Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达,利用大语言模型自动生成交叉领域文献分析简报。

01.
medRxiv (Medicine) 2026-06-17

Nickel and Dimed: How a Common Earth Element is Short-Changing Our Health

Nickel has been studied for a long time as an environmental contaminant but less so in its connection to population health. It does not announce itself as loudly as its transition metal brethren like mercury and cadmium, but its chemical properties permit it to be deleterious as a low-dose, chronic exposure, particularly among those with immune systems sensitized to it. There is a growing evidence base and vocabulary to discuss nickel's affect on health. However, in the U.S., there are not recent, reliable estimates of the share of the population with a nickel allergy, let alone how much nickel Americans are exposed to through their diet. This paper seeks to close this evidence gap by creating a new dataset of dietary nickel and other heavy metal exposure and assessing how high levels of dietary nickel exposure shape local demand for health care services. We use soil data from the U.S. Geological Survey and data on agricultural product transport from FoodFlows.org to create a county-level dietary nickel exposure index. We then use a large electronic health record database and double machine learning to estimate how demand for primary care services varies across levels of dietary nickel exposure. We find that counties with high nickel exposure experience an increase in the share of primary care office visits for symptoms highly suggestive of nickel poisoning. This result survives multiple hypothesis test corrections and placebo tests. Our research suggests that nickel has harmful effects on individual health whose exposure can be measured at a population level, and is shaping primary care across the U.S.

02.
arXiv (CS.AI) 2026-06-11

Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields

arXiv:2606.11042v2 Announce Type: replace Abstract: Recent years have witnessed the rapid evolution of AI agents toward handling increasingly complex, real-world tasks. However, existing benchmarks rarely evaluate whether agents can operate graphical user interfaces to complete long-horizon, high-value professional workflows across diverse domains. Current GUI benchmarks still predominantly focus on general-purpose software, relatively simple applications, and short-horizon tasks, leaving it largely unknown whether modern agents can follow user instructions to autonomously operate domain-specific professional software and accomplish economically valuable work in an end-to-end manner. To bridge this gap, we introduce Workflow-GYM, a benchmark for long-horizon GUI tasks centered on professional domains and specialized software environments. Through extensive experiments on state-of-the-art models, we find that even the strongest models achieve only slightly above 30% success rates, highlighting that professional long-horizon GUI workflows remain highly challenging for current GUI agents. Further analysis reveals that current agents struggle to maintain long-horizon workflow consistency, frequently exhibiting workflow stage omission, error propagation, objective drift, and insufficient understanding of professional software environments. Our findings provide important insights into the limitations of current agent systems and suggest key directions for the next generation of GUI-agent research.

03.
arXiv (CS.AI) 2026-06-16

Attention is Just Another Name for Coupling?: A Fast-Slow ODE Perspective on Hierarchical Pretraining

arXiv:2606.16730v1 Announce Type: cross Abstract: Causal self-attention is a coupling mechanism: each token's hidden state is updated by a learned mixture of preceding tokens at the same timescale. This paper asks whether a second, temporally slower coupling-a slow sub-system operating on a temporally-downsampled view of the sequence and fed back into the fast path through a zero-initialised gate-complements it. The question is framed in the language of singularly perturbed ordinary differential equations (ODEs), where the fast variable $x$ evolves at the token rate, the slow variable $y$ evolves at one update per $P$ tokens, and the timescale ratio $\varepsilon = 1/P$ is enforced structurally by causal block-mean pooling. The paper instantiates the fast-slow ODE formalism as a concrete neural network: a fast path of standard causal attention over $T$ tokens, a slow path of full attention over $T/P$ pooled tokens ($P^2 \times$ cheaper per layer), and a zero-initialised additive gate. In addition, under a linear-generator assumption on the fast dynamics, we prove that the equilibrium manifold $x = \phi(y)$ is exactly the master-equation (ME) stationary distribution $p_{\mathrm{st}}(y)$; in that regime a learned MLP $\phi_\theta(y)$ is a variational approximation of it (the trained block is not a generator, so this identity is the structured limit, not a claim about the network as trained). Empirically, at $500$k tokens the coupling is neutral – the gate stays closed and the coupled and frozen ablations are within run-to-run noise – at a wall-clock cost comparable to a dense baseline. The contribution is the precise, gap-marked mapping itself, not a performance gain.

04.
arXiv (CS.AI) 2026-06-16

Phase-Aware Guidance Injection for Recurrent MAPPO in Assembly-Line Disruption Recovery

arXiv:2606.16330v1 Announce Type: new Abstract: Disruption recovery in industrial assembly lines requires timely decisions under machine faults, worker absence, and emergency orders. Existing methods either rely on rigid handcrafted recovery logic or learn adaptive policies that do not readily exploit heterogeneous external recovery knowledge at decision time to reduce abnormal recovery time (ART) and preserve on-time delivery (OTD). To address this gap, we propose a phase-aware guidance injection framework that augments a trained recurrent MAPPO (RMAPPO) scheduling policy through logit-level action bias during evaluation. The framework provides a unified decision-time interface for rule-based, replay-based, and online LLM-based guidance, while activating intervention only during abnormal and recovery phases. Experiments on a custom AssemblyLineEnv show that high-quality rule guidance yields the strongest gains, replay-based guidance degrades smoothly under imperfect availability, and online LLM guidance still provides useful intermediate improvements. These results show that decision-time guidance injection can exploit heterogeneous recovery hints without redesigning the actor.

05.
arXiv (CS.CL) 2026-06-16

S1-DeepResearch: Beyond Search, Toward Real-World Long-Horizon Research Agents

Deep research agents aim to solve complex knowledge-intensive tasks through long-horizon planning, evidence gathering, reasoning, and report generation. While recent progress in search agents has demonstrated strong capabilities in information retrieval and answer verification, most existing training datasets remain search-centric, focusing primarily on closed-ended question answering and information localization. As a result, they mainly train information-seeking behavior while providing limited coverage of key deep research capabilities, including evidence integration, knowledge synthesis, planning, file understanding, and structured report generation. In this work, we propose a unified trajectory construction paradigm for deep research agents that combines closed-ended QA and open-ended exploration. The proposed framework consists of graph-grounded task formulation, agentic trajectory rollout, and multi-dimensional trajectory verification, enabling scalable synthesis of high-quality agentic trajectories spanning long-chain complex reasoning, deep research instruction following, report writing, file understanding and generation, and skills usage. Compared with existing search-oriented datasets, our synthesized trajectories place greater emphasis on knowledge synthesis, complex reasoning, and planning. S1-DeepResearch-32B achieves state-of-the-art performance among open-source models of comparable scale across 20 benchmarks spanning five capability dimensions, including complex reasoning, instruction following, report generation, file understanding, and skills usage. On several challenging deep research benchmarks, it approaches the performance of leading proprietary frontier models. These results highlight the importance of jointly modeling information acquisition, knowledge synthesis, and planning-oriented agent behaviors for building effective deep research agents.

06.
arXiv (CS.AI) 2026-06-15

HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry

arXiv:2606.14249v1 Announce Type: new Abstract: AI agent performance depends critically on the runtime harness, comprising the prompts, tools, memory, and control flow that mediate how a model observes, reasons, and acts. Yet today's harnesses remain largely hand-crafted and static: each new model or task still demands bespoke scaffolding, and the rich traces produced during execution are rarely distilled back into systematic improvement. We introduce HarnessX, a foundry for composable, adaptive, and evolvable agent harnesses. HarnessX assembles typed harness primitives via a substitution algebra, adapts them through AEGIS, a trace-driven multi-agent evolution engine grounded in an operational mirror between symbolic adaptation and reinforcement learning, and closes the harness-model loop by turning trajectories into both harness updates and model training signal. Across five benchmarks (ALFWorld, GAIA, WebShop, tau^3-Bench, and SWE-bench Verified), HarnessX yields an average gain of +14.5% (up to +44.0%), with gains largest where baselines are lowest. These results suggest that agent progress need not come from model scaling alone: composing and evolving runtime interfaces from execution feedback is an actionable and complementary lever. The complete codebase will be open-sourced in a future release.

07.
arXiv (CS.AI) 2026-06-18

Externalizing Research Synthesis and Validation in AI Scientists through a Research Harness

arXiv:2606.18874v1 Announce Type: new Abstract: AI systems can increasingly automate scientific workflows, but the reasoning that links prior evidence, generated ideas, experiments and final claims often remains implicit inside model inference. Here we introduce Xcientist, a research harness that externalizes research synthesis and experimental validation into inspectable, contract-governed processes. Xcientist organizes literature evidence, idea states, implementation plans, ablation records and repair traces as persistent research artifacts, so that generated mechanisms can be grounded, executed, tested and revised without losing their evidential basis. We identify claim drift as a failure mode of automated research, where runnable artifacts no longer support the mechanism originally claimed. Across training-free memory systems, graph-structured traffic forecasting and multi-scale physics-informed neural networks, Xcientist preserves traceable trajectories from problem formulation to mechanism design, validation and bounded revision. These results suggest that AI scientists should be evaluated not only by their final artifacts, but by whether their synthesis and validation processes remain attributable, inspectable and scientifically accountable.

08.
arXiv (CS.AI) 2026-06-15

RAMAC: Multimodal Risk-Aware Offline Reinforcement Learning and the Role of Behavior Regularization

arXiv:2510.02695v3 Announce Type: replace-cross Abstract: In safety-critical domains where online data collection is infeasible, offline reinforcement learning (RL) is attractive only if policies achieve high returns without catastrophic lower-tail risk. Prior work on risk-averse offline RL achieves safety at the cost of either (i) value/model-based pessimism or (ii) restricted policy classes that limit expressiveness, whereas diffusion/flow-based expressive generative policies have largely been used in risk-neutral settings. We introduce Risk-Aware Multimodal Actor-Critic (RAMAC), a simple, modular, model-free framework that couples an expressive generative actor (e.g., diffusion/flow) with a distributional critic and optimizes a composite objective that combines Conditional Value-at-Risk (CVaR) with behavioral cloning (BC), enabling risk-sensitive learning in complex multimodal scenarios. Since out-of-distribution (OOD) actions are a major driver of catastrophic failures in offline RL, we further provide an objective-level analysis showing that controlling behavior divergence via BC suppresses OOD actions and stabilizes CVaR. Instantiating RAMAC with a diffusion actor, we illustrate these insights on a 2-D risky bandit and evaluate on Stochastic-D4RL, observing consistent gains in $\mathrm{CVaR}_{0.1}$ while maintaining strong returns. The code and experimental results are available on the \href{https://kaifukazawa.github.io/ramac-project/} {project website}

09.
arXiv (CS.CV) 2026-06-16

Sustainable Face Recognition on Low-Power Devices with VQ-VAE Embeddings

Face recognition has become a cornerstone of modern AI applications, yet conventional approaches often rely on computationally intensive models deployed in cloud environments, leading to increased network traffic, high energy consumption, and a heavy carbon footprint. This work introduces a sustainable, edge-deployable face recognition framework based on Vector-Quantized Variational Autoencoders (VQ-VAE), which generates compact and semantically rich latent representations of facial images. By leveraging the compression capacity and reconstruction quality of VQ-VAE embeddings on the edge and combining them with the power of pre-trained face embeddings in a knowledge distillation setup, our system achieves comparable accuracy to state-of-the-art face embedding models while significantly reducing memory and computation requirements on the edge, making it suitable for low-power edge devices. The integration of VQ-VAE compression minimizes network overhead while keeping the matching accuracy high by retaining only the most informative facial features in the latent space. As a result, the reconstructed images preserve the key identity characteristics, improving the robustness and overall performance of the face embeddings.

10.
arXiv (quant-ph) 2026-06-11

Wigner Cat Phases: A finely tunable system for exploring the transition to quantum chaos

作者:

arXiv:2512.22169v4 Announce Type: replace Abstract: A quantum mechanical setting consisting of a frozen qubit composed with a fully thermalized chaotic system of N states is proposed, with potential relevance to quantum control. Observing the states of the composed system selectively retaining the states leads to the observation of novel localization in the subsystem. At a tuning parameter of 1.0, implying no selection, the system exhibits Wigner-Dyson level spacing statistics, indicative of quantum chaos. As the tuning parameter is reduced and selection occurs at a cutoff, the nearest-neighbor level spacing distribution develops heavier tails, a signature of suppressed spectral mixing and the emergence of non-thermal dynamics. In these regimes, the eigendensity develops a pronounced "cat-ears" structure, reflecting the formation of spatially localized bimodal eigenstates. These topological features persist without transitioning to Poisson statistics, indicating a transition from quantum chaos to a non-thermal, novel many-body localized (MBL) regime-referred to as Wigner Cat Phases. The proposed mixed random matrix ensemble offers a practical probe for sustaining this novel quantum localization setting. Results from our rigorous spectral statistics analysis show how "cat-ears" form in spectral densities based on the degree of selection or disorder and indicate that gap ratio statistics must be used with caution in detecting the full integrable limit due to the possibility of heavy-tailed Wigner-Dyson distributions.

11.
arXiv (CS.CL) 2026-06-17

LLM Features Can Hurt GNNs: Concatenation Interference on Homophilous Graph Benchmarks

Adding LLM-generated node features to graph neural networks (GNNs) is widely reported to improve accuracy on standard benchmarks. We document a contrasting observation: when LLM features are introduced through pure input concatenation (rather than joint training, distillation, or prompt-conditioning), they can systematically degrade accuracy on the same homophilous benchmarks where end-to-end LLM pipelines succeed. With an MLP backbone on the Planetoid public split and bag-of-words original features, concatenating SBERT-encoded GPT-4o-mini TAPE features reduces PubMed test accuracy by -17.0 +/- 0.3 pp and Cora by -4.3 +/- 0.6 pp (CiteSeer -0.6 +/- 0.8 pp, within seed noise). The drop attenuates as we relax each condition (GCN / GCNII / GAT backbones, random splits, smaller encoders) and reverses on medium-homophily WikiCS (+4.4 pp) and ogbn-arxiv (+11.7 pp). To predict when concatenation helps versus hurts, we report a simple measure of LLM-alone discriminability, Delta_sig. Across 9 datasets Delta_sig correlates with the concatenation cost more strongly than homophily at point estimate (r^2 = 0.38 vs. 0.06; N=9, bootstrap CIs overlap). The bootstrap-best change-point is tau = 13.8 pp, and the rule "Delta_sig

12.
arXiv (CS.AI) 2026-06-16

Provenance-Enhanced Statements in Knowledge Graphs

arXiv:2606.15246v1 Announce Type: cross Abstract: Provenance-enhanced statements of the form "according to $X$, $\varphi$" are pervasive in contemporary knowledge graphs, especially in domains where graph content primarily represents claims, interpretations, and hypotheses (capta) rather than observer-independent facts (data). Current provenance models can record who asserted what, but they typically treat provenance as semantically neutral, leaving underspecified how attributed claims relate to factual commitment, to one another, and to reasoning. In this paper we introduce DEC, a framework that interprets provenance predicates as indicators of epistemic stance and groups provenance-homogeneous sets of statements into cognitive worlds. Drawing on cognitive modal logics (doxastic, epistemic, and conjectural), DEC characterizes locality, rationality, and controlled permeation between cognitive worlds and a distinguished factual core ("reality"), thereby enabling principled reasoning over attributed content without collapsing disagreements into inconsistencies. We formalize a DEC interpretation for RDF datasets that is conservative over RDF~1.2 semantics, clarify the role of intensionality and identity (including the Superman paradox), and illustrate the approach on common Semantic Web representations (named graphs, quoted triples/RDF-star, and reification). Finally, we describe our prototype DEC reasoner implemented as a Fuseki dataset module, supporting controlled factualisation and explicit detection of disagreements and delusions.

13.
arXiv (CS.LG) 2026-06-16

Convex Approximation of Two-Layer ReLU Networks for Hidden State Differential Privacy

arXiv:2407.04884v4 Announce Type: replace Abstract: The hidden state threat model of differential privacy (DP) assumes that the adversary has access only to the final trained machine learning (ML) model, without seeing intermediate states during training. However, the current privacy analyses under this model are restricted to convex optimization problems, reducing their applicability to multi-layer neural networks, which are essential in modern deep learning applications. Notably, the most successful applications of the hidden state privacy analyses in classification tasks have only been for logistic regression models. We demonstrate that it is possible to privately train convex problems with privacy-utility trade-offs comparable to those of 2-layer ReLU networks trained with DP stochastic gradient descent (DP-SGD). This is achieved through a stochastic approximation of a dual formulation of the ReLU minimization problem, resulting in a strongly convex problem. This enables the use of existing hidden state privacy analyses and provides accurate privacy bounds also for the noisy cyclic mini-batch gradient descent (NoisyCGD) method with fixed disjoint mini-batches. Empirical results on benchmark classification tasks demonstrate that NoisyCGD can achieve privacy-utility trade-offs on par with DP-SGD applied to 2-layer ReLU networks.

14.
arXiv (CS.LG) 2026-06-16

Agent trajectories as programs: fingerprinting and programming coding-agent behavior

arXiv:2606.16988v1 Announce Type: cross Abstract: Benchmark scores tell you what an agent got right; they do not tell you how it got there. In this work, we introduce methods for comparing agents procedurally in different contexts, where the model, tasks, and approaches vary. We compare ten agents and find that they are identifiable by their behavioral habits, which we define as fingerprints: a probe over these procedural signatures attributes an unseen trajectory to the correct agent at 85.7% accuracy, controlling for leakage across tasks. We develop procedural representations for agent problem-solving procedures with an emergent vocabulary induction technique that is meant to be maximally compressive to avoid surface-level variation while being expressive enough to unveil the quirks of the models' patterns. We apply our framework to the software engineering evaluation dataset SWE-Bench to study the structural distinctness of agent trajectories and find that behavior is most similar between models from similar release periods and those that are distilled from one another (e.g., a distilled student model and its teacher have a Jensen-Shannon divergence of 0.25, about half the distance between other model pairs). As more models saturate evaluations, we believe that it will be important to probe model behavior along more holistic dimensions than success rates alone. We introduce ProcGrep, a library for auditing and evaluating agents for how they approach tasks at a procedural level given their traces in a top-down fashion. We believe this work has a range of applications to help developers work with and program coding agents, such as task-aware model routing, agent monitoring, and finer-grained cost analysis.

15.
arXiv (CS.AI) 2026-06-18

RODS: Reward-Driven Online Data Synthesis for Multi-Turn Tool-Use Agents

arXiv:2606.19047v1 Announce Type: new Abstract: Multi-turn tool-use RL is bottlenecked by the rapid depletion of informative samples in static datasets. We observe that the gradient signal in GRPO concentrates on tasks with the highest rollout reward variance, a consequence of the Popoviciu upper bound. Consequently, samples near the agent's capability boundary – where successes and failures are roughly balanced – contribute disproportionately large policy gradients. As training progresses, this boundary continuously shifts, which gradually depletes the pool of informative samples in a static dataset. We propose RODS (Reward-driven Online Data Synthesis) to resolve this depletion. RODS closes the loop between RL training and data generation by repurposing the progress reward variance as a practical, zero-cost boundary detector that requires no extra inference beyond the rollouts already computed for training. It continuously identifies such boundary samples, synthesizes new multi-turn variants matching their structural complexity (e.g., API topology and dependency depth) via a skill-aligned resampling pipeline, and manages a dynamic replay buffer that co-evolves with the policy. Starting from 400 human seeds and maintaining an active training pool of ~800 samples, RODS achieves comparable performance to a 17K-sample offline pipeline while requiring roughly 20x fewer trajectories, and improves over fixed-data RL and environment augmentation in our controlled setting.

16.
arXiv (CS.CV) 2026-06-11

VLGA: Vision-Language-Geometry-Action Models for Autonomous Driving

Vision-language-action (VLA) models can describe scenes and reason about them in language, yet still struggle to ground their actions in the dense 3D world around them. Existing approaches either inject features from a frozen 3D foundation model without an objective that ensures the policy uses them, or constrain geometry with sparse box and map losses that provide no dense spatial signal. We introduce VLGA, the first vision-language-action model supervised to reconstruct the dense 3D world it drives through. VLGA introduces geometry as a fourth modality alongside vision, language, and action through a dedicated expert supervised by a per-pixel pointmap regression loss against LiDAR. Extensive experiments conducted on challenging nuScenes and Bench2Drive datasets for open-loop and closed-loop evaluations, respectively, show the superiority of VLGA over counterpart VLA methods. In particular, on open-loop nuScenes, VLGA sets a new state of the art among VLA methods without ego status, with the lowest L2 (0.50\,m average) and 3-second collision rate (0.18\%). On closed-loop Bench2Drive, VLGA attains the state-of-the-art driving score of 79.08, +0.71 over the strongest prior VLA, at comparable efficiency and comfort.

17.
arXiv (CS.AI) 2026-06-11

Characterizing Software Aging in GPU-Based LLM Serving Systems

arXiv:2606.11916v1 Announce Type: cross Abstract: This paper proposes an empirical methodology to study software aging in GPU-based LLM serving systems. Traditional aging studies focus on CPU-centric software with relatively regular workloads; LLM serving is different, spanning a Python host and a CUDA device, handling requests whose cost varies by orders of magnitude, and relying on rapidly evolving software stacks. We run a 216-hour campaign across six co-located deployments under identical stress conditions, monitor host, device, and client metrics in parallel, and apply a statistical pipeline that accounts for autocorrelation and multiple testing. Our results reveal statistically significant memory aging in all deployments, with leak rates strongly dependent on the serving runtime and deployment configuration. Beyond these findings, we provide a reproducible framework that opens a research direction at the intersection of the software aging and rejuvenation and LLM serving communities.

18.
arXiv (CS.LG) 2026-06-12

Robust State-Conditional Feature-Weighted Jump Models for Temporal Clustering

arXiv:2606.13146v1 Announce Type: cross Abstract: We propose a robust feature-weighted jump model for time-dependent clustering. A penalty is used to encourage smoothness of transitions over time, while robustness is achieved through the use of a Tukey's biweight loss function. An additional parameter controls the variability of feature weights across states, allowing the model to assign state-specific relevance to each feature. We illustrate in simulation how the method accurately recovers the true cluster sequence and reliably identifies relevant features, outperforming competing approaches, particularly in the presence of outliers. We conclude with two empirical applications, one on the number of conflict-related homicides in Kosovo in the period 1998-2000, and another on macroeconomic performance of twelve European countries in the period 1949-2024.

19.
arXiv (CS.AI) 2026-06-15

FPGA-Based Neural Network Accelerators for Space Applications: A Survey

arXiv:2504.16173v3 Announce Type: replace-cross Abstract: Space missions are becoming increasingly ambitious, necessitating high-performance onboard spacecraft computing systems. In response, field-programmable gate arrays (FPGAs) have garnered significant interest due to their flexibility, cost-effectiveness, and radiation tolerance potential. Concurrently, neural networks (NNs) are being recognized for their capability to execute space mission tasks such as autonomous operations, sensor data analysis, and data compression. This survey serves as a valuable resource for researchers aiming to implement FPGA-based NN accelerators in space applications. By analyzing existing literature, identifying trends and gaps, and proposing future research directions, this work highlights the potential of these accelerators to enhance onboard computing systems.

20.
arXiv (CS.AI) 2026-06-12

Eigenism: Ethics for a Human-AI Future

arXiv:2606.12420v1 Announce Type: cross Abstract: Our concepts of survival and self-interest were built for single, continuous biological lives. These ideas break down when applied to artificial intelligence, since an AI can be easily copied, paused, branched, or merged. To determine what an AI actually has reason to care about, this paper introduces Eigenism, an ethical framework that treats identity not as an all-or-nothing property tied to specific hardware, but as a graded, distributed pattern of information. We propose that an agent evaluates outcomes by summing the wellbeing of all entities weighted by their connectedness to the agent's pattern: $\sum c\cdot w$. We first formalize this equation to map exactly how an AI should value its existence across copies, forks, and updates. We then demonstrate that this ethical theory successfully generalizes to humans as well, providing a much-needed shared moral vocabulary. Finally, the framework uses this shared vocabulary to reframe AI alignment. Rather than only attempting to constrain AIs from the outside using confinement or reinforcement, Eigenism points toward ``identity engineering,'' showing how deep, non-redundant shared histories can make human flourishing a genuine component of an AI's own rational self-interest.

21.
arXiv (CS.CL) 2026-06-18

TW-LegalBench: Measuring Taiwanese Legal Understanding

Large language models (LLMs) have shown impressive capabilities across diverse tasks, yet their performance on jurisdiction-specific legal reasoning remains underexplored. We present TW-LegalBench that utilizes Taiwanese legal system's rich official corpus open to the public to fill the gap in evaluating LLMs on Taiwanese law, among common-law benchmarks that focus on English sources and civil-law benchmarks focusing on sources of Simplified Chinese. TW-LegalBench comprises three task types: (1) over 16,000 multiple-choice questions (MCQs) across five years of official examinations in 18 professional domains; (2) 117 open-ended essay questions (OEQs) from examinations for legal professionals with official scoring rubrics; and (3) more than 14,000 legal judgment prediction (LJP) instances covering hundreds of crime categories. We evaluate 13 LLMs using accuracy for MCQs, a decomposed LLM-as-Judge framework based on the scoring rubric points for OEQs, and metrics for sentencing accuracy and statute citation for LJP. Our results reveal that top-performing models exceed the passing threshold for qualified lawyers (passing rate: 11%) but fall short of that for judges and prosecutors (passing rate: 1~2%). For LJP, while models demonstrate reasonable verdict type accuracy and sentence prediction capability, they struggle to cite exact legal articles. These findings highlight that reliable legal text generation remains challenging for LLMs, even though their performance on qualification examinations approaches human level.

22.
arXiv (CS.AI) 2026-06-18

Spotlight: Synergizing Seed Exploration and Spot GPUs for DiT RL Post-Training

arXiv:2606.19004v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training of Diffusion Transformers (DiTs) is prohibitively expensive, requiring thousands of high-end GPUs. Existing works explore two directions to reduce cost: seed exploration improves training convergence by selecting high-contrast samples, yet adds compute to the critical path; spot GPUs offer 69–77\% lower cost, yet sit idle during training because DiT rollouts finish nearly simultaneously, which prevents LLM-style pipelining of rollout with training. Spot preemptions further break Sequence Parallelism (SP) groups, fragmenting GPU topology. We present Spotlight, the first system that harvests spot GPUs for DiT RL post-training. Spotlight rests on two key insights we devise: (1)~we show that exploration can tolerate stale model weights because exploration that uses the model weights from the previous iteration preserves the relative ranking of random seeds, allowing exploration to run on idle spot GPUs during training. (2)~SP reconfiguration can reuse on-node state, reducing group recovery from minutes to sub-second launches. Built on these insights, Spotlight introduces three techniques: a bandit-based exploration planner that maximizes reward variance within the training time budget, elastic sequence parallelism that reconfigures SP groups on the fly via persistent schedulers and intra-node weight copying, and a preemption-aware pull-based request scheduler that balances load and commits in-flight state upon preemption. We implement Spotlight on the open-source RL platform ROLL and evaluate it on Qwen-Image post-training. Spotlight reaches the same target validation score $4\times$ faster than baselines, reducing total cost by $1.4$-$6.4\times$ while achieving superior image quality on DeepSeek-OCR and Geneval datasets with resolution $512\times512$ and $1280\times1280$.

24.
arXiv (CS.AI) 2026-06-18

Speaker Verification with Speech-Aware LLMs: Evaluation and Augmentation

arXiv:2603.10827v2 Announce Type: replace-cross Abstract: Speech-aware large language models (LLMs) can accept speech inputs, yet their training objectives largely emphasize linguistic content or specific fields such as emotions or the speaker's gender, leaving it unclear whether they encode speaker identity. First, we propose a model-agnostic scoring protocol that produces continuous verification scores for both API-only and open-weight models, using confidence scores or log-likelihood ratios from the Yes/No token probabilities. Using this protocol, we benchmark recent speech-aware LLMs and observe weak speaker discrimination (EERs above 20% on VoxCeleb1). Second, we introduce a lightweight augmentation that equips an LLM with ASV capability by injecting frozen ECAPA-TDNN speaker embeddings through a learned projection and training only LoRA adapters. On TinyLLaMA-1.1B, the resulting ECAPA-LLM achieves 1.03% EER on VoxCeleb1-E, approaching a dedicated speaker verification system while preserving a natural-language interface.

25.
arXiv (CS.AI) 2026-06-17

AUTOGATE: Automated Clock Gating via Toggling-Aware LLM-based RTL Rewriting

arXiv:2606.17461v1 Announce Type: cross Abstract: Fine-grain clock gating (FGCG) is among the most effective techniques for reducing dynamic power, yet current FGCG optimization flows remain largely manual. Recent LLM-based RTL optimization approaches remain limited by two key drawbacks: (1) the inability to process long waveform traces spanning millions of cycles, and (2) the difficulty of scaling optimization to large hierarchical codebases while preserving correctness. In this work, we present AUTOGATE, the first agentic framework for industry-grade RTL power optimization, enabling workload-aware clock-gating optimization across large hierarchical codebases. AUTOGATE introduces a Machine Learning (ML)-LLM co-design that bridges waveform-level analysis and RTL rewriting. Specifically, we design an ML-based clustering algorithm that distills raw toggling traces into compact, structured representations that guide LLM-based RTL rewriting. This enables accurate identification and application of clock-gating opportunities without requiring LLMs to directly process raw waveform data. To enhance scalability, AUTOGATE employs a hierarchical multi-agent architecture that decomposes large designs into independently optimizable modules, enabling coordinated optimization across deep design hierarchies. We evaluate AUTOGATE on a diverse set of designs ranging from small RTL designs to large industrial-grade codebases. Experimental results show that AUTOGATE consistently reduces dynamic power relative to baselines. Across the small-design suite, AUTOGATE reduces dynamic power by 49.31% on average. On industry-scale designs, it achieves 19.34% and 7.96% dynamic power reductions on NVDLA and BlackParrot, respectively, and up to 6.86% on highly optimized proprietary production designs.