Explore the Frontier of Global Academia

01.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.12881

Direct Preference Optimization for Chatbot Fine-Tuning: An Empirical Study

Authors:

Yvonne Qiu↗Dezhi Yu↗ShuoJia Fu↗

We present an approach to fine-tuning large language models using Direct Preference Optimization (DPO), a reinforcement learning technique. Our experimental results demonstrate that DPO simplifies the training pipeline, improves computational efficiency, and achieves competitive performance. The evaluation using BLEU, ROUGE, and cosine similarity metrics indicates effective learning and convergence, though further investigation is needed to address observed training instability.

Read & Discuss → View Source →

02.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2501.08425

Is Stochastic Gradient Descent Effective? A PDE Perspective on Machine Learning processes

Authors:

Davide Barbieri↗Matteo Bonforte↗Peio Ibarrondo↗

arXiv:2501.08425v3 Announce Type: replace Abstract: In this paper we analyze the behaviour of the stochastic gradient descent (SGD), a widely used method in supervised learning for optimizing neural network weights via a minimization of non-convex loss functions. Since the pioneering work of E, Li and Tai (2017), the underlying structure of such processes can be understood via parabolic PDEs of Fokker-Planck type, which are at the core of our analysis. Even if Fokker-Planck equations have a long history and a extensive literature, almost nothing is known when the potential is non-convex or when the diffusion matrix is degenerate, and this is the main difficulty that we face in our analysis. We identify two different regimes: in the initial phase of SGD, the loss function drives the weights to concentrate around the nearest local minimum. We refer to this phase as the drift regime and we provide quantitative estimates on this concentration phenomenon. Next, we introduce the diffusion regime, where stochastic fluctuations help the learning process to escape suboptimal local minima. We analyze the Mean Exit Time (MET) and prove upper and lower bounds of the MET. Finally, we address the asymptotic convergence of SGD, for a non-convex cost function and a degenerate diffusion matrix, that do not allow to use the standard approaches, and require new techniques. For this purpose, we exploit two different methods: duality and entropy methods. We provide new results about the dynamics and effectiveness of SGD, offering a deep connection between stochastic optimization and PDE theory, and some answers and insights to basic questions in the Machine Learning processes: How long does SGD take to escape from a bad minimum? Do neural network parameters converge using SGD? How do parameters evolve in the first stage of training with SGD?

Read & Discuss → View Source →

03.

medRxiv (Medicine) 2026-06-18 DOI: HASH:42c939cd9d60e7324856eac14871b703

Expert in Ultrasound Skills: Feasibility of an IMU-video platform to describe technical profiles during focused cardiac ultrasound. Pilot study

Authors:

morales↗f. r↗Gonzalez↗S. R↗Osses↗M. F. S↗Hernandez↗B. L↗Ramirez↗D. A↗

Background: Focused cardiac ultrasound (FoCUS) is operator dependent and requires coordinated probe manipulation, image interpretation and iterative visual feedback. Existing assessment approaches often emphasize final image quality or expert rating. We developed Expert in Ultrasound Skills (EXUS) , a platform that synchronizes transducer-mounted inertial measurement unit (IMU) data with ultrasound video, and evaluated its technical feasibility during FoCUS acquisition. Methods: This observational pilot study included 6 operators performing two repetitions of a four-view FoCUS protocol, yielding 12 analytical sessions and 48 planned acquisitions. Feasibility was defined by acquisition completion, video availability, start/stop events, fused IMU-video windows, temporal coverage, complete human label entries and IMU integrity. A 100-image Likert rating task was used to summarize pairwise inter-rater agreement for still-frame image quality assessment. Results: All 48 planned acquisitions were completed with video, start/stop events, fused windows and complete human label entries. Temporal coverage was at least 90% in 47/48 acquisitions. IMU integrity endpoints exceeded the 80% threshold: 43/48 acquisitions had no extreme IMU-derived artifact, 43/48 had no active-segment IMU restart and 44/48 had no complete motion flatline. Mean pairwise exact agreement for the Likert task was 38.9%, with mean quadratic-weighted Cohen's kappa of 0.564. Post hoc profiles varied across duration, visual quality, mechanical load and motor efficiency. Conclusions: EXUS was technically feasible for synchronized IMU-video capture during FoCUS. The pilot supports multimodal acquisition data as a way to describe technical profiles and generate formative feedback hypotheses, but the post hoc indices are not validated competency measures. Keywords: focused cardiac ultrasound; point-of-care ultrasound; inertial measurement unit; medical education; deliberate practice

Read & Discuss → View Source →

04.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15017

Are Online Skill and Memory Modules Always Worth Their Tokens? A Budget-Constrained Study of Web Agents

Authors:

Sina Hajimiri↗Masih Aminbeidokhti↗Jose Dolz↗Ismail Ben Ayed↗Issam H. Laradji↗Spandana Gella↗Nicolas Gontier↗

Online web agents often augment a base actor with memory, workflow, or skill modules. These modules can improve performance, but they also consume test-time tokens, a cost rarely reported alongside the actor's inference cost. We study online augmentation, where this overhead is paid on every task, and re-evaluate its benefits under a fixed total inference budget. We compare AWM, ASI, and ReasoningBank with a token-matched vanilla baseline that uses the same budget for additional actor steps. Across three WebArena domains and three models, Gemini 3 Flash, GPT-5.4-mini, and Qwen 3.6-27B, the vanilla baseline matches or surpasses all three augmentation methods in aggregate success rate while often using fewer total tokens. We observe a similar trend on WorkArena-L1 with Qwen 3.6-27B, indicating that the effect extends to enterprise knowledge-work tasks. Our results suggest that skills and workflow memory can be useful in specific domains, but their apparent gains often vanish against a budget-matched actor. We further show that run-to-run variance materially affects outcomes and should be reported as a core evaluation criterion for online web agents.

Read & Discuss → View Source →

05.

medRxiv (Medicine) 2026-06-15 DOI: HASH:3d6062ab9384e2472bd9996f1f3c83ae

Long-read sequencing enables high-accuracy mitochondrial heteroplasmy detection in Parkinson's disease

Authors:

Lüth↗Schaake↗Much↗Belyea↗M. M↗Seibler↗Grünewald↗May↗Klein↗Weissensteiner↗Trinh↗

Background: Low-frequency heteroplasmic mitochondrial DNA (mtDNA) variants are associated with aging and neurological diseases, including Parkinson's disease (PD). Targeted deep mtDNA sequencing using PacBio HiFi long reads has the potential to resolve heteroplasmy across the full mitochondrial genome with high accuracy. Methods: To validate Vega PacBio sequencing for detecting mtDNA heteroplasmy, we analyzed four predefined mixtures of two mtDNA haplotypes. We generated a single long-range PCR amplicon covering the entire mitochondrial genome. These amplicons were mixed at predefined ratios (minor mixture haplotype component: 5%, 2%, 1%, and 0.1%). Variant calling was performed using Mutserve2, and accuracy was assessed by calculating the F1 score from comparisons between expected and detected variants. Full-length mtDNA PacBio sequencing was applied to investigate heteroplasmy across fibroblast passages derived from five LRRK2 p.Gly2019Ser variant carriers (n=3 affected with PD and n=2 unaffected carriers). Changes in mtDNA heteroplasmy level and variant load were assessed longitudinally using a linear mixed model. Results: The single-amplicon approach enabled full-length haplotype resolution without amplification bias associated with overlapping PCR strategies. The F1 score of the predefined mixtures was 1.0 for heteroplasmy levels between 5% and 1% and remained high (0.91) at 0.1%. We detected n=10/62 variants discordant with the Illumina reference at the 0.1% mixture, but sensitivity remained very high at 1.00 in that mixture. Detected minor variants closely matched expected heteroplasmy levels, with average variant levels of 0.057 (5%), 0.022 (2%), 0.011 (1%), and 0.001 (0.1%). Across twelve fibroblast passages, we observed fewer mtDNA heteroplasmic variants ({beta}=-3.2, p=0.026). Increased heteroplasmic variant load over time was also associated with older age ({beta}=1.50, p=0.001) and PD affection status ({beta}=5.0, p=1.0 x 10-4) in LRRK2 variant carriers. Notably, we observed distinct patterns of heteroplasmic variants that either increased or decreased in heteroplasmy level across passages. Conclusion: PacBio HiFi sequencing, combined with a single-amplicon strategy, enables accurate full-length mtDNA heteroplasmy detection and longitudinal analysis, providing a valuable tool for studying mitochondrial variation and dynamics in disease.

Read & Discuss → View Source →

06.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.14885

Dr-DCI: Scaling Direct Corpus Interaction via Dynamic Workspace Expansion

Authors:

Yi Lu↗Zhuofeng Li↗Ping Nie↗Haoxiang Zhang↗Yuyu Zhang↗Kai Zou↗Wenhu Chen↗Jimmy Lin↗Dongfu Jiang↗Yu Zhang↗

Agentic search over large corpora relies on retriever-mediated interfaces (e.g., BM25 or ColBERT) for scalable candidate discovery. While effective at ranking relevant documents, these interfaces expose evidence only as ranked results or bounded document views, limiting agents' ability to reorganize material and verify constraints across documents. Direct Corpus Interaction (DCI) addresses this limitation by exposing shell-executable corpus operations for flexible search, filtering, comparison, and verification. However, full-corpus terminal commands become slow and unstable as the corpus grows, degrading performance and efficiency. We introduce DR-DCI, a retriever-steered DCI framework that treats retrieval as an agent-callable action for expanding a local workspace. Rather than operating directly over the full corpus, the agent dynamically pulls relevant documents into an evolving workspace and conducts DCI operations within it. This design combines retriever-level recall with DCI-style precision: retrieval keeps exploration scalable, while DCI preserves the local operations needed for effective evidence resolution. Experiments show that DR-DCI is both effective and efficient across scales. On Browsecomp-Plus, DR-DCI reaches 71.2\% accuracy, improving over raw DCI and ablated variants by up to 8.3 points while reducing tool usage, wall time, and estimated cost. With workspace-preserving context reset, accuracy further improves to 73.3\%. In corpus-scaling experiments, DR-DCI remains effective from 100K to 10M documents, whereas raw DCI becomes unstable and BM25 performs substantially worse. DR-DCI also scales to a 20M-scale file-per-document Wiki-18 QA setting, achieving an average score of 63.0 across six benchmarks and outperforming retrieval-based and trained search-agent baselines. Ablation analysis further shows that ranked previews and inter-document DCI are key to performance.

Read & Discuss → View Source →

07.

arXiv (math.PR) 2026-06-16 DOI: arXiv:2312.01265

The optimal sub-Gaussian normalisation for randomised monotone functions

Authors:

Thomas Anton↗Rabee Tourky↗

arXiv:2312.01265v5 Announce Type: replace Abstract: Let $\mathcal{M}$ denote the class of randomised monotone functions on $\mathbb{R}$ with values in $[0,1]$, and let $U_{\mathcal{M}}\colon \mathbb{R}_+\to \mathbb{R}_+$ be the minimal function for which $$ \mathbb{P}\left\{ \sqrt{\eta_f}\, \sup_{t\in\mathbb{R}} \left| f_Z(t) - \Exf{f_Z(t)} \right| \ge \varepsilon\sqrt{U_{\mathcal{M}}(\eta_f)} \right\} \le 2\e^{-2\varepsilon^2} $$ holds for every member $f_Z$ of $\mathcal{M}$ with finite effective sample size $\eta_f$ and every positive $\varepsilon$. We prove that for every $x> 1$, $$ \left| \sqrt{U_{\mathcal{M}}(x)} - \sqrt{\log_4 x} \right| \le 2 \min\!\left\{ 1,\, \frac{2 \ln(\e + \ln x)}{\sqrt{\ln x}} \right\}\,. $$ The optimal adjustment $\sqrt{U_{\mathcal{M}}(x)}$ matches $\frac{1}{\sqrt{2\ln 2}}\sqrt{\ln x}$ for all $x>1$, with residuals bounded as above.

Read & Discuss → View Source →

08.

arXiv (quant-ph) 2026-06-12 DOI: arXiv:2409.04091

Squeezing Enhancement in Lossy Multi-Path Atom Interferometers

Authors:

Julian G\"unther↗Jan-Niclas Kirsten-Siem{\ss}↗Naceur Gaaloul↗Klemens Hammerer↗

arXiv:2409.04091v3 Announce Type: replace Abstract: This paper explores the sensitivity gains afforded by spin-squeezed states in atom interferometry, in particular using Bragg diffraction. We introduce a generalised input-output formalism that accurately describes realistic, non-unitary interferometers, including losses due to velocity selectivity and scattering into undesired momentum states. This formalism is applied to evaluate the performance of one-axis twisted spin-squeezed states in improving phase sensitivity. Our results show that by carefully optimising the parameters of the Bragg beam splitters and controlling the degree of squeezing, it is possible to improve the sensitivity of the interferometer by several dB with respect to the standard quantum limit despite realistic levels of losses in light pulse operations. However, the analysis also highlights the challenges associated with achieving these improvements in practice, most notably the impact of finite temperature on the benefits of entanglement. The results suggest ways of optimising interferometric setups to exploit quantum entanglement under realistic conditions, thereby contributing to advances in precision metrology with atom interferometers.

Read & Discuss → View Source →

09.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17242

Landsat-Sentinel-2 Algal Bloom Mapping Using Vision Transformers: Model Description, Implementation, and Examples

Authors:

Thainara Lima↗Vitor Martins↗

Coastal algal bloom monitoring requires frequent, spatially detailed, and globally consistent observations, provided by Landsat-8/9 and Sentinel-2 A/B/C. Together, these missions offer over a decade of medium-resolution multispectral imagery with near-global coverage every 2-3 days, enabling the detection of fragmented bloom structures not resolvable by coarse ocean-color sensors. However, their use in aquatic environments remains challenging due to limited spectral coverage and a lack of harmonized reflectance products. As an alternative to traditional bio-optical methods, deep learning-based image classification offers a data-driven approach that can overcome many of these limitations. This study presents the first successful implementation of vision transformer-based coastal algal bloom mapping using 30-m Landsat-Sentinel-2 images. A globally distributed bloom patch dataset was generated across bloom-prone coastal hotspots worldwide. Four transformer-based architectures were compared against a standard convolutional baseline for fine-scale bloom detection, and assessed under different optical water types and atmospheric and surface conditions. All deep learning models showed strong capabilities in detecting floating bloom areas, with omission and commission errors of 8-65%. Under cloud and glint stress in a time series, the Swin Transformer outperformed traditional spectral-index approaches, which produced widespread false positives, effectively avoiding cloud- and glint-affected pixels. Comparisons with MODIS-derived products further highlighted the benefits of higher spatial resolution in detecting fragmented and irregularly affected blooms. Our findings support deep learning as a reliable tool for medium-resolution, consistent monitoring of floating algal blooms in dynamic coastal environments.

Read & Discuss → View Source →

10.

arXiv (math.PR) 2026-06-16 DOI: arXiv:2605.29641

Experimentation for Different Scheduling Policies on Queues: Mixed Differences-in-Q Estimators Based on Little's Law

Authors:

Nanshan Jia↗Ramesh Johari↗Nian Si↗Zeyu Zheng↗

arXiv:2605.29641v2 Announce Type: replace-cross Abstract: In data centers, tasks are dispatched to various servers to evenly distribute the workload. When a data center considers implementing a new scheduling algorithm, it typically conducts an A/B test prior to deployment to assess the real-world impact of this new method. However, a straightforward A/B test might be interfered with so-called ``Markovian'' interference. We utilized the Differences-in-Q estimator, as developed by Farias et al. (2022), and introduced mixed Differences-in-Q estimators grounded in Little's Law. We show that our A/B testing methods significantly reduce bias and variance when testing various scheduling policies. Extensive simulations were conducted under scenarios like non-stationary arrival rates, heterogeneous service rates, and communication delays. These simulations highlight the robustness and efficacy of our A/B testing approach.

Read & Discuss → View Source →

11.

PLOS Computational Biology 2026-06-18 DOI: HASH:de02d995e48341830d3685ee816cd9c8

A comparison of contact patterns derived from the population structure in agent-based models and empirical contact survey data

Authors:

Janik Suer↗

by Janik Suer, Johannes Ponge, Michael Brüggemann, Jan Pablo Burgard, Vitaly Belik, Bernd Hellingrath, Alejandra Rincón Hidalgo, Andrzej K. Jarynowski, Richard Pastor, Huynh Thi Phuong, Steven Schulz, Ashish Thampi, Chao Xu, Marlli Zambrano, Rafael Mikolajczyk, André Karch, Veronika K. Jaeger, on behalf of the OptimAgent Consortium Agent-based models (ABMs) are powerful tools for simulating disease spread, relying on individual-level interaction rules from which emergent dynamics arise. An important component in ABMs is contact behaviour. To reduce computational complexity, contact behaviour in ABMs is often assumed as random mixing within structurally defined settings (as, e.g., workplaces). with setting composition typically based on empirical data such as census information. However, the validity of this approach to represent contacts remains unclear. To address this gap, we compare the contact structure derived through this approach in a large-scale ABM with empirical contact survey data with respect to age contact matrices for households, schools, workplaces, all remaining contact settings, and all contacts combined (based on difference matrices and sum of squared errors (SSE)). Our results demonstrate that random mixing in settings with known age compositions like households (SSE:0.7(95%CI0.4–0.9)), schools (SSE:0.7(95%CI:0.3–1.1)) and workplaces (SSE:0.5(95%CI:0.2-0.7)), captures basic interaction patterns but fails to account for age-related variation in contact numbers. The largest differences arise for contacts outside these settings (SSE:3.8(95%CI:1.2–6.5)), as ABMs typically use random regional contacts that do not capture age-structured behaviour observed in contact surveys. Applying contact matrices from both approaches to an age-structured compartmental model, leads to noticeable differences in simulated epidemic outcomes regarding reproduction numbers and spreading dynamics between age groups. Our results suggest that naïve approaches to represent contact behaviour in ABMs based on population structure can be valid in settings with defined age-structures while settings with low a priori structure require more advanced methods to represent contact behaviour observed in contact surveys.

Read & Discuss → View Source →

12.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19613

StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns

Authors:

Vlad Sobal↗Shuo Yang↗Yuting Zhang↗Wei Xia↗Stefano Soatto↗

arXiv:2606.19613v1 Announce Type: cross Abstract: We introduce StaminaBench, a benchmark that measures the stamina of coding agents: how many consecutive interaction turns (change requests) they can handle before failing. Unlike the prevailing fraction-of-tasks-solved metric, this matches real vibe-coding where sessions run dozens or hundreds of turns. In StaminaBench, agents implement a REST API server and modify it across a tunable number of procedurally generated follow-up change requests - 100 in our experiments, resulting in codebases of up to 6,000 lines. Tests are generated fully programmatically without LLM involvement, ensuring reproducibility and reliability; change sequences are drawn from either a hardcoded or LLM-driven sampler, both constrained to a structured action space to ensure changes are valid. The agent and the server run in an isolated environment and communicate with the benchmark through HTTP, making testing fully black-box and language-agnostic. We evaluate six agent harnesses paired with seven open-source LLMs across 20 scenarios of 100 turns each and find that: (1) all the tested models fail within 5-6 turns, confirming that vibe-coding-style programming without thorough testing produces bugs; (2) passing test feedback back to the agent and allowing it to retry improves passed turn count by up to 12x; and (3) a good harness is required for strong performance: stronger models exhibit up to a 6x gap between their best and worst harness, while weaker models fail with any harness. We release the benchmark and the generated tasks to enable further research into multi-turn coding agent behavior. Benchmark code and data: github.com/amazon-science/StaminaBench.

Read & Discuss → View Source →

13.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13663

HyperTool: Beyond Step-Wise Tool Calls for Tool-Augmented Agents

Authors:

Yaxin Du↗Yifan Zhou↗Yujie Ge↗Jiajun Wang↗Xianghe Pang↗Shuo Tang↗Tuney Zheng↗Bryan Dai↗Jian Yang↗Siheng Chen↗

Tool-augmented LLM agents commonly rely on step-wise atomic tool calls, where each invocation, observation, and value transfer is exposed in the main reasoning trace. This creates an execution-granularity mismatch: locally deterministic tool workflows are unfolded into repeated model-visible decisions, consuming context and forcing the model to manage low-level dataflow in the trace. We introduce HyperTool, a unified executable MCP-style tool interface that changes the model-visible unit of tool execution. A model invokes HyperTool with a code block that can call existing tools through their original schemas, manipulate returned values, and pass intermediate results locally, folding deterministic tool subroutines into a single outer call. To train models to use this interface, we synthesize HyperTool-format trajectories from cross-tool compositional tasks and verify them in real MCP environments. On MCP-Universe, HyperTool improves average accuracy from 15.69\% to 35.29\% on Qwen3-32B and from 9.93\% to 33.33\% on Qwen3-8B, and surpass GPT-OSS and Kimi-k2.5 on average accuracy, showing that our HyperTool can substantially improve multi-step tool use.

Read & Discuss → View Source →

14.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.16131

Shift-and-Sum Quantization for Visual Autoregressive Models

Authors:

Jaehyeon Moon↗Bumsub Ham↗

Post-training quantization (PTQ) enables efficient deployment of deep networks using a small set of data. Its application to visual autoregressive models (VAR), however, remains relatively unexplored. We identify two key challenges for applying PTQ to VAR: (i) large reconstruction errors in attention-value products, especially at coarse scales where high attention scores occur more frequently; and (ii) a discrepancy between the sampling frequencies of codebook entries and their predicted probabilities due to limited calibration data. To address these challenges, we propose a PTQ framework tailored for VAR. First, we introduce a shift-and-sum quantization method that reduces reconstruction errors by aggregating quantized results from symmetrically shifted duplicates of value tokens. Second, we present a resampling strategy for calibration data that aligns sampling frequencies of codebook entries with their predicted probabilities. Experiments on class-conditional image generation, inpainting, outpainting, and class-conditional editing show consistent improvements across VAR architectures, establishing a new state of the art in PTQ for VAR.

Read & Discuss → View Source →

15.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.15648

Fusing Transferred Priors and Physics-based Decomposition for Underwater Image Enhancement

Authors:

Haochen Hu↗Yanrui Bin↗Zhengyan Zhang↗Minchen Wei↗Chih-yung Wen↗Bing Wang↗

The underwater images are captured within diverse water-medium conditions, leading to complex degradation, including color bias, low contrast, and blur effect. Recently, learning-based methods have demonstrated their potential for underwater image enhancement (UIE). However, most of the previous work focus on the training strategy or network design to make the enhanced result aligned well with the labels in datasets, ignoring that the labels are selected from the enhanced results of previous UIE methods and these pseudo-labels are noisy. Consequently, the performance of their models is not satisfactory to a certain extent. However, collecting the true labels of the underwater images is challenging. In this work, we propose a transfer learning-based UIE that does not require underwater images to have paired noisy or true labels for learning. Instead, the UIE task is first divided into global color correction, haze removal, and background noise suppression following the underwater physics. Then multiple types of prior from other vision tasks are leveraged as cross-domain supervision in each step. In this way, a novel UIE is available via transfer learning, and the physics-aligned UIE decomposition provides theoretical soundness. Qualitative and quantitative experiments demonstrate that our proposal based on physics and priors fusion achieves SOTA performance in the UIE task and effectively boosts downstream vision tasks, significantly outperforming benchmark methods. Project repo: https://github.com/Haru2022/P2-UIE.

Read & Discuss → View Source →

16.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2606.18537

Do as the Romans Do: Learning Universal Behaviors from Heterogeneous Agents

Authors:

Caleb Chang↗Davin Win Kyi↗Natasha Jaques↗Karen Leung↗

arXiv:2606.18537v1 Announce Type: new Abstract: Humans often acquire new skills by observing others, since observed behaviors implicitly reveal how to act in an environment. However, observations drawn from a heterogeneous population introduce conflicting behavioral signals, making it difficult to determine which behaviors are worth imitating. We address this challenge with General Reward Inference and Disentanglement (GRID), a social learning method that extracts universally useful behaviors from a heterogeneous population of demonstrators pursuing different goals. GRID decomposes per-agent reward functions into a general reward, capturing behaviors shared across all agents, and specific rewards, capturing individual preferences and objectives. Training exclusively on the general reward provides a new paradigm of generalist pretraining. It yields a generalist agent that internalizes universal environmental competencies, such as safety and basic task proficiency, without the mode-averaging bias that afflicts standard learning from demonstration techniques. This generalist serves as a superior prior for fine-tuning to downstream tasks, including preferences unseen during training. Experiments across a synthetic basis function decomposition, multi-agent Craftax, and a continuous autonomous driving simulator (Highway-Env) confirm that GRID successfully disentangles reward structure in a semantically meaningful way, outperforms standard learning from demonstration baselines, and enables more efficient and stable specialization.

Read & Discuss → View Source →

17.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.14260

ChronoID: Infusing Explicit Temporal Signals into Semantic IDs for Generative Recommendation

Authors:

Dongdong Nian↗Dongqi Fu↗Chenliang Xu↗Yinglong Xia↗Hong Li↗Hong Yan↗Jian Kang↗

arXiv:2606.14260v1 Announce Type: cross Abstract: Semantic IDs are crucial in generative recommendation, but with a fundamental limitation: temporal information is not well incorporated into semantic IDs. Instead, time influences recommendation only implicitly (e.g., through session construction heuristics, preference alignment, or sequence order), while existing semantic ID learning remains entirely time-agnostic. This design conflates interactions occurring under distinct temporal contexts into identical semantic representations, implicitly assuming that item semantics and user intent are temporally stationary. Such an assumption is misaligned with real-world recommendation scenarios, where evolving interaction rhythms play a central role. In this work, we investigate where and how the explicit time should be incorporated into semantic ID for generative recommendation. First, we systematically characterize the design space along three orthogonal dimensions of temporal signals and present a unified framework, ChronoID, for time-aware semantic ID learning. Then, by contributing a new time-explicit generation recommendation benchmark, ChronoID answers the questions: what is the effective way of infusing time, how to design the architecture, and where does the gain come from.

Read & Discuss → View Source →

18.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.16748

MyPCBench: A Benchmark for Personally Intelligent Computer-Use Agents

Authors:

Lawrence Keunho Jang↗Andrew Keunwoo Jang↗Jing Yu Koh↗Ruslan Salakhutdinov↗

Current benchmarks for computer-use agents evaluate models in impersonal environments. This leaves a gap between evaluation and deployment where personal assistants are expected to work across a user's whole digital life, including their context, historical data, and logged-in accounts. This gap is widest on web tasks, where live web evaluations cannot exercise sites that require logging in or personal information, the kind of site a real personal assistant has to drive. We introduce MyPCBench, which tests computer-use agents as personal assistants on a Linux desktop populated with 17 simulated real-world web applications and a full desktop stack, all seeded for one canonical persona, Michael Scott from The Office. We define 184 tasks in this environment, each inspired by a real request drawn from the OpenClaw community, and benchmark six closed and open-weight models with a uniform computer+bash tool surface. We find that the best model, Claude Opus 4.6, fully solves 55.4\% of the tasks, the only model above 50\%. Model failures cluster on tasks that span many applications and on long trajectories, where personalization stresses an assistant the most. We release the environment, task set, and agent harness at https://mypcbench.com.

Read & Discuss → View Source →

19.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13003

The Illusion of Multi-Agent Advantage

Authors:

Prathyusha Jwalapuram↗Hehai Lin↗Chuyuan Li↗Fangkai Jiao↗Sudong Wang↗Yifei Ming↗Zixuan Ke↗Chengwei Qin↗Giuseppe Carenini↗Shafiq Joty↗

Prevailing wisdom posits that Multi-Agent Systems (MAS) are superior to Single-Agent Systems (SAS), citing advantages like context protection, parallel processing and distributed decision-making. However, empirical support for this claim relies primarily on comparisons with SAS baselines using benchmarks that prioritize isolated reasoning tasks, which do not adequately assess these advantages. Focusing on automatically generated MAS that are designed for enhanced generalizability over manually-designed counterparts, we perform a rigorous, systematic evaluation against SAS, specifically Chain-of-Thought with Self-Consistency (CoT-SC). Across traditional reasoning datasets and tasks with interactive multi-step workflows (e.g., BrowseComp-Plus), we demonstrate that automatic MAS consistently underperform CoT-SC despite being up to 10x more expensive. To isolate these failures from limitations inherent to task structure, we introduce a diagnostic synthetic dataset tailored for MAS featuring explicit task decomposition, context separation and parallelization potential. We show that expert-architected MAS consistently outperforms automatically generated architectures in both raw performance and cost-efficiency on this dataset, demonstrating that existing evaluation frameworks mask critical architectural gaps and inefficiencies of complex MAS by failing to account for the marginal utility of increased computational cost. Critically, systematic deconstruction of the generated MAS architectures reveals that current automated design paradigms produce architectural bloat that prioritizes superficial complexity which does not translate into functional utility, exposing a fundamental misalignment with multi-agent principles.

Read & Discuss → View Source →

20.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.20376

CRAX: Fast Safe Reinforcement Learning Benchmarking

Authors:

Tristan Tomilin↗Mourad Boustani↗Mickey Beurskens↗Thiago D. Sim\~ao↗

arXiv:2606.20376v1 Announce Type: cross Abstract: Safety is a core concern for deploying reinforcement learning (RL) agents in real-world domains such as robotics and autonomous driving. While benchmarks have been central to progress in RL, existing safety benchmarks with high-fidelity 3D physics remain computationally slow, limiting large-scale experimentation and rapid prototyping. To address this gap, we propose CRAX (Constrained RL Accelerated with JAX). Built on top of the MuJoCo XLA (MJX) physics engine with realistic 3D dynamics, CRAX leverages vectorized operations and hardware acceleration, yielding up to ~100x speedups over comparable CPU-based safety benchmarks. The benchmark features six environment suites and three agent-specific tasks, each spanning three difficulty levels. Evaluating six popular safe RL methods shows that no single approach dominates across all tasks, and reveals the trade-offs between performance and safety. We find that curriculum learning across difficulty levels and safety transfer can improve performance over direct training in harder settings.

Read & Discuss → View Source →

21.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.20487

Beyond Global Replanning: Hierarchical Recovery for Cross-Device Agent Systems

Authors:

Shu Yao↗Yuhua Luo↗Qian Long↗Jingru Fan↗Zhuoyuan Yu↗Yuheng Wang↗Lin Wu↗Yufan Dang↗Huatao Li↗Chen Qian↗

Real-world computer-use tasks often span multiple applications and devices, requiring agents to coordinate heterogeneous environments under dynamic runtime failures. Existing multi-device agent systems support task decomposition and cross-device assignment, but recovery remains largely coarse-grained: when execution fails, they typically retry the same strategy, reassign the subtask, or revise the global plan, without systematically modeling the device-local strategy space. This limits their ability to distinguish failures that can be repaired within the current device from those that require cross-device replanning. We propose H-RePlan, a hierarchical replanning framework for multi-device agents with unified API–CLI–GUI execution. H-RePlan equips each device with interchangeable execution strategies and separates device-local strategy recovery from orchestrator-level global replanning through a compact cross-layer failure abstraction. To evaluate this capability, we introduce HeraBench, a fault-injected benchmark that constructs cross-device workflows over Linux and Android devices and injects strategy- and device-level failures. Experiments show that H-RePlan substantially outperforms single-strategy and coarse-grained multi-device baselines, achieving higher completion, instruction adherence, and perfect-pass rates while reducing the token cost required for reliable end-to-end success. These results demonstrate that scope-aware hierarchical recovery is essential for robust multi-device agent execution.

Read & Discuss → View Source →

22.

arXiv (quant-ph) 2026-06-17 DOI: arXiv:2605.01169

A Quantum Approach to Stochastic Optimization in Insurance Underwriting

Authors:

Mitchell Bordelon↗Maurice Garfinkel↗Vivek Dixit↗Thomas Whitehead↗Jenny Holzbauer↗Guillermo Mijares Vilarino↗Alberto Maldonado Romo↗Abhijit Mitra↗Vaibhaw Kumar↗Jean Utke↗

arXiv:2605.01169v2 Announce Type: replace Abstract: The presence of stochastic elements in combinatorial optimization problems makes them particularly challenging, as such problems quickly become intractable for classical computers even at relatively small sizes. In this work, we propose a novel quantum-classical hybrid scheme for solving a class of stochastic optimization problems known as chance-constrained knapsack problems, in which item weights follow probability distributions and constraints may be violated within a specified risk tolerance. Our method employs knapsack-specific QAOA-based circuits to generate samples which, when combined with a new self-consistent classical recovery scheme introduced in this work, produce high-quality solutions. Experiments carried out on IBM Heron processors, using circuits with depths up to 177 and comprising 3443 gates acting on as many as 150 qubits, yield solutions that indicate performance comparable to classical optimization schemes. The proposed quantum-classical scheme paves the way to tackling such problems, with the potential to outperform approaches that rely solely on classical computation.

Read & Discuss → View Source →

23.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.05551

Conformal Risk-Averse Decision Making with Action Conditional Guarantee

Authors:

Zihan Zhu↗Shayan Kiyani↗George Pappas↗Hamed Hassani↗

arXiv:2606.05551v2 Announce Type: replace-cross Abstract: Reliable decision making pipelines powered by machine learning models require uncertainty quantification (UQ) methods that come with explicit safety guarantees. Conformal prediction provides such UQ by wrapping ML predictions into prediction sets, and recent work by Kiyani et al. (2025b) established that these sets can be translated into optimal risk-averse decision policies – yet only inheriting marginal safety guarantees. We generalize and strengthen their results by (i) introducing action-conditional conformal prediction, which yields safety guarantees conditioned explicitly on each action taken by the decision maker, (ii) showing that action-conditional prediction sets serve as a proxy for the feasible decision space for risk-averse decision makers aiming to optimize action-conditional value-at-risk, and (iii) proposing a principled finite-sample algorithm based on pinball-loss minimization, connecting the framework of Gibbs et al. (2025) to action-conditional guarantees. Experiments on two real-world datasets confirm that our approach significantly improves action-conditional performance over conformal baselines.

Read & Discuss → View Source →

24.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2606.14122

Beyond Perplexity: UTF-8 Validity in Byte-aware Language Models

Authors:

Sangwhan Moon↗Daisuke Oba↗Youmi Ma↗Tatsuya Hiraoka↗Naoaki Okazaki↗

Byte-level tokenization enables language models to handle any Unicode input, but models can generate invalid UTF-8 sequences when encountering rare or unseen characters. We investigate the relationship between training scale and UTF-8 generation reliability with a 355M parameter model trained on 80B tokens from a balanced multilingual corpus of English, Japanese, Korean, and Chinese. We introduce multiple evaluation protocols that isolate UTF-8 structural validity from language modeling. UTF-8 validity convergence lags perplexity by a roughly a factor of two: perplexity stabilizes after 2.1B tokens, but UTF-8 validity requires 4.2B tokens. In context-free generation, rare characters achieve higher structural validity than common characters, suggesting over-specialization of frequent character representations. Through experiments, we observed that reliable UTF-8 generation is a distinct capability requiring evaluation beyond perplexity.

Read & Discuss → View Source →

25.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16613

CoffeeBench: Benchmarking Long-Horizon LLM Agents in Heterogeneous Multi-Agent Economies

Authors:

Issa Sugiura↗Daichi Hattori↗Kazuo Araragi↗Keita Ogawa↗Shota Onose↗Taro Makino↗Teppei Usuki↗Takashi Ishida↗

arXiv:2606.16613v1 Announce Type: new Abstract: As LLM agents become capable of increasingly long-horizon tasks, evaluating their performance in economic systems is becoming increasingly important. Unlike existing benchmarks that primarily evaluate a single agent interacting with a passive environment, economic systems are inherently multi-agent, requiring autonomous agents to communicate, negotiate, and transact while pursuing their own objectives over extended periods. We introduce CoffeeBench, a benchmark for evaluating LLM agents in a long-horizon multi-agent economy composed of heterogeneous firms. In CoffeeBench, two farmers, two roasters, and two retailers autonomously operate their businesses over a 90-day simulation, each seeking to maximize cumulative net income through communication and transactions while managing cash, inventory, and pricing. The evaluated model controls one coffee roaster, while the remaining firms are controlled by fixed reference agents. Across several recent open-weight and proprietary LLMs, all models outperform a passive baseline that takes no actions, with most achieving positive net income. Analysis of agent behavior reveals substantial differences in long-horizon economic interaction: higher-performing models communicate more actively with other firms, whereas Claude~Haiku~4.5 exhibits an idle-drift failure mode, repeatedly choosing inaction despite producing coherent assessments and plans. We release our code and agent trajectories to support future research.

Read & Discuss → View Source →