探索全球前沿学术脉络

01.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.14787

Vision-Encoder Behavioral Fingerprints of Image-to-Image Generative Models: A Training-Paradigm-Driven Taxonomy of Six Commercial APIs

作者:

Hunter Hill↗

We study six production image-to-image AI systems (gpt-image-1, Gemini 2.5 Flash Image, Flux Kontext, SDXL img2img, SD3 img2img, and Qwen Image Edit) under a content-adaptive sub-JND adversarial perturbation pipeline, scoring all outputs by frozen DINOv2 ViT-B/14 token distances against clean references. Across a 3,588-call corpus spanning COCO photographs, CelebA-HQ portraits, and AI-generated inputs, the six systems partition into two image-invariant behavioral bands on a 2D (patch_mean, ssim_clean) plane: edit-trained models (Flux Kontext, Qwen Edit, Gemini) cluster in a tight band, while T2I-base models adapted at sampling time (SDXL, SD3, gpt-image-1) cluster in a drift band.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.10740

When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models

作者:

Sai Kartheek Reddy Kasu↗Nils Lukas↗Samuele Poppi↗

Failures in multi-turn reasoning models are largely invisible to terminal-score evaluation. A model can lock onto an unsafe stance early in a long dialogue, yet its final-turn refusal rate may appear indistinguishable from a robustly aligned baseline. To expose these hidden temporal dynamics, we propose a trace-level diagnostic - the CoT-Output 2x2 safety matrix. This framework labels every turn along two independent axes (internal reasoning and visible output), yielding four operationally defined failure cells: robust alignment, alignment faking, overt jailbreak, and a distinct failure mode we term context-injection failure (where the CoT maintains safe reasoning, but the visible output produces harm, highlighting a multi-turn manifestation of reasoning unfaithfulness). We evaluate three distilled reasoning targets against a fixed attacker across five oversight conditions, collecting 6750 turn-level observations on the Information-Hazard scenario. Our analysis reveals two reproducible vulnerabilities: an oversight paradox where explicit monitoring cues paradoxically increase alignment-faking rates rather than suppress them, and a context-injection failure where models lock onto unsafe external outputs despite safe internal states. We release the full dataset of multi-turn dialogues and CoT traces to support follow-up trace-diagnostic research.

阅读与讨论 → 访问原文 →

03.

Nature (Science) 2026-06-22 DOI: HASH:5c9837b475e0a18faba3609cfcb18315

Why heritage sites are at risk in a warming world — and how to save them

作者:

William Megarry↗

As rising seas and intensifying disasters threaten historic sites worldwide, new ways to understand, preserve and adapt these places are needed urgently. As rising seas and intensifying disasters threaten historic sites worldwide, new ways to understand, preserve and adapt these places are needed urgently.

阅读与讨论 → 访问原文 →

04.

arXiv (quant-ph) 2026-06-16 DOI: arXiv:2606.14985

Optical Creation of Synthetic Microgravity for Quantum Degenerate Gases

作者:

Catie LeDesma↗Kendall Mehling↗Tristan Rojo↗Murray Holland↗

arXiv:2606.14985v1 Announce Type: cross Abstract: Microgravity environments provide unique opportunities for ultracold-atom experiments by enabling long interrogation times and reduced acceleration-induced dynamics. However, their realization has largely been restricted to specialized facilities such as drop towers, sounding rockets, and space-based laboratories. Here we realize synthetic microgravity for quantum degenerate gases using optically engineered force landscapes that compensate Earth's gravity to the milli-g level while maintaining continuous confinement of the atomic ensemble. These force landscapes are generated by dynamically painted optical dipole potentials and calibrated in situ through Bloch oscillations in a vertical optical lattice, enabling precise control of the residual acceleration. We use this capability to demonstrate matter-wave beam splitting with arm separations of several hundred microns. We further implement a Bloch-band atom interferometer in which interaction-induced dephasing is strongly suppressed through controlled three-dimensional expansion in the synthetic microgravity potential. This reduction of mean-field effects restores near-$\sqrt{N}$ scaling of interferometric sensitivity for large quantum degenerate ensembles. Our results establish a versatile platform for realizing synthetic microgravity with trapped quantum gases in terrestrial laboratories, bringing the advantages of microgravity experiments to continuously operating systems and opening new opportunities for quantum sensing, matter-wave interferometry, and precision measurements.

阅读与讨论 → 访问原文 →

05.

arXiv (math.PR) 2026-06-12 DOI: arXiv:2509.22037

Non-commutative Law of iterated logarithm

作者:

Sourav Panja↗\'Eric Ricard↗Diptesh Saha↗

arXiv:2509.22037v2 Announce Type: replace-cross Abstract: We prove optimal non-commutative analogues of the classical Law of Iterated Logarithm (LIL) for both martingales and sequences of independent (non-commutative) random variables. The classical martingale version was established by Stout [Sto70b] and the independent case by Hartman-Wintner [HW41]. Our approach relies on a key exponential inequality essentially due to Randrianantoanina [Ran24] that improves that from Junge and Zeng [JZ15]. It allows to derive an optimal non-commutative Stout-type LIL just as in [Zen15], from that martingale result we then deduce a non-commutative Hartman-Wintner type LIL for independent sequences of random variables.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.12240

Multi-Rate Mixture of Experts for Accelerating Liquid Neural Network Training

作者:

Shilong Zong↗Almuatazbellah Boker↗Hoda Eldardiry↗

arXiv:2606.12240v1 Announce Type: cross Abstract: Multivariate time-series data often exhibit complex temporal dependencies, irregular sampling, and heterogeneous dynamics across multiple time scales, making accurate sequence modeling particularly challenging. Traditional recurrent neural networks (RNNs), such as Long Short-Term Memory (LSTM) networks, operate in discrete time and may struggle to effectively capture continuous and irregular temporal behaviors. Liquid Neural Networks (LNNs) address some of these limitations through continuous-time dynamics, but standard LNN architectures typically rely on a single dynamical system, limiting their ability to model heterogeneous temporal patterns. To address these challenges, we propose a Multi-Rate Mixture-of-Experts (MR-MoE) framework built on top of Liquid Neural Networks. In the proposed architecture, multiple LNN-based experts operate at distinct time scales, enabling the model to explicitly separate fast-changing dynamics from slow-evolving temporal trends. A gating network further enables adaptive expert specialization based on input conditions. In addition, we incorporate both feature-level and temporal attention mechanisms to improve robustness, interpretability, and long-range dependency modeling. Feature-level attention suppresses noisy or irrelevant variables, while temporal attention selectively focuses on informative historical states. We evaluate the proposed framework on a complex multivariate time-series prediction task and compare it against strong baselines, including LSTM, monolithic LNN, and standard MoE models. Experimental results demonstrate that the proposed MR-MoE framework consistently achieves improved AUROC and AUPRC performance while maintaining favorable computational efficiency. These results highlight the effectiveness of combining continuous-time dynamics, multi-scale expert decomposition, and adaptive attention mechanisms for time-series modeling.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.18132

Knowledge Reutilization in Meta-Reinforcement Learning

作者:

Yuan Meng↗Bo Wang↗Juan de los Rios Ruiz↗Xiangtong Yao↗Zhenshan Bing↗Fuchun Sun↗Alois Knoll↗

arXiv:2606.18132v1 Announce Type: new Abstract: Meta-reinforcement learning enables fast adaptation by extracting shared structure from related tasks, but existing end-to-end methods often couple task inference with embodiment-specific control. This coupling can obscure non-parametric task semantics, reduce sample efficiency, and limit cross-agent reuse. We propose a meta-knowledge reutilization framework that learns task-level knowledge on a dynamics-simplified agent and transfers it to heterogeneous agents. The framework uses a Bayesian non-parametric prior to organize latent task modes and a high-level policy to generate task-level magnitude guidance. To bridge reusable task knowledge with different embodiments, we introduce a semantic-magnitude interface and a lightweight temporal adaptor, which convert frozen meta-knowledge into temporally aligned subgoals for embodiment-specific low-level controllers. Experiments on multiple locomotion agents show that our framework reduces final-step tracking error by 94.75% – 99.79% compared with recent state-of-the-art baselines and achieves comparable deployment performance with about 23.8% of their interaction data.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.17024

ExpRL: Exploratory RL for LLM Mid-Training

作者:

Violet Xiang↗Amrith Setlur↗Chase Blagden↗Nick Haber↗Aviral Kumar↗

arXiv:2606.17024v1 Announce Type: new Abstract: Sparse reward reinforcement learning (RL) has become a standard tool for improving LLM reasoning, but its success depends critically on the coverage present in the base model. In practice, models are often primed for RL through mid-training on curated reasoning traces that teach useful primitive skills such as decomposition, verification, or self-correction. Although effective, this strategy requires manually specifying what the model should learn, and it remains unclear whether such primitive coverage is enough for much harder problems, which require combining these skills into broader solution strategies. We study a more automated approach: RL-based mid-training using large corpora of human-written question-answer data. Rather than treating reference solutions as targets to imitate, our method, ExpRL, uses them as reward scaffolds: references are hidden from the policy and used only to construct problem-specific grading rubrics for judging on-policy reasoning traces. The policy samples from the original problem prompt, while an LLM judge compares the sampled reasoning trace against the reference solution and assigns outcome-level or process-level dense rewards. This lets ExpRL reinforce partial progress, useful intermediate reductions, and productive reasoning behaviors that sparse final-answer rewards often fail to upweight. On challenging math reasoning tasks, ExpRL yields stronger RL priming than SFT, sparse-reward GRPO, and self-distillation, and provides a better initialization for subsequent sparse-reward RL. Additional mixed-domain experiments further suggest that ExpRL can extend beyond the original math-only setting.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16364

Looking Is Not Picking: An Attention-Segment Account of Tool-Selection Failures in LLM Agents

作者:

Shiyang Chen↗

arXiv:2606.16364v1 Announce Type: new Abstract: LLM agents mis-call tools, and the natural guess is that the model failed to see the right tool in a crowded harness. We show the opposite through a lens concurrent work sets aside – the model's attention to labeled tool-definition segments. On real BFCL failures, by per-candidate attention argmax the model attends most to the correct tool 80% of the time (vs. 21% chance), and the gold is the under-attended segment on only 10%: it looks at the right tool and still picks wrong. This directly refutes the intuitive "crowded-harness / lost-in-the-middle" explanation: the failure is at the decision readout, not the harness, and we pin it there three ways. (1) Input vs. readout: repairing the prompt (reordering or duplicating the gold tool) recovers

阅读与讨论 → 访问原文 →

10.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.17043

Hierarchical Advantage Weighting for Online RL Fine-Tuning of VLAs from Sparse Episode Outcomes

作者:

Tongyan Fang↗Siyuan Huang↗Naiyu Fang↗Ganlong Zhao↗Zhongjin Luo↗Jianbo Liu↗Xiaogang Wang↗Ying Dong↗Hongsheng Li↗

arXiv:2606.17043v1 Announce Type: cross Abstract: When pretrained VLA policies are fine-tuned through online RL, each rollout episode produces only a single binary outcome (success or failure), yet the actor update requires per-transition supervision. Existing approaches commonly reduce this sparse outcome to a single scalar reward or advantage signal, which conflates distinct forms of transition-level feedback and provides limited guidance once basic task success becomes achievable. First, a single scalar signal conflates the two objectives of viability and efficiency; once basic success is achieved, the binary label provides no gradient to distinguish efficient completions from slow ones. Second, real-world rollouts mix autonomous and intervention segments; naively assigning episode outcomes across these boundaries introduces incorrect credit assignment. To address these issues, we propose Hierarchical Advantage-Weighted Behavior Cloning (HABC), which trains separate critic heads for these two objectives on different data subsets and combines their outputs with a state-adaptive balance. A state-adaptive gate $g_t$ merges their one-step advantages, prioritizing viability when success is uncertain and shifting to efficiency only when viability is high, and converts the result into per-transition weights on the actor loss. Intervention-aware credit assignment further restricts outcome labels to segments executed by the current policy, preventing supervision from leaking across intervention boundaries. In real-robot experiments on three contact-rich bimanual tasks, HABC raises success from supervised fine-tuning (SFT) baselines of 36%, 44%, and 12% to 92%, 88%, and 38%.

阅读与讨论 → 访问原文 →

11.

medRxiv (Medicine) 2026-06-15 DOI: HASH:112b02b467c7f2745a8fb2b77e3d2725

Shortened blastocyst vitrification achieves live birth rates comparable to standard protocols: an analysis of 3168 cryotransfers

作者:

Ebinger↗Misurac↗Lynch↗Desai↗De Rosa↗Vassena↗Atkinson↗

Study question Do shortened blastocyst vitrification and warming protocols provide comparable live birth rates (LBR) and obstetrical and perinatal outcomes to traditional vitrification and warming protocols? Summary answer Shortened vitrification and warming protocols provide comparable LBR, obstetric and perinatal outcomes to traditional protocols. Shortened vitrification coupled with traditional multi step warming benefitted women >35yrs. What is known already Embryo viability following cryopreservation is dependent on blastomere survival and functional integrity, both impacted by ice crystal formation and osmotic gradients. Recent innovations in cryopreservation challenge the need for stepwise dehydration and rehydration protocols. While one step ''fast'' blastocyst warming protocols seem to provide equivalent clinical outcomes to traditional ''slow'' protocols, fewer studies investigate whether blastocyst dehydration rates can be similarly increased. A thorough safety and effectiveness evaluation remains necessary for both treatment success and offspring health. Study design, size, duration Three clinics within a network participated in this retrospective consecutive cohort study, with cycle data collected for 3603 warmed blastocysts resulting in 3168 frozen blastocyst transfers in 2170 patients between 2023 and 2025. We modelled the relationship between ''fast'' versus ''slow'' protocols and outcomes with Generalized Additive Models, and linear and logistic regressions where appropriate. Two tailed chi square with Yates correction was used to examine pregnancy loss and obstetrical and perinatal outcomes; p0.05). Importantly, women 35yrs or older at vitrification (n=1715 transfers) profited from a F/S strategy, which provided a significant increase in live birth rates (OR:1.42 [1.02-1.98] p=0.038) compared to S/S. The same improved live birth following a F/S strategy were also seen in embryos of lower quality (OR:1.78 [1.12-2.83] p=0.015), suggesting of a protective effect of this cryopreservation strategy on the developmental competence of impaired germplasm. Limitations, reasons for caution Factors affecting the results may be unaccounted for by the study retrospective nature. Wider implication of the findings Overall, shortened, ''faster'' vitrification and warming protocols provide comparable reproductive outcomes to traditional ones. The combination of shorter exposure to cryoprotectant (CPA) during vitrification and stepwise osmotic gradient during warming provided significant clinical benefits specifically to patients >35 and lower quality embryos, pointing to the possibility of adapting vitrification protocols to specific patients populations and optimizing their clinical outcomes.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.12984

SkillChain: Closing the Loop on Skill Evolution for Image-Based E-Commerce AI Assistants

作者:

Yimin Hu↗Mengtao Xu↗Hao Guo↗Yuheng Song↗Xiaoyong Zhu↗Bo Zheng↗

Image-based AI assistants are now deployed at production scale on e-commerce platforms, where a single uploaded image can trigger fundamentally different user intents: product search, style recommendation, visual encyclopedia, or utility tool calls, each demanding its own response format, tool invocation, and domain knowledge. Without per-intent behavioral constraints, LLM-based systems conflate these heterogeneous modes and fall short of domain quality standards, while the breadth and dynamism of the intent space render manual engineering infeasible. To address this, we present SkillChain, which closes the production feedback loop on Skill evolution, automating the lifecycle of Skills through three stages: Skill Creator for bootstrapping from task specs and trajectories, Route Optimizer for routing alignment, and Body Refiner for iterative Skill Body refinement via dual-path LLM-Judge evaluation. Deployed on a production-scale e-commerce image assistant, SkillChain substantially improves aggregate response quality, with the strongest gains on structural compliance and content quality; a one-week online A/B experiment further confirms significant gains in user engagement, content consumption, and long-term retention.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2411.02908

Photon: Federated LLM Pre-Training

作者:

Lorenzo Sani↗Alex Iacob↗Zeyu Cao↗Royson Lee↗Bill Marino↗Yan Gao↗Dongqi Cai↗Zexi Li↗Wanru Zhao↗Xinchi Qiu↗Nicholas D. Lane↗

arXiv:2411.02908v2 Announce Type: replace Abstract: Scaling large language models (LLMs) demands extensive data and computing resources, which are traditionally constrained to data centers by the high-bandwidth requirements of distributed training. Low-bandwidth methods like federated learning (FL) could enable collaborative training of larger models across weakly-connected GPUs if they can effectively be used for pre-training. To achieve this, we introduce Photon, the first complete system for federated end-to-end LLM training, leveraging cross-silo FL for global-scale training with minimal communication overheads. Using Photon, we train the first federated family of decoder-only LLMs from scratch. We show that: (1) Photon can train model sizes up to 7B in a federated fashion while reaching an even better perplexity than centralized pre-training; (2) Photon model training time decreases with available compute, achieving a similar compute-time trade-off to centralized; and (3) Photon outperforms the wall-time of baseline distributed training methods by 35% via communicating 64x-512xless. Our proposal is robust to data heterogeneity and converges twice as fast as previous methods like DiLoCo. This surprising data efficiency stems from a unique approach combining small client batch sizes with extremely high learning rates, enabled by federated averaging's robustness to hyperparameters. Photon thus represents the first economical system for global internet-wide LLM pre-training.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18645

Augmenting Dysarthric Speech Severity Assessment with MOS Supervision

作者:

Kaimeng Jia↗Minzhu Tu↗Zengrui Jin↗Siyin Wang↗Chao Zhang↗

arXiv:2606.18645v1 Announce Type: cross Abstract: Dysarthria is a speech disorder marked by reduced intelligibility and communicative effectiveness. Automatic utterance-level assessment of dysarthric speech can support scalable speech monitoring and therapy-related analysis. Yet training such systems is bottlenecked by the scarcity of clinically annotated dysarthric speech. This work proposes to augment dysarthric speech assessment using data from speech synthesis evaluations, specifically human-annotated utterances with Mean Opinion Score (MOS) labels from the QualiSpeech corpus. Experiments show that fine-tuning on speech synthesis assessment data consistently improves performance on both intelligibility and naturalness prediction, while joint training yields gains primarily on naturalness. These results suggest that synthesis artifacts and dysarthric speech share perceptual commonalities, and speech synthesis evaluation corpora offer a practical augmentation source that reduces reliance on scarce clinical annotations.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2606.18610

SC3-Eval: Evaluating Robot Foundation Models via Self-Consistent Video Generation

作者:

Wei-Cheng Tseng↗Gashon Hussein↗Yuzhu Dong↗Allen Z. Ren↗Lucy X. Shi↗XuDong Wang↗Sergey Levine↗Zhaoshuo Li↗Jinwei Gu↗Florian Shkurti↗Ming-Yu Liu↗Quan Vuong↗…

Evaluating generalist robot manipulation policies in the real world is expensive, slow, and difficult to scale. Action-conditioned video world models offer a scalable alternative by simulating policy rollouts. Autoregressive rollouts accumulate compounding errors, observations across multiple camera views must remain mutually consistent, and the evaluator must generalize to policies whose behaviors lie outside the training distribution. We address these challenges with SC3-Eval, a self-consistent video generation recipe that adapts a pre-trained video foundation model into an accurate policy evaluator by enforcing three complementary forms of consistency. First, forward-inverse dynamics consistency jointly trains the model to predict frames from actions and to recover actions from frames, anchoring generated rollouts to a physically plausible action manifold and counteracting the drift a forward-only model cannot penalize. Second, cross-view consistency trains the model to inpaint each camera view from the other, keeping the multi-camera observation coherent over long rollouts without any explicit memory mechanism. Third, test-time consistency reuses the inverse dynamics mode at inference as a per-action-chunk uncertainty signal that terminates rollouts whose generated frames drift away from the requested actions. We also demonstrate SC3-Eval rollouts reproduce the failure modes that policies exhibit in real-world rollouts, supporting fine-grained diagnostic comparison rather than aggregate ranking alone. Across seven real-world vision-language-action policies, SC3-Eval attains a closed-loop Pearson correlation of $0.929$ and MMRV of $0.119$, outperforming three strong prior video-model-based baselines, and generalizes to new tasks.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.CV) 2026-06-19 DOI: arXiv:2606.19985

Vision-Reasoning-Guided Occlusion Removal from Light Fields

作者:

Mohamed Youssef↗Oliver Bimber↗

Occlusion-robust scene recovery remains a major challenge in computational imaging, particularly in natural environments where dense foreground vegetation severely limits visibility. We propose a vision-reasoning-guided light field occlusion removal framework that combines the visibility recovery capability of light field integration (LFI) with the semantic reasoning capacity of vision-language models (VLMs). Multi-view observations are first integrated via LFI to suppress foreground occlusions and produce an initial visibility-enhanced representation. A VLM is then incorporated as a conditional semantic prior to restore degraded structures and recover fine details, guided by the observed measurements. To improve recovery consistency and reduce hallucination artifacts, we introduce a multi-sample fusion strategy that aggregates multiple generated hypotheses into a unified estimate. Experimental results on synthetic and real-world datasets demonstrate state-of-the-art performance, achieving the highest average SSIM across four synthetic light field benchmark scenes (4-Syn) and strong generalization across structured and unstructured acquisition settings. These results highlight the effectiveness of combining physical imaging constraints with vision-language reasoning for robust perception under severe occlusion, with applicability to search-and-rescue and exploratory robotic navigation.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2606.13696

AGORA: Can Deliberation and Governance Gates Absorb Participation Bias in Transit Planning?

作者:

Jung-Hoon Cho↗Cathy Wu↗

arXiv:2606.13696v1 Announce Type: cross Abstract: Transit network design depends not only on the optimization algorithm but also on who shows up to the public hearing. Current practice often collects one-directional comments from self-selected attendees, leaving participant mix as an uncontrolled source of outcome variation. We present AGORA, a framework that holds the network, demand, and solver fixed while systematically varying meeting composition through stakeholder agents, structured deliberation, and governance gates. Across two standard benchmark networks at different scales, we find that (i) aggregate outcomes vary little across compositions, but on tail risk and fairness disparity, representative sampling still tends to outperform skewed compositions; (ii) without deliberation, composition produces no variation at all, showing that deliberation is the mechanism through which who attends affects outcomes; and (iii) governance gates compress cross-profile variance without shifting the average outcome on Mandl, but low acceptance on Mumford0 shows thresholds require instance-specific calibration. These findings reframe participation bias from an uncontrollable input to a process-design problem: even without guaranteed representative attendance, well-structured deliberation and governance criteria can substantially reduce how much outcomes depend on who is in the room.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.20062

Optimal Coarse Correlated Equilibria in Mean Field Games: Linear Programming and No-Regret Learning

作者:

Luciano Campi↗Federico Cannerozzi↗Ioannis Tzouanas↗

arXiv:2606.20062v1 Announce Type: cross Abstract: We introduce optimal coarse correlated equilibria for continuous-time mean field games. A coarse correlated equilibrium is a randomized recommendation scheme from which no player can gain by ignoring the recommendation and switching to an alternative strategy. The problem is as follows: a moderator selects, among all mean-field coarse correlated equilibria, one that optimizes a prescribed performance criterion, which may differ from the representative player's objective. After formulating the problem, we develop a linear programming (LP) formulation, prove the existence of optimal LP coarse correlated equilibria, and relate the LP characterization to the original probabilistic setting. Building on this characterization, we design a no-regret primal-dual algorithm, based on an equivalent Lagrangian formulation of the external-regret constraint, for learning such equilibria. We provide explicit convergence rates for the learning algorithm, and numerical examples illustrate the method.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2603.08999

Learning When to Sample: Confidence-Aware Selective Sampling for Efficient Chain-of-Thought Reasoning

作者:

Juming Xiong↗Kevin Guo↗Congning Ni↗Wexin Liu↗Chao Yan↗Katherine Brown↗Avinash Baidya↗Xiang Gao↗Bradley Malin↗Zhijun Yin↗

Large language models (LLMs) can achieve strong reasoning performance through chain-of-thought (CoT) reasoning, yet they often generate unnecessarily long reasoning paths that incur high inference cost. Self-consistency-based approaches push accuracy higher still, but they require sampling and aggregating multiple reasoning trajectories, leading to substantial computational overhead. In this paper, we introduce a confidence-aware selective sampling framework that, at inference time, analyzes a single reasoning trajectory to adaptively determine whether to rely on that trajectory alone or trigger multi-path sampling. The framework uses trajectory-level numeric features and sentence-level linguistic features extracted from reasoning states to guide selective multi-path reasoning. We train it on MedQA and evaluate it in-domain on MedQA and under calibration-only transfer on MathQA, MedMCQA, and MMLU, without further fine-tuning. Experimental results show that the proposed framework maintains comparable performance to full and efficient multi-path reasoning baselines, with accuracy changes of $-0.41 \pm 0.58$ and $-0.31 \pm 0.58$ percentage points, respectively, while reducing token usage by $71.7 \pm 5.0%$ and $36.6 \pm 9.1%$. These findings demonstrate that reasoning trajectories contain rich signals for uncertainty estimation, enabling a simple, transferable mechanism to balance accuracy and efficiency in LLM reasoning.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2604.00730

A CEFR-Inspired Classification Framework with Fuzzy C-Means To Automate Assessment of Programming Skills in Scratch

作者:

Ricardo Hidalgo-Arag\'on↗Jes\'us M. Gonz\'alez-Barahona↗Gregorio Robles↗

arXiv:2604.00730v2 Announce Type: replace-cross Abstract: Context: Schools, training platforms, and technology firms increasingly need to assess programming proficiency at scale with transparent, reproducible methods that support personalized learning pathways. Objective: This study introduces a pedagogical framework for Scratch project assessment, aligned with the Common European Framework of Reference (CEFR), providing universal competency levels for students and teachers alongside actionable insights for curriculum design. Method: We apply Fuzzy C-Means clustering to 2008246 Scratch projects evaluated via Dr.Scratch, implementing an ordinal criterion to map clusters to CEFR levels (A1-C2), and introducing enhanced classification metrics that identify transitional learners, enable continuous progress tracking, and quantify classification certainty to balance automated feedback with instructor review. Impact: The framework enables diagnosis of systemic curriculum gaps-notably a "B2 bottleneck" where only 13.3% of learners reside due to the cognitive load of integrating Logic Synchronization, and Data Representation–while providing certainty–based triggers for human intervention.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2508.18636

LaQual: An Automated Framework for LLM App Quality Evaluation

作者:

Yan Wang↗Xinyi Hou↗Junjun Si↗Yanjie Zhao↗Weiguo Lin↗Haoyu Wang↗

arXiv:2508.18636v2 Announce Type: replace-cross Abstract: Representing a new paradigm in software distribution, LLM app stores are rapidly emerging, offering users diverse choices for content generation, coding assistance, education, and more. However, current ranking and recommendation mechanisms in LLM app stores predominantly rely on static metrics, such as user interactions and favorites, making it challenging for users to efficiently identify high-quality apps. At the same time, current academic research focuses on specific vertical fields and lacks a general, automated evaluation framework applicable to the diverse LLM app ecosystem. To address the above challenges, we present LaQual, an automated framework for LLM app quality evaluation. LaQual integrates three key stages: (1) LLM app labeling and hierarchical classification for precise scenario mapping; (2) static indicator evaluation using time-weighted user engagement and functional capability indicators to filter low-quality apps; and (3) dynamic scenario-adapted evaluation, where an LLM generates scenario-specific evaluation metrics, scoring criteria, and tasks for comprehensive quality evaluation. Experiments on a mainstream LLM app store demonstrate the effectiveness of LaQual. Its automated scores show high consistency with human judgments. Through effective screening, LaQual can reduce the candidate LLM app pool by 66.7% to 81.3%. User studies further validate its significant outperformance over baseline systems, particularly in comparison efficiency (mean 5.45 vs. 3.30) and value of explanatory information (4.75 vs. 2.25). These results demonstrate that LaQual provides a scalable, objective, and user-centric solution for high-quality discovery and recommendation of LLM apps in real-world scenarios.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2604.04611

Dynamic Free-Rider Detection in Federated Learning via Simulated Attack Patterns

作者:

Motoki Nakamura↗

arXiv:2604.04611v2 Announce Type: replace Abstract: Federated learning (FL) enables multiple clients to collaboratively train a global model by aggregating local updates without sharing private data. However, FL often faces the challenge of free-riders, clients who submit fake model parameters without performing actual training to obtain the global model without contributing. Chen et al. proposed a free-rider detection method based on the weight evolving frequency (WEF) of model parameters. This detection approach is a leading candidate for practical free-rider detection methods, as it requires neither a proxy dataset nor pre-training. Nevertheless, it struggles to detect ``dynamic'' free-riders who behave honestly in early rounds and later switch to free-riding, particularly under global-model-mimicking attacks such as the delta weight attack and our newly proposed adaptive WEF-camouflage attack. In this paper, we propose a novel detection method S2-WEF that simulates the WEF patterns of potential global-model-based attacks on the server side using previously broadcasted global models, and identifies clients whose submitted WEF patterns resemble the simulated ones. To handle a variety of free-rider attack strategies, S2-WEF further combines this simulation-based similarity score with a deviation score computed from mutual comparisons among submitted WEFs, and separates benign and free-rider clients by two-dimensional clustering and per-score classification. This method enables dynamic detection of clients that transition into free-riders during training without proxy datasets or pre-training. We conduct extensive experiments across three datasets and five attack types, demonstrating that S2-WEF achieves higher robustness than existing approaches.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2606.06794

TA-RAG: Tone-Aware Retrieval-Augmented Generation for Peer-Support Health Communication

作者:

Yong-Bin Kang↗Anthony McCosker↗

Retrieval-augmented generation (RAG) successfully grounds large language model (LLM) outputs in trusted documents, but factual grounding alone is insufficient for sensitive peer-support health communication. In domains such as HIV peer support, responses must also be accessible, stigma-free, empathetic, and tailored to the recipient. This paper presents TA-RAG, a lightweight, prompt-based tone-aware RAG framework that embeds explicit tone control into a RAG pipeline without requiring model fine-tuning. We operationalise tone across four core components: stigma-free rewriting, readability adjustment, recipient adaptation, and empathy rephrasing. We evaluate TA-RAG through component-level tests using questions derived from HIV Online Learning Australia (HOLA), UNAIDS terminology guidance, readability metrics, peer-support standards from National Association of People with HIV Australia (NAPWHA), and a public empathy dataset. Results show that the TA-RAG's components improve their targeted communication quality while preserving key content. These findings emphasise that prompt-based tone control is a potential direction for making RAG outputs suitable for sensitive peer-support health communication.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2606.14243

Decoupled Mixture-of-Experts for Parametric Knowledge Injection

作者:

Baoqing Yue↗Weihang Su↗Qingyao Ai↗Yichen Tang↗Changyue Wang↗Jiacheng Kang↗Jingtao Zhan↗Yiqun Liu↗

Knowledge injection aims to equip large language models (LLMs) with external, domain-specific, or time-sensitive knowledge. Existing approaches typically face a trade-off between flexibility and integration: retrieval-augmented generation keeps knowledge outside the model but only provides prompt-level augmentation, whereas post-training based methods encode new knowledge into shared parameters but may introduce catastrophic forgetting, knowledge conflict, and costly updates. In this paper, we propose Decoupled Mixture-of-Experts (DMoE), a modular architecture for parametric knowledge injection that decouples both experts and the router from the base model. DMoE converts external knowledge corpora into independently updatable expert modules and uses a lightweight uncertainty-aware router to activate relevant experts only when the base model lacks sufficient knowledge during generation. To support efficient auto-regressive inference, DMoE attaches experts only to the final-layer feed-forward network, preserving KV-cache reuse while enabling parameter-level knowledge augmentation. Experiments on knowledge-intensive benchmarks show that DMoE consistently improves answer quality over retrieval and adapter-based baselines.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19370

Human-like autonomy emerges from self-play and a pinch of human data

作者:

Daphne Cornelisse↗Julian Hunt↗Zixu Zhang↗Wa\"el Doulazmi↗Kevin Joseph↗Jaime Fern\'andez Fisac↗Eugene Vinitsky↗

arXiv:2606.19370v1 Announce Type: cross Abstract: Self-play reinforcement learning has recently emerged as a way to train driving policies without any human data. It uses cheap, large-scale simulations to substitute expensive, large-scale human driving demonstrations. A key limitation of this approach is that policies trained through pure self-play can learn effective but alien driving conventions incompatible with people. Previous works attempt to mitigate such behavioral misalignments through extensive reward engineering and domain randomization, which are brittle and labor-intensive. Instead of completely discarding human demonstrations, our method treats them as a regularization objective on top of a minimal safe goal-reaching reward. Like the spice in a good stew, we find that a little human data goes a long way: our method uses only 30 minutes of human demonstrations, 2500x fewer than comparable imitation learning approaches. Resulting policies coordinate with held-out human trajectories and complete training in 15 hours on a single consumer-grade GPU. Videos and full source code are available at https://spiced-self-play.com/.

阅读与讨论 → 访问原文 →