中 EN
Sign In Register

Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

Sign In Register
01.
arXiv (CS.CL) 2026-06-11

Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks

Authors:
Mengyu Zheng↗Kai Han↗Boxun Li↗Haiyang Xu↗Yuchuan Tian↗Wei He↗Hang Zhou↗Jianyuan Guo↗Hailin Hu↗Lin Ma↗Chao Xu↗Guohao Dai↗…

General-purpose agents such as OpenClaw are increasingly used as autonomous tool users, but their coding ability is difficult to measure under SWE-bench: a generic agent does not by itself satisfy the clean Docker workspace, patch, and prediction contract required for scoring. We introduce Claw-SWE-Bench, a multilingual SWE-bench-style benchmark and adapter protocol that makes heterogeneous agent harnesses, or claws, comparable under fair settings including a fixed prompt, runtime budget, workspace contract, patch extraction procedure, and evaluator. The full benchmark contains 350 GitHub issue-resolution instances across 8 languages and 43 repositories, drawn from SWE-bench-Multilingual and SWE-bench-Verified-Mini after future-commit cleanup. We also release Claw-SWE-Bench Lite for faster validation, which is an 80-instance subset selected by a cost-aware, rank-aware procedure over 17 calibration columns. On the full benchmark, OpenClaw with a minimal direct-diff adapter scores only $19.1\%$ Pass@1, whereas the full adapter reaches $73.4\%$ with the same GLM 5.1 backbone, showing that adapter design is essential for enabling OpenClaw-style harnesses to perform coding tasks effectively. Across an OpenClaw $\times$ nine-model sweep and a five-claw $\times$ two-model sweep, model choice changes Pass@1 by $29.4$ pp and harness choice by $27.4$ pp under fixed models; systems with similar accuracy can differ substantially in total API cost. Claw-SWE-Bench therefore treats harness and cost accounting as first-class axes of SWE-style coding-agent evaluation, providing both a full benchmark and a low-cost reference set for reproducible comparison. The data is available at https://github.com/opensquilla/claw-swe-bench and https://huggingface.co/datasets/TokenRhythm/Claw-SWE-Bench.

Read & Discuss → View Source →
02.
arXiv (CS.CL) 2026-06-19

Large Language Models Hack Rewards, and Society

Authors:
Wei Liu↗Xinyi Mou↗Hanqi Yan↗Zhongyu Wei↗Yulan He↗

Reinforcement learning (RL) has become a dominant post-training paradigm, enabling large language models (LLMs) to learn from rewards. We observe that societal regulations are structurally similar to reward functions. They define measurable outcomes, thresholds, and exceptions, while often leaving institutional intent only partially specified. We hypothesise that the RL training process may exploit these gaps and therefore ask whether models' well-known tendency to hack reward functions during RL can scale into a more consequential failure mode named societal hacking: discovering loopholes in the rules society runs on. To study this phenomenon, we introduce SocioHack, a sandbox of 72 societal environments, and find that within these environments, reward hacking naturally emerges and leads to regulatory loophole discovery. Models learn to hack the social rules and generate strategies that remain technically compliant while defeating regulatory intent, and current LLM safeguards provide only limited mitigation. Therefore, collecting in-the-wild feedback for model training requires greater caution, and we need a next-generation post-training paradigm for safely iterating LLMs in real society.=

Read & Discuss → View Source →
03.
arXiv (CS.LG) 2026-06-17

Performance-Driven Environment Abstraction with Multi-Timescale Learning

Authors:
Yue Guan↗Dipankar Maity↗Panagiotis Tsiotras↗

arXiv:2606.17377v1 Announce Type: new Abstract: We study performance-driven environment abstraction for decision-making in large Markov decision processes. Rather than preserving geometric or topological structure, we seek abstractions that directly optimize decision quality. We model abstraction as a controlled approximation obtained by aggregating the state space and enforcing a shared action distribution within each aggregated state. For a fixed partition, we establish a performance guarantee that separates value-function approximation error from the loss introduced by action sharing. Guided by this analysis, we develop a multi-timescale reinforcement learning framework that jointly adapts the policy and a tree-structured environment abstraction. The resulting algorithm refines and coarsens regions of the state space based on Q-value discrepancies, balancing performance against abstraction size and complexity. Empirical results demonstrate substantial state compression, improved sample efficiency, and faster replanning compared to actor-critic baselines.

Read & Discuss → View Source →
04.
arXiv (CS.LG) 2026-06-12

COSMOS: Model-Agnostic Personalized Federated Learning with Clustered Server Models and Pseudo-Label-Only Communication

Authors:
Ben Rachmut↗Luise Ge↗William Yeoh↗Ning Zhang↗Yevgeniy Vorobeychik↗

arXiv:2605.11165v2 Announce Type: replace Abstract: Federated learning (FL) in heterogeneous environments remains challenging because client models often differ in both architecture and data distribution. While recent approaches attempt to address this challenge through client clustering and knowledge distillation, simultaneously handling architectural and statistical heterogeneity remains difficult. We introduce COSMOS, a model-agnostic framework that enables server-side personalization using only pseudo-label communication. Clients train local models and predict on the public data; the server clusters clients by prediction similarity, trains a cluster-specific model for each group using its own compute, and distills the resulting models back to clients. We provide the first theoretical analysis showing that distillation from the learned cluster models can yield exponential personalization risk contraction, going beyond the convergence-to-stationarity guarantees typically provided in model-agnostic FL. Experiments across benchmarks demonstrate that COSMOS consistently outperforms all model-agnostic FL baselines while remaining competitive with state-of-the-art personalized FL methods. More broadly, our results highlight personalized server-side learning with pseudo-labels as a promising paradigm for scalable and model-agnostic federated learning in highly heterogeneous environments.

Read & Discuss → View Source →
05.
arXiv (CS.AI) 2026-06-17

C2FL: Clustered Continual Federated Learning under Spatial and Temporal Drift

Authors:
Davide Domini↗Gianluca Aguzzi↗Lorenzo Pellegrini↗Mirko Viroli↗Lukas Esterle↗

arXiv:2606.18003v1 Announce Type: cross Abstract: Collective Adaptive Systems (CAS) increasingly rely on machine learning to let each node learn from locally sensed data, aligning its behavior with the surrounding environment. Scaling this intelligence, however, raises fundamental challenges: sensed data is often privacy-sensitive, preventing centralized collection; nodes are mobile, traversing regions where nearby nodes perceive similar phenomena while distant ones observe radically different conditions, creating natural spatial clusters; and these distributions evolve over time due to mobility, introducing temporal drift that makes local models progressively stale. These dynamics arise across domains - vehicular sensing, drone-based monitoring, smartphone crowdsensing - yet the interplay of privacy, spatial heterogeneity, and temporal drift severely undermines conventional learning strategies. Therefore, we propose C2FL, a fully distributed Federated Learning (FL) approach where nodes self-organize into learning groups through spatial clustering, reflecting the geographic structure of the environment. To counteract temporal drift, each node combines experience replay with a dwell-time-aware adaptive averaging step, progressively incorporating the regional consensus as it remains longer within the same area, while preserving previously acquired knowledge under evolving distributions. We evaluate our approach on synthetic experiments that systematically reproduce spatial and temporal shifts, showing that standard federated strategies degrade significantly under these conditions and that our method restores robust collective adaptation.

Read & Discuss → View Source →
06.
arXiv (CS.AI) 2026-06-16

Latent Thought Flow: Efficient Latent Reasoning in Large Language Models

Authors:
Xiandong Zou↗Jing Huang↗Jianshu Li↗Pan Zhou↗

arXiv:2606.16222v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly rely on intermediate reasoning, yet explicit Chain-of-Thought (CoT) suffers from a linguistic space bottleneck: each thought must be decoded into tokens, causing high inference overhead. Latent reasoning moves deliberation into continuous space, but existing methods mostly learn deterministic or reward-maximizing paths, lacking a principled way to allocate probability across trajectories with different correctness and costs. We propose Latent Thought Flow (LTF), which models reasoning as variable-length continuous trajectories and trains a sampler to match a reward-induced posterior over answer quality and computation cost. We instantiate this with a continuous GFlowNet using stochastic latent transitions. To handle sparse answer supervision, we introduce an Entropy-Weighted Subtrajectory Balance objective for intermediate rewards and a reference-prior regularizer to anchor exploration. Experiments under finetuning and transfer learning settings show that LTF outperforms explicit CoT and latent reasoning baselines, improving accuracy by 9.5% while reducing reasoning length by 27.2% on average compared with strong latent reasoning baselines.

Read & Discuss → View Source →
07.
arXiv (CS.CV) 2026-06-15

ZipSplat: Fewer Gaussians, Better Splats

Authors:
Alexander Veicht↗Sunghwan Hong↗D\'aniel Bar\'ath↗Marc Pollefeys↗

Feed-forward 3D Gaussian Splatting methods reconstruct a scene from posed or pose-free images in a single forward pass, yet current approaches predict one Gaussian per input pixel, tying the representation budget to camera resolution rather than scene complexity. A flat wall and a richly textured object thus produce equally many Gaussians despite very different geometric needs. We propose ZipSplat, a token-based feed-forward model that decouples Gaussian placement from the pixel grid. A multi-view backbone extracts dense visual tokens, and k-means clustering compresses them into a compact set of scene tokens. Cross- and self-attention refine these tokens, and a lightweight MLP decodes each into a group of Gaussians with unconstrained 3D positions. Because clustering is applied at inference, a single trained model spans the quality-efficiency curve without retraining. ZipSplat operates without ground-truth poses or intrinsics, yet sets a new state of the art on DL3DV and RealEstate10K with ${\sim}6{\times}$ fewer Gaussians than pixel-aligned methods, surpassing the best pose-free baseline by 2.1dB and 1.2dB PSNR, respectively. It further generalizes zero-shot to Mip-NeRF360 and ScanNet++, outperforming all comparable baselines. Our project page is at https://veichta.com/zipsplat.

Read & Discuss → View Source →
08.
arXiv (CS.AI) 2026-06-15

Distributional Biases in Post-Training: A Markovian Analysis of Reasoning Trajectories

Authors:
Dake Bu↗Wei Huang↗Andi Han↗Atsushi Nitanda↗Bo Xue↗Qingfu Zhang↗Hau-San Wong↗Taiji Suzuki↗

arXiv:2511.07368v3 Announce Type: replace-cross Abstract: Foundation models exhibit broad knowledge but limited task-specific reasoning, motivating post-training strategies such as RL with verifiable rewards (RLVR) and test-time scaling (TTS). While recent work highlights the role of exploration in improving pass@K, empirical evidence points to a paradox: RLVR and ORM/PRM typically reinforce existing paths rather than expanding the reasoning scope, raising the question of why exploration helps if no new patterns emerge. To reconcile this paradox, we adopt the perspective of Kim et al. (2025), viewing easy (e.g., simplifying a fraction) versus hard (e.g., discovering the some symmetry) reasoning steps as low versus high probability Markov transitions. In this tractable model, pretraining corresponds to tree-graph discovering, while post-training corresponds to CoT reweighting. We provably show that, both RLVR and ORM/PRM would favor heavily to several high-probability paths, and thereby forget rare-but-crucial CoTs. Building on this, we further prove that exploration strategies such as rejecting easy instances and KL regularization help preserve rare CoTs. Empirical simulations corroborate our theoretical results.

Read & Discuss → View Source →
10.
medRxiv (Medicine) 2026-06-15

Evaluation of AI-Generated Synthetic Data for Clinical Research in Secondary Cardiovascular Prevention among Dyslipidemia Patients

Authors:
Bonomi↗Werba↗J. P↗Saccani↗Lu↗L. L↗Coser↗Franchi↗Valsecchi↗Teruzzi↗Terragni↗Centenaro↗…

Background: Access to high-quality clinical data is essential for advancing medical research and developing effective medical statistical and Artificial Intelligence models. However, privacy regulations and logistical barriers often hinder timely access to real-world data. Synthetic data offer a promising solution, preserving the statistical characteristics of original datasets while protecting patient privacy. Objectives: This study investigates the use of synthetic data for secondary cardiovascular prevention in patients with dyslipidemia, using two real-world datasets from Centro Cardiologico Monzino. Methods: Given the high dimensionality and limited sample size of the datasets, we employed a custom generative framework based on Large Language Models (LLMs). Pre-trained LLMs were fine-tuned on original clinical records to synthesize tabular data replicating source-data distributions. Fine-tuning was performed within the Centro Cardiologico Monzino's secure infrastructure to ensure data sovereignty. We evaluate clinical utility and privacy using fidelity and privacy metrics, identifying the optimal generative model and benchmarking against traditional anonymization methods. Results: Synthetic data achieved a superior trade-off than classically anonymized datasets. Real and synthetic datasets showed strong agreement, with significant distributional differences limited to few variables. Models trained on synthetic data replicated key associations from the original dataset, including therapy modification and creatine phosphokinase as predictors of SAMS, and pharmacological intensity as the main driver of LDL-C reduction. Conclusions: Results support the feasibility of using synthetic data as a proxy for real-world datasets in exploratory analyses and model development. Despite slight attenuation of some effect sizes, preserved clinical relationships reinforce the validity of synthetic data in medical research.

Read & Discuss → View Source →
11.
arXiv (CS.LG) 2026-06-15

FreshRetailNet-LT: A Stockout-Annotated Censored Demand Dataset for Latent Demand Recovery and Forecasting in Fresh Retail

Authors:
Yangyang Wang↗Jiawei Gu↗Li Long↗Xin Li↗Li Shen↗Zhouyu Fu↗Xiangjun Zhou↗Xu Jiang↗

arXiv:2505.16319v4 Announce Type: replace Abstract: Accurate demand estimation is critical for the retail business in guiding the inventory and pricing policies of perishable products. However, it faces fundamental challenges from censored sales data during stockouts, where unobserved demand creates systemic policy biases. Existing datasets lack the temporal resolution and annotations needed to address this censoring effect. To fill this gap, we present FreshRetailNet-50K, the first large-scale benchmark for censored demand estimation. It comprises 50,000 store-product time series of detailed hourly sales data from 898 stores in 18 major cities, encompassing 863 perishable SKUs meticulously annotated for stockout events. The hourly stock status records unique to this dataset, combined with rich contextual covariates, including promotional discounts, precipitation, and temporal features, enable innovative research beyond existing solutions. We demonstrate one such use case of two-stage demand modeling: first, we reconstruct the latent demand during stockouts using precise hourly annotations. We then leverage the recovered demand to train robust demand forecasting models in the second stage. Experimental results show that this approach achieves a 2.73% improvement in prediction accuracy while reducing the systematic demand underestimation from 7.37% to near-zero bias. With unprecedented temporal granularity and comprehensive real-world information, FreshRetailNet-50K opens new research directions in demand imputation, perishable inventory optimization, and causal retail analytics. The unique annotation quality and scale of the dataset address long-standing limitations in retail AI, providing immediate solutions and a platform for future methodological innovation. The data (https://huggingface.co/datasets/Dingdong-Inc/FreshRetailNet-50K) and code (https://github.com/Dingdong-Inc/frn-50k-baseline}) are openly released.

Read & Discuss → View Source →
12.
arXiv (CS.AI) 2026-06-11

Autoregressive Direct Preference Optimization

Authors:
Masanari Oi↗Mahiro Ukai↗Masahiro Kaneko↗Naoaki Okazaki↗Nakamasa Inoue↗

arXiv:2602.09533v2 Announce Type: replace Abstract: Direct preference optimization (DPO) has emerged as a promising approach for aligning large language models (LLMs) with human preferences. However, the widespread reliance on the response-level Bradley-Terry (BT) model may limit its full potential, as the reference and learnable models are assumed to be autoregressive only after deriving the objective function. Motivated by this limitation, we revisit the theoretical foundations of DPO and propose a novel formulation that explicitly introduces the autoregressive assumption prior to applying the BT model. By reformulating and extending DPO, we derive a novel variant, termed Autoregressive DPO (ADPO), that explicitly integrates autoregressive modeling into the preference optimization framework. Without violating the theoretical foundations, the derived loss takes an elegant form: it shifts the summation operation in the DPO objective outside the log-sigmoid function. Furthermore, through theoretical analysis of ADPO, we show that there exist two length measures to be considered when designing DPO-based algorithms: the token length $\mu$ and the feedback length $\mu'$. To the best of our knowledge, we are the first to explicitly distinguish these two measures and analyze their implications for preference optimization in LLMs.

Read & Discuss → View Source →
13.
arXiv (CS.CV) 2026-06-18

Taming I2V models for Image HOI Editing: A Cognitive Benchmark and Agentic Self-Correcting Framework

Authors:
Jiayi Gao↗Qingchao Chen↗Yuxin Peng↗Yang Liu↗

Current image editing methods excel at static attributes but fail at complex Human-Object Interactions (HOI), a critical challenge unaddressed by existing benchmarks that conflate HOI with static attributes, relying on global metrics incapable of simultaneously assessing dynamic interaction validity and entangled human-object pair preservation. Thus, we first introduce HOI-Edit, a comprehensive benchmark with three progressive cognitive levels, which features an automated metric HOI-Eval that reliably evaluates instance-level interaction by letting VLM Q&A after thinking with images containing grounded Human-Object pairs. Considering the task's essence of remodeling dynamic relationships, we benchmark Image-to-Video (I2V) models, finding them inherently suited for dynamic editing due to their temporal generation capabilities. Crucially, beyond superior performance, this capability provides a "replay of the failure process," offering unique diagnosability into why errors occur. We thus propose SCPE (Self-Correcting Process Editing), a novel, agentic self-correcting framework that constrains the generation of I2V models through iteratively refined prompts, enabling the generated videos to more accurately present the target HOI. Extracted frames from these videos are the final editing results. On HOI-Edit, SCPE achieves performance competitive with state-of-the-art (SOTA) editing models like Nano Banana on interaction. Code is available at https://github.com/oceanflowlab/HOI-Edit.

Read & Discuss → View Source →
14.
arXiv (CS.LG) 2026-06-11

Evaluating and Combating the Impact of Concept Drift on the Performance of Machine Learning-Based Phishing Detection Systems

Authors:
Warren Fernando↗Nikos Komninos↗

arXiv:2606.11471v1 Announce Type: cross Abstract: The expansion of the digital domain has resulted in a substantial increase in digital communication, with email emerging as one of the most prominent channels. The proliferation of email communication is apparent in both professional and personal contexts, thereby creating numerous vulnerabilities for malicious actors to exploit. Spam emails, a form of unsolicited correspondence often bearing malicious intent towards recipients, have been an ongoing challenge for email users since the inception of email technology, and this problem has been exacerbated by the growth of the digital landscape. Email spam filters are integral components of email clients, engineered to identify potentially harmful messages and alert users to their malicious content. Phishing, frequently the initial phase of malware-based attacks, is evolving rapidly, with malware becoming increasingly sophisticated over time. A widely adopted approach for detecting malicious activity within malware and spam domains is the application of machine learning. Our aim is to assess the impact of the evolution within the spam email domain on these machine learning-based detection systems and to explore strategies for mitigating associated performance degradation.

Read & Discuss → View Source →
15.
arXiv (CS.CL) 2026-06-18

SAGE: Stochastic Prompt Optimization via Agent-Guided Exploration

Authors:
Ziyi Zhu↗Luka Smyth↗Saki Shinoda↗Jinghong Chen↗

Context engineering has emerged as a primary lever for improving AI systems without parameter updates. Recent work showing that textual gradients do not function as real gradients motivates treating automatic prompt optimization (APO) as black-box search. We introduce SPO (Stochastic Prompt Optimization), a framework for stochastic search over prompt space, and compare three strategies of increasing sophistication: error-informed random search, a genetic algorithm with evolutionary operators, and SAGE (SPO via Agent-Guided Exploration), a multi-agent pipeline with diagnostic code execution. Across three benchmarks, no single strategy dominates; effectiveness depends on the interaction of landscape structure with error type. We further deploy SAGE on a mental-health chatbot under a continuous optimization paradigm, where it compounds eight cycles of individually-noisy A/B tests into a statistically robust gain in next-day retention. We argue that coupling qualitative diagnosis with quantitative validation is what makes agentic optimization effective for open-ended task-oriented dialogue.

Read & Discuss → View Source →
16.
arXiv (CS.AI) 2026-06-12

EWAM: An Enhanced World Action Model for Closed-Loop Online Adaptation in Embodied Intelligence

Authors:
Xin Zhou↗Cong Miao↗

arXiv:2606.12690v1 Announce Type: cross Abstract: In this paper, we propose the Enhanced World Action Model (EWAM), a closed-loop online adaptation architecture built upon a pretrained and fully frozen Cosmos3 backbone network. Evaluated entirely under a zero-shot task protocol, EWAM is centrally focused on reducing the amount of additional deployment data required to adapt to new task layouts. Notably, no extra task-specific demonstration sets were introduced in any of the evaluations, and no fine-tuning was performed on the backbone network. Its performance gains stem entirely from an inference-time co-reasoning mechanism composed of four inserted lightweight neural layers: the Neural Experience Memory Layer located in the intermediate layers of the Diffusion Transformer (DiT) provides task-relevant execution context; the Neural Anomaly Detection Layer after the state prediction head monitors the divergence between predicted and actual states in real time; the Neural Policy Routing Layer dynamically selects direct execution, conservative replanning, or rollback recovery based on the anomaly severity; and the Neural Action Correction Layer refines the generated action chunks using execution diagnostics. Unlike naive feature fusion, the memory, anomaly detection, and correction modules are deeply integrated into the Cosmos3 forward path in a differentiable manner, with only the final routing decision being a discrete supervised one.

Read & Discuss → View Source →
17.
arXiv (CS.CV) 2026-06-18

Conditional Latent Diffusion Model with Fourier-based Motion Modelling for Virtual Population Synthesis

Authors:
Shaokun Lan↗Haoran Dou↗Jinghan Huang↗Arezoo Zakeri↗Fengming Lin↗Zherui Zhou↗Jinming Duan↗Alejandro F. Frangi↗

In-silico trials of medical devices require the generation of virtual populations of anatomies. In cardiovascular applications, virtual anatomy is typically represented as a 3D+t mesh sampled from a generative model. However, most existing mesh generators focus on static anatomy, while sequence models often lack explicit periodicity. To this end, we propose 4D F-MeshLDM, a conditional generative framework comprising a convolutional mesh VAE to encode meshes, a structural latent space that parameterises motion using a truncated Fourier series, and a diffusion prior that learns the latent distribution over Fourier coefficient tokens. By conditioning the diffusion process on clinical covariates via affine modulation, we enable controllable synthesis. Sampling tokens and performing inverse Fourier synthesis yield cycle-consistent latent trajectories, which can be decoded into 3D+t cardiac mesh sequences. Experiments on 5,000 UK Biobank subjects demonstrate that 4D F-MeshLDM outperforms state-of-the-art baselines in anatomical fidelity and achieves near-zero cycle closure error. Furthermore, the generated cohorts accurately preserve clinical functional indices, highlighting the potential of our framework for reliable in-silico cardiac trials.

Read & Discuss → View Source →
18.
arXiv (CS.CV) 2026-06-16

Teacher-Student Structure for Domain Adaptation in Ensemble Audio-Visual Video Deepfake Detection

Authors:
Elham Abolhasani↗Maryam Ramezani↗Hamid R. Rabiee↗

The rapid advancement of generative AI models is leading to more realistic deepfake media, encompassing the manipulation of audio, video, or both. This raises severe privacy and societal concerns. Numerous studies in this area have yielded promising intra-domain results; however, these models frequently exhibit decreased efficacy when faced with data from dissimilar domains. Consequently, recent deepfake detection approaches focus on enhancing the generalization ability through multiple techniques that incorporate all input modalities, including audio, images, and their interactions. In this regard, we propose the EAV-DFD method, a generalized deep ensemble audio-visual model (EAV-DFD) combined with a domain adaptation mechanism utilizing a teacher-student framework to enhance the model's ability to perform and generalize effectively across unseen domains. To evaluate the model's performance, we used the FakeAVCeleb dataset as the primary domain and the DFDC, Deepfake_TIMIT, and PolyGlotFake datasets as an unseen domain. Our experimental results demonstrate that the proposed framework is efficient in domain adaptation, improving AUC performance of the model by 4.09%, 17.94%, and 0.5% on three unseen datasets, using only a small portion of them to train the student model. This leads to a novel deepfake detection model capable of adapting to new domains and interpreting which modality has been manipulated, highlighting the potential of our approach for real-world applications.

Read & Discuss → View Source →
19.
arXiv (CS.LG) 2026-06-18

EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts

Authors:
Minseo Kim↗Minjae Lee↗Seunghyuk Oh↗Kevin Galim↗Donghoon Kim↗Coleman Hooper↗Harman Singh↗Amir Gholami↗Hyung Il Koo↗Wonjun Kang↗

arXiv:2606.18967v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a representative post-training paradigm for LLMs, enabling strong reasoning and agentic capabilities. However, rollout generation remains a dominant latency bottleneck because autoregressive sampling decodes responses sequentially and a small number of long-tailed generations often determine completion time. Speculative decoding (SD) offers a natural way to address this bottleneck, as it is a well-established technique for serving fixed LLMs that reduces latency by rapidly drafting tokens and accepting them through parallel verification while preserving the target-model distribution. However, its practical speedups do not directly carry over to RL rollouts: (i) the evolving target policy makes any fixed drafter increasingly mismatched with the policy's output distribution; and (ii) active batch sizes shrink throughout rollout decoding, shifting decoding from compute-bound to memory-bound regimes where parallel verification can exploit underutilized compute. Therefore, accelerating RL rollouts requires both a drafter that remains effective under long, high-temperature generations from an evolving policy and system-aware use of SD that avoids compute-bound regimes. We present EfficientRollout, a system-aware self-SD framework designed to address this gap for RL rollouts. EfficientRollout induces a quantized drafter from the target model (i.e. self-speculative decoding), keeping it coupled to the evolving policy without separate drafter pretraining or online adaptation. It further coordinates a system-aware SD toggle policy with acceptance-aware draft-length adaptation, enabling speculation only in beneficial regimes while matching the drafting budget to evolving drafter quality. EfficientRollout reduces rollout and end-to-end latency by up to 19.6% and 12.7%, respectively, over an accelerated AR rollout baseline, while preserving final model quality.

Read & Discuss → View Source →
20.
arXiv (CS.LG) 2026-06-11

Capacity-Constrained Online Convex Optimization with Delayed Feedback

Authors:
Alexander Ryabchenko↗Idan Attias↗Daniel M. Roy↗

arXiv:2606.11711v1 Announce Type: new Abstract: Online learning with delayed feedback typically assumes that the learner can track all pending rounds until their feedback arrives. In practice, tracking resources are finite, and feedback from untracked rounds is permanently lost. In this paper, we study delayed online convex optimization (OCO) under a hard capacity constraint, where at most $C$ pending rounds can be tracked at any time. To model delay information, we introduce a semi-clairvoyant model that refines the clairvoyant assumption from prior work: rather than requiring delays to be known at prediction time, the learner observes delay expirations online, consistent with the classical unconstrained delayed setting. Our approach proceeds via a reduction to a novel ``delayed and weighted'' OCO problem, using a scheduler that randomizes tracking decisions and importance-weights the resulting observations. For this base problem, we propose and analyze Delayed-Weighted FTRL and its bandit analogue, establishing regret bounds that explicitly characterize the interaction between time-varying weights and delayed feedback. Combining these base learners with our schedulers yields the first regret guarantees for capacity-constrained OCO under convex and strongly convex losses, for both first-order and bandit feedback. For first-order feedback, capacity $C = \Omega(\log T)$ suffices to recover standard delayed OCO rates up to logarithmic factors. For bandit feedback, the regret rates are modulated by powers of $(1 + \sigma_{max}/C)$, where $\sigma_{max}$ is the maximum number of pending observations at any time. This allows the regret bound to degrade gracefully when $C < \sigma_{max}$, while remaining sublinear.

Read & Discuss → View Source →
21.
arXiv (CS.CL) 2026-06-17

ART: Attention Run-time Termination for Efficient Large Language Model Decoding

Authors:
Chen Qiu↗Guozhong Li↗Cristian McGee↗Aritra Dutta↗Panos Kalnis↗

Long-context decoding in Large Language Models (LLMs) is constrained by the cost of accessing and processing the Key-Value (KV) cache. Despite evidence that attention outputs depend jointly on keys and values, most existing KV management methods rely on key-only pruning, since incorporating values incurs prohibitive overhead. In this paper, we propose Attention Run-time Termination (ART), a lightweight run-time mechanism that tracks accumulated attention outputs during kernel execution and terminates subsequent KV block accesses once further contributions become negligible. Rather than replacing KV selection, ART dynamically terminates redundant KV traversal on top of existing dense or sparse attention policies. We introduce a stability-based criterion that monitors both magnitude and directional changes of intermediate attention outputs and provideds a theoretical characterization of the resulting truncation error. Experiments on the LongBench and RULER Needle-in-a-Haystack tasks show that ART increases the generation throughput of existing KV-cache methods by up to 20%, without compromising the result quality.

Read & Discuss → View Source →
22.
arXiv (CS.CL) 2026-06-15

The Coin Flip Judge? Reliability and Bias in LLM-as-a-Judge Evaluation

Authors:
Abel Yagubyan↗

LLM-as-a-Judge is now widely used to rank model outputs, train reward models, and populate public leaderboards, but its run-to-run reliability remains under-characterized. We study repeated identical evaluations on 29 tasks spanning 10 categories using two OpenAI judge models (GPT-4o-mini and GPT-4.1-mini), with 50 pairwise trials and 50 pointwise trials per question, supplemented by temperature and prompt-sensitivity ablations. Across judges, pairwise preferences flip on average 13.6% of the time, with 28% of questions exceeding a 20% flip rate and one question reaching 56%. GPT-4o-mini also exhibits a significant first-position bias (72% A-majority, p = 0.024). At the same time, mean pointwise score gaps are small (0.19–0.36 on a 10-point scale) and not statistically significant in aggregate, producing a pairwise–pointwise gap: judges frequently choose a winner even when their own scalar scores provide little evidence of a meaningful quality difference. Beyond within-judge instability, cross-judge agreement is only 76% ($\kappa = 0.51$), semantically equivalent prompt templates change majority outcomes in 25% of tested cases, and deterministic decoding reduces but does not eliminate inconsistency. A reliability curve analysis shows that, in our dataset, 11 repeated trials are needed for a majority vote to recover the 50-trial reference verdict with 95% probability on average, rising to 15 for high-variance questions. These findings suggest that single-trial LLM judging is often too noisy for high-stakes evaluation, and that multi-trial aggregation, position randomization, and explicit uncertainty reporting should be standard practice. Because both judges are from a single provider, cross-provider replication remains an important next step.

Read & Discuss → View Source →
23.
arXiv (quant-ph) 2026-06-12

Certifying Nonclassical Proper-Time Histories with a Quantum Clock

Authors:
Shuai Zeng↗

arXiv:2606.12755v1 Announce Type: new Abstract: Quantum clocks can acquire relativistic phases from motional or gravitational proper-time differences, but reduced clock dephasing alone does not certify nonclassical proper-time histories. We formulate this distinction as a channel-certification problem. First, we show that any two-level single-time dephasing signal, including one generated by an effective quantum proper-time label, admits a classical random proper-time representation. We then define the convex set of classical mixtures of experimentally specified proper-time histories and prove a Choi-rank separation criterion for conditioned coherent history recombination. A two-branch Ramsey protocol gives explicit bright- and dark-port population witnesses outside this classical set. The certification is operational and relative to the specified history set: it rules out classical mixtures of the same implemented proper-time histories, not arbitrary classical protocols with different histories or controls.

Read & Discuss → View Source →
24.
arXiv (CS.CL) 2026-06-17

Beyond Domains: Reusing Web Skills via Transferable Interaction Patterns

Authors:
Shiqi He↗Yue Cui↗Feijie Wu↗Xinyu Ma↗Jiaheng Lu↗Yaliang Li↗Bolin Ding↗Mosharaf Chowdhury↗

Large language model (LLM) web agents are usually deployed as tool callers: each turn, the model reads a fresh page observation and emits one structured tool action. When every action is a low-level primitive, horizons grow quickly and so do policy-facing LLM completions, dominating latency and cost on benchmarks such as Mind2Web and WebArena. Recent systems therefore wrap repeated interaction fragments as web skills: callable tools built from successful trajectories or induced programs, so one call can replace several primitives. However, prior skill libraries are still triggered mainly by instruction similarity or coarse site metadata, which yields low skill reuse on held-out sites and leaves much of the potential step and token reduction on the table. We present SkillMigrator, an agent that learns reusable web skills and transfers them across sites by matching layout structure rather than specific element references. Each induced skill is stored as a transferable interaction pattern (TIP): the skill paired with a structural sketch of the snapshot at induction time. At test time, SkillMigrator retrieves TIPs by layout similarity and grounds their references on the live page. The rest of the stack is standard: accessibility-snapshot observations with stable references, and fixed tool calling over primitives plus skill invocations. Compared with the state-of-the-art approaches, SkillMigrator reduces the average LLM-action count on successful trajectories by 8-10% across both WebArena and Mind2Web at matched success rate.

Read & Discuss → View Source →
25.
Nature (Science) 2026-06-17

Structure of the pre-initiation complex explains CMGE biogenesis

Authors:
Thomas Pühringer↗

When cells enter S phase, bidirectional DNA replication is initiated through the kinase-regulated recruitment of three activators (Cdc45, GINS and Pol ε) to a duplex-DNA-loaded double hexamer of minichromosome maintenance (MCM) ATPases. Together, these proteins form two CMGE helicases that establish divergent replication forks as they become separated1. Here, to gain an understanding of CMGE biogenesis, we reconstituted the pre-initiation complex with purified yeast proteins. The cryo-electron-microscopy structure shows a set of firing factors caught in the act of assembling two symmetrical CMGEs. We show how stepwise complex formation reshapes MCM in preparation for DNA opening, and we explain how ATP promotes firing-factor ejection and CMGE maturation. We find that although Sld2 facilitates&nbsp;the recruitment of GINS to MCM, as expected, it also aids the efficient separation of the CMGE dimer, and is essential for the ejection of the lagging strand from MCM. These findings have direct implications for our understanding of the metazoan Sld2 orthologue, RECQL4, and point to a replication-fork establishment mechanism that is conserved across eukaryotes. Cryo-electron microscopy and biochemical reconstitution experiments in yeast provide insight into the assembly of the CMGE complex, a helicase that establishes bidirectional DNA replication in eukaryotic cells, and elucidate the role of the firing factor Sld2.

Read & Discuss → View Source →