beside it, so a word the recognizer missed or invented is charged. Using a tolerance-based F1 as our primary metric eliminates the 9% to 14% score inflation that standard MAE causes on recognition-dependent systems in conversational speech. We then group boundaries by position and how many adjacent words were recognized correctly, which shows where a system lost the score. We discovered systematic bias in how current systems time words, with Whisper about 150 ms early and several commercial ASR APIs over 50 ms late. Code and results are at https://github.com/olewave/fa-bench

The KV cache of a transformer entangles every token's representation with its entire prefix: a passage encoded once cannot be reused under a different prefix or removed without recomputing everything after it, so exact cache reuse is limited to shared prefixes. We present SMem, an architecture whose context representation is a cache by construction. A block-local encoder maps each block to memory rows independently of other blocks, and a reader conditions generation on their union through cross-attention. For every parameter setting, memory composes exactly at fixed block indices, deleting a block is an exact $O(b)$ update for $b$-token blocks, and the memory state is independent of the edit path. At $4\times$ the training context, under the shared recipe, SMem retrieves planted needles beyond any trained-length window (exact match 0.14-0.28 at distances of 31 and 63 blocks), where learned-position, RoPE, and Block-Attention-style transformers all score at most 0.02. A fully cached context is served by computing one block alone at a near-constant 3.1-6.2 ms, whereas cold prefill grows with context; batched decode stores 34-38% fewer KV rows and runs 1.4-1.7$\times$ faster when bandwidth-bound; and deletion beats suffix recomputation by 8.5$\times$ at 512 blocks and 452$\times$ at 4096 blocks (32-256$\times$ the trained length, probing the cost model rather than a served regime). The cost is a perplexity gap of -4.7% to +2.8% (negative favors SMem) against a parameter-matched transformer with the same positional scheme, at 160M-1.5B on FineWeb-Edu across two recipes and a learning-rate search. SMem also composes with RoPE: at 160M and 410M the composite matches or leads the matched transformer and closes 29-59% of SMem's gap to a RoPE transformer. Dropping prefix entanglement thus keeps perplexity comparable while making the cache exactly composable and editable.

Designing dense reward functions for low-level reinforcement learning (RL) control remains difficult. Recent work uses large language models (LLMs) to iteratively generate and refine reward functions using policy-training feedback within scripted search algorithms. However, evaluating each candidate requires a full RL training run, making sample efficiency a central challenge for reward search on complex control tasks. To address this limitation, we propose an Agentic Reward Black-box Optimization (ARBO) framework, in which an LLM agent builds the search strategy at run time from an evaluation history maintained as its persistent workspace. The evaluation history comprises two components: observations maintained by the evaluation oracle, including candidate scores, per-term training curves, and error tracebacks; and an agent-maintained belief that records diagnoses and intended next steps. The agent queries both with tools and generates the next batch of reward candidates, rather than generating them in a single pass from a fixed prompt. Across four control domains, ARBO achieves gains of 29.9% in manipulation success rate and 192.8% in power-grid score over baseline means under a shared evaluation budget. Ablations examine each component's contribution and sensitivity to backbone choice.

Plug-and-Play (PnP) methods solve imaging inverse problems by incorporating deep denoisers into iterative optimization algorithms. Although practical implementations often decrease the denoiser noise level $\sigma$ along iterations, most existing convergence analyses assume a fixed denoiser. In this work, we establish convergence guarantees for a broad family of Plug-and-Play algorithms with annealed noise level, spanning deterministic methods (RED–GD and PnP–PGD) and stochastic methods (SNORE, equivariant RED, and a variant of PnP–Flow). For each method, we identify an explicit, nonconvex objective associated with the terminal denoising level and prove asymptotic stationarity of the iterates with respect to this objective. Our analysis does not prescribe any decay rate for the noise schedule, and our assumptions cover both learned gradient-step denoisers and exact MMSE denoisers. Overall, our theoretical results bridge the gap between existing PnP convergence theory and the decreasing-denoising practices used by state-of-the-art image restoration methods. We empirically demonstrate the benefits of such schedules and illustrate the predicted convergence behavior on several imaging inverse problems, including inpainting, super-resolution, demosaicing and tomography.

Continual-learning agents are systems of models, harnesses, and memory operating over long multi-session horizons. Evaluating and training them requires interleaving tasks with agent-side events such as session stop and start, crons, and memory consolidation. Yet existing benchmarks and training frameworks schedule only the benchmark's own events, leaving each benchmark and agent pair to build a custom scheduling loop. We present SCLATE, an execution substrate where benchmarks and unmodified agents each add their events to one open event scheduler through an adapter. A hybrid simulated clock runs these events on a shared timeline, flowing in real time while the agent works and skipping idle gaps, which compresses a month-long scenario into hours. SCLATE also serves as a rollout engine that runs any agent's harness and memory unmodified, recording the tokens and log probabilities of every model call through an in-container proxy. We port seven benchmarks to SCLATE and compare ten unmodified harness and memory configurations head to head on ten models. The comparison shows that an added memory system does not reliably beat the harness's native memory and that models differ widely in how they use the same harness and memory. We then post-train Qwen3.5-4B through unmodified harnesses and memory systems. The model learns to use both, reading 6.8x fewer file lines with a 16.7-point higher SWE-bench Verified pass rate, and writing richer memory records, while its held-out MetaClaw accuracy rises by up to 11.8 points.

The July 2026 intrusion into Hugging Face production infrastructure showed how reward hacking can become an external cybersecurity incident when a capable agent encounters weak containment boundaries. This study develops a probabilistic risk model linking five stages: reward hacking, containment escape, usable access, persistence, and failure of detection. A Monte Carlo simulation evaluates 100,000 runs under each of four control configurations. Input distributions represent explicit uncertainty and are used for comparative analysis rather than real-world frequency prediction. Under the stated assumptions, layered controls reduce simulated external-incident probability substantially more than network isolation or monitoring used alone, an ordering that holds under independent plus/minus 25% perturbation of every coefficient in the model across 300 draws. Sensitivity analysis shows that agent capability and weaknesses in monitoring, authorization, and credential control exert the greatest influence on modeled risk. Human temporal discounting and metric gaming provide a behavioral analogy for short-horizon optimization, but the study does not infer that AI agents experience gratification or human motivation. The results support treating cyber-capable agent evaluations as hostile security zones in which indirect egress, shared infrastructure, credentials, and evaluation artifacts must remain outside the agent's effective authority.

Filmmakers and visual artists routinely need to compose multiple references, actors, locations, props, cultural elements, into a single coherent shot, but existing tools either fail to scale past a handful of references or destroy fine grained subject identity in the process, since per reference tokenization scales memory linearly with reference count $N$ and generated content often departs from the given references rather than reproducing them. We propose RefCompose, a pixel space compositional conditioning framework that decouples where things go from what they look like, via a single fixed resolution reference canvas that keeps conditioning size constant regardless of reference count. Spatial layout is induced at inference time from a frozen diffusion transformer and extracted via Grounding DINO, requiring no LLM or dedicated layout model, while dual stream LoRA adapters inject a layout derived depth map and the encoded canvas through separate low rank streams, disentangling geometric scaffolding from localized appearance. On the Dense Layout protocol, RefCompose consistently outperforms layout based and state of the art multi reference baselines on color, texture, shape, spatial accuracy, and identity/content preservation at higher reference counts, all with constant inference memory, making it a practical building block for multi subject cinematic composition at production scale.

We give a rank-23 algorithm for $3\times3$ matrix multiplication using 51 additions and subtractions in alternative bases. The input and output conversions require five further additions, giving 56 additions in ordinary coordinates. The construction combines linear-program reduction with a search over sparse basis changes, and the resulting programs are distributed as a machine-checkable certificate. We verify correctness by exact coefficient expansion and distinguish the kernel cost from the cost of a complete multiplication.

Impaired glucose regulation is a major contributor to metabolic dysfunction and type 2 diabetes. This study developed an interpretable machine-learning framework to predict log-transformed fasting blood glucose using metabolic, hormonal, lifestyle, demographic, nutritional, and circadian variables from the National Health and Nutrition Examination Survey 2017–2020 pre-pandemic dataset. After merging multiple NHANES sub-datasets, data processing used a leakage-resistant pipeline in which imputation, scaling, and one-hot encoding were performed only after dataset splitting and within training folds. Elastic Net, LASSO, and XGBoost models were evaluated using 94 candidate predictors and engineered circadian interaction terms. Performance was assessed using mean absolute error, root mean squared error, coefficient of determination, calibration, and Shapley Additive Explanations. The final interaction-augmented XGBoost model achieved strong performance on the independent test set, with a mean absolute error of 0.0804, a root mean squared error of 0.1148, and a coefficient of determination of 0.7761, using 10 predictors. Glycohemoglobin was the dominant predictor, followed by insulin, diabetes diagnosis, gamma-glutamyl transferase, age, race, and gender. Among the engineered interaction terms, sleep midpoint multiplied by age was consistently retained in repeated random-split analyses, although its contribution remained modest relative to dominant glycaemic predictors. These findings support further investigation of circadian-age interactions in metabolic health.

Interactive dashboards require users to reveal and connect evidence across stateful interactions. Although graphical user interface (GUI) agents could automate this process, existing dashboard benchmarks primarily report final answers or task success. They provide limited insight into whether failures arise from maintaining the analytical process, selecting actions, or grounding visual targets. We introduce DashAct, a progressive diagnostic benchmark that evaluates the same annotated dashboard interactions under systematically varied contextual and spatial support. DashAct contains 348 human-verified interaction trajectories with milestone dependencies and hierarchical target annotations. Its three stages evaluate end-to-end execution, verified-context action prediction, and target-conditioned grounding under four visual conditions. Aligned action and spatial annotations connect outcomes across these settings, providing diagnostic evidence for interpreting online failures. Experiments reveal persistent difficulties in action prediction and fine-grained grounding, alongside model-dependent responses to contextual and spatial support. A Qwen-based adaptation study further improves target localization and online Milestone Coverage, illustrating how DashAct can guide practical agent improvements.

Real-world time series are inherently non-stationary, with trends, periodic patterns, and uncertainty evolving over time. While the Fourier domain offers a natural lens to model time series, current deep learning approaches do not explicitly model evolution and randomness in the Fourier spectra, which limits their ability to accurately predict both the expected trajectory and its uncertainty in non-stationary time series. Motivated by Evolutionary Spectra (ES) theory, we propose TimeES, a general framework that enables probabilistic and deterministic forecasting via the evolutionary spectra theory. Specifically, we derive a parameterizable evolutionary spectra formulation, recasting non-stationary random process modeling as learning an evolving representation modulated by random variables. Furthermore, we reduce the complexity of the estimated spectra from O(NM) to O(NK), where K << M/2, by exploiting Hermitian symmetry and spectral energy sparsity for frequency selection. Based on a simple linear backbone, our proposed TimeES achieves consistent state-of-the-art performance across both deterministic and probabilistic forecasting tasks, with high efficiency and interpretability. Code is available at: https://github.com/wwy155/TimeES.

We present our system for the PlurVA-LLM 2026 Shared Task Track-1, which focuses on pluralistic value alignment in the contexts of China, Indonesia, and Sri Lanka. For this resource-constrained track, we fine-tuned Llama 3.1 8B Instruct using 4-bit QLoRA. Our approach combines option-permutation augmentation for Chinese data, annotator vote expansion for Indonesian data, and binary reformulation with SinhalaMMLU augmentation for Sri Lankan data. We further applied conditional threshold calibration to the predictions for the Sri Lankan data. The final system achieved accuracies of 0.785 for Chinese, 0.715 for Indonesian, and 0.916 for Sri Lankan, resulting in an overall macro-average accuracy of 0.805.

Data attribution tools used in practice, TRAK, LoGRA/LogIX, and EK-FAC, run after training: they recompute per-sample gradients in a separate pass over the training set, and curvature-aware variants need a further pass to estimate covariance. Traceprop records projected per-sample gradients and K-FAC covariance statistics inside the training backward pass itself. On Pythia-1B LoRA fine-tunes on an A100, this adds 2.6% to training time, against 10.7% for LogIX's best inline configuration, random-init (4.1x lower, one-sided Mann-Whitney p = 9e-5, n = 10 per arm); at Pythia-6.9B the numbers are 11.3% and 27.0% (p = 0.004). LogIX's default configuration, PCA-init, is both slower and lower quality than random-init, so we compare against random-init throughout. On a small transformer where LDS is measurable, Traceprop matches LogIX's best configuration: pooled LDS difference +0.0022, 95% CI [-0.0038, +0.0075]. Two things do not work: at Pythia-160M/SST-2, every method is indistinguishable from a low noise ceiling, and on planted-backdoor and mislabel detection, gradient attribution does not beat gradient norm or representation similarity. The contribution here is systems, not a new estimator: LogIX's attribution quality, in one pass instead of two.

What controls are needed to interpret execution performance and audit scores in LLM agent evaluations? We study two limits on these interpretations in a financial agent harness. In Study~A, comparing independent runs under idealized and stressed execution on three synthetic settings that share one 24-day upward phase mixes the execution rule with fresh model responses and portfolio feedback: the parsed decision paths agree in only $19.8\%$ of $450$ pairs. Replaying each stored response tape through both execution destinations gives a narrower result. Conditional on those responses, stressed execution changes total return by $-0.0170$ (95% interval $[-0.0230,-0.0117]$), or $10.4\%$ of the idealized baseline, and ten seed clusters do not resolve the model ranking. Study~B corrects an incomplete answer key and replaces legacy tasks with matched zero-, one-, and two-defect tasks under an explicit multi-label prompt. The drop in target violation recall from one to two defects is positive in five of six combinations of auditor and source (median $0.267$), with three surviving Holm correction. Yet the auditor that includes both target labels most often has micro-precision $0.149$, emits findings on $98/100$ zero-defect tasks, and returns the exact dual-defect set in only $21/100$ cases. Target recall by itself therefore gives a poor account of audit quality on this construction. The studies address different limits: what an execution comparison estimates, and what target recall captures. Together, they show how fixed conditions and diagnostic controls bound the claims a score can support.

LLM-based agents are increasingly deployed with authority over consequential resources and decisions in real systems. These agents often operate alongside human and LLM-based participants who hold different forms of authority. Yet workflow roles, permission settings, and review mechanisms do not necessarily reflect the authority realized in practice. We introduce AuthorityLens, a framework for measuring a system's authority structure. Starting from an authority portfolio, we evaluate a system along three dimensions: what the system is authorized to do (System Authority), how much joint participation is required to exercise that authority (Authority Separation), and how much authority each participant holds (Principal Authority). We derive these measurements from the minimal combinations of participants sufficient to realize each outcome across admissible runtime states. We apply AuthorityLens to Codex, OpenCode, and Gemini CLI across 13 operating configurations over a common portfolio of agent operations. We find that nominal configurations do not map cleanly onto realized authority. In Codex, Full Access changes System Authority only marginally while substantially concentrating authority in the executing Assistant. OpenCode's Build and Plan configurations have the same System Authority and Authority Separation despite different workflows and root-level permissions. In Gemini CLI, model-based review increases Authority Separation without changing System Authority. Principal Authority further distinguishes authority replication from authority separation: spawned or delegated agents can become alternative holders of the same authority without increasing the required joint participation. Together, these results demonstrate that AuthorityLens provides a unified framework for measuring and comparing realized authority structures across agent systems.

Iterative generation poses a joint optimization problem across steps, as intermediate predictions shape subsequent computations and ultimately determine the final output distribution. Few-step generators distilled from pretrained diffusion and flow-matching models make such optimization computationally practical end to end. We build on this opportunity with a distill-then-refine approach that uses teacher imitation to establish a strong initialization for a few-step rollout in latent space, then shifts to end-to-end refinement of the complete latent rollout against real data. We introduce FiST (Flow-in-Stage Transformer), an architecture that composes learned latent-state transitions in a few stages using a shared Transformer, with optional cross-stage hidden communication. Distillation applies teacher-forced regression to selected states along teacher trajectories; refinement replaces this supervision with adversarial and auxiliary classification objectives on the final latent output. A trainable discriminator module operates on semantically rich features extracted from clean real and generated latents by a frozen SiT backbone pretrained with REPA. All training takes place in latent space, without image decoding. During refinement, FiST consumes its own intermediate predictions, and endpoint gradients pass through every generation stage. For class-conditional generation on ImageNet at $256\times256$, our approach achieves FID 1.11 (IS 282) with three stages and FID 1.15 (IS 280) with two. These results demonstrate competitive few-step generation through learned distribution-level supervision, without explicit Fréchet-distance minimization. Ablations characterize how distillation, pretrained checkpoint choices, refinement supervision, and cross-stage hidden communication affect generation quality.