Explore the Frontier of Global Academia

01.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.14409

Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stack

Authors:

He Zhang↗Lingzhu Xiang↗Haitao Lin↗Zeyu Huang↗Minghui Wang↗Dingyan Zhong↗Yubo Dong↗Yihao Wu↗Yongming Rao↗Dongsheng Zhang↗Wanjia He↗Ling Chen↗…

arXiv:2606.14409v1 Announce Type: cross Abstract: In this report, we present Hy-Embodied-0.5-VLA, abbreviated as HyVLA-0.5, an end-to-end system that spans the full robot learning stack: data collection, model design, continued pre-training and supervised fine-tuning, RL post-training, and real-world deployment. Each component serves a distinct role in this stack.

Read & Discuss → View Source →

02.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.15110

Physics-Driven Zero-Shot MRI Reconstruction with Non-local Image Priors

Authors:

Lingtong Zhang↗Wenlei Li↗Mu He↗Li Xiao↗Yang Ji↗

Zero-Shot Self-Supervised Learning (ZS-SSL) has emerged as a promising paradigm for accelerated Magnetic Resonance Imaging (MRI) reconstruction, eliminating the reliance on fully-sampled external datasets. However, learning solely from a single under-sampled scan suffers from supervision scarcity and optimization instability, often leading to overfitting or artifacts. To address these challenges, we propose a robust physics-driven ZS-SSL framework that synergizes physical consistency with image-domain non-local priors. Our method introduces three core innovations: (1) a Coil Sensitivity Map (CSM)-Guided Dynamic Repository, which stabilizes the training trajectory by filtering physically inconsistent artifacts based on coil sensitivity constraints; (2) a SPIRiT-based regularization, which enforces k-space self-consistency via a learned correlation kernel and stochastic masking; (3) a Non-Local Self-Similarity (NSS) Pixel Bank, which leverages the high-fidelity reference established by the former modules to explicitly mine non-local anatomical similarities, thereby augmenting supervision in the image domain. Extensive experiments on the FastMRI dataset demonstrate that our approach achieves state-of-the-art performance, particularly under high acceleration factors, effectively bridging the gap between zero-shot learning and supervised methods. The code is available at https://github.com/Zolento/NS-SSL.

Read & Discuss → View Source →

03.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.19308

Enhancing Decision-Making with Large Language Models through Multi-Agent Fictitious Play

Authors:

Leyang Shen↗Yang Zhang↗Xiaoyan Zhao↗Chun Kai Ling↗Tat-Seng Chua↗

Large language model (LLM)-based multi-agent systems (MAS) have demonstrated great potential in solving tasks with execution complexity, by distributing subtasks across cooperative agents. However, this divide-and-conquer paradigm falls short on decision-making tasks that are also prevalent in the real world. These tasks require simultaneous reasoning from the stances of all involved stakeholders whose decisions are mutually dependent and thus cannot be solved in isolation. We characterize this challenge as stance entanglement, a form of decision complexity distinct from execution complexity. To address it, we propose Multi-Agent Fictitious Play (MAFP), a novel MAS paradigm that represents stakeholder stances as agents and formulates decision-making as an equilibrium-seeking process. Built on the game-theoretic principle of fictitious play, MAFP iteratively updates each agent's decision by best responding to the empirical mixture of other agents' past decisions. This enables agents to expose and address one another's weaknesses, progressively improving decision quality and robustness. We evaluate MAFP on challenging decision-making tasks that test the capability of deciding strategies for competitive scenarios prior to acting. MAFP outperforms both single-round and multi-round baselines on two complementary metrics, tournament strength and robustness, demonstrating its effectiveness in addressing stance entanglement.

Read & Discuss → View Source →

04.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.13513

CloudCons: A Comprehensive End-to-End Benchmark for Cloud Resource Consolidation

Authors:

Xiaobin Zhang↗Lefei Shen↗Mouxiang Chen↗Zhuo Li↗Hongkai Li↗Han Fu↗Jianling Sun↗Xiaoxue Ren↗Chenghao Liu↗

arXiv:2606.13513v1 Announce Type: new Abstract: Driven by conservative over-provisioning to guarantee service reliability, resource utilization in cloud data centers remains at low levels. To mitigate this, the forecast-then-optimize paradigm has emerged to optimize consolidation by anticipating future demands. While emerging time series foundation models promise to enhance this paradigm through zero-shot generalization, existing benchmarks focus solely on prediction error metrics. The actual decision utility of these advanced models remains unverified, rendering their practical value for downstream tasks uncertain. To bridge this gap, we propose CloudCons, a comprehensive end-to-end benchmark designed to evaluate forecasting models within the specific context of cloud resource consolidation. We build high-quality datasets that cover diverse workloads from Huawei Cloud, Microsoft Azure, and Google Borg, capturing distinct service characteristics ranging from synchronized diurnal rhythms to stochastic, pulse-like bursts and high-frequency noise. We conduct an extensive evaluation of statistical, deep learning, and foundation models. Our experiments reveal a pivotal finding: while foundation models demonstrate superior zero-shot forecasting accuracy, this advantage does not inherently translate into better decision utility. Of practical significance, we systematically analyze how the selection of predictive quantiles acts as a critical lever. We provide actionable guidelines for calibrating these selections to balance the trade-off between resource efficiency and service reliability, offering vital insights for real-world deployment decisions.

Read & Discuss → View Source →

05.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2305.08175

ResidualPlanner+: a scalable matrix mechanism for marginals and beyond

Authors:

Guanlin He↗Yingtai Xiao↗Levent Toksoz↗Zeyu Ding↗Danfeng Zhang↗Daniel Kifer↗

arXiv:2305.08175v5 Announce Type: replace-cross Abstract: Noisy marginals are a common form of confidentiality protecting data release and are useful for many downstream tasks such as contingency table analysis, construction of Bayesian networks, and even synthetic data generation. Privacy mechanisms that provide unbiased noisy answers to linear queries (such as marginals) are known as matrix mechanisms. We propose ResidualPlanner and ResidualPlanner+, two highly scalable matrix mechanisms. ResidualPlanner is both optimal and scalable for answering marginal queries with Gaussian noise, while ResidualPlanner+ provides support for more general workloads, such as combinations of marginals and range queries or prefix-sum queries. ResidualPlanner can optimize for many loss functions that can be written as a convex function of marginal variances (prior work was restricted to just one predefined objective function). ResidualPlanner can optimize the accuracy of marginals in large scale settings in seconds, even when the previous state of the art (HDMM) runs out of memory. It even runs on datasets with 100 attributes in a couple of minutes. Furthermore, ResidualPlanner can efficiently compute variance/covariance values for each marginal (prior methods quickly run out of memory, even for relatively small datasets). ResidualPlanner+ provides support for more complex workloads that combine marginal and range/prefix-sum queries (e.g., a marginal on race, a range query on age, and a combined race/age tabulation that answers age range queries for each race). It even supports custom user-defined workloads on different attributes. With this added flexibility, ResidualPlanner+ is not necessarily optimal, however it is still extremely scalable and outperforms the prior state-of-the-art (HDMM) on prefix-sum queries both in terms of accuracy and speed.

Read & Discuss → View Source →

06.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.13669

Agents-K1: Towards Agent-native Knowledge Orchestration

Authors:

Zongsheng Cao↗Bihao Zhan↗Jinxin Shi↗Jiong Wang↗Fangchen Yu↗Zhijie Zhong↗Zijie Guo↗Tianshuo Peng↗Zhuo Liu↗Yi Xie↗Xiang Zhuang↗Yue Fan↗…

arXiv:2606.13669v1 Announce Type: new Abstract: Current LLM-based research agents have advanced through agent orchestration, yet largely overlook scientific knowledge orchestration. Existing works often reduce papers to abstracts, surface mentions, and flat \texttt{cites} edges, omitting key entities, claims, evidence, mechanisms, and method lineages essential for scientific reasoning. To this end, we introduce Agents-K1, an end-to-end knowledge orchestration pipeline that converts raw documents into agent-native scientific knowledge graphs. Agents-K1 integrates three components under a unifying theoretical foundation: a multimodal parser whose five-module schema captures entities, multimodal evidence, citations, and typed inter-entity relations across the full paper rather than abstracts alone; a 4B information-extraction backbone trained with GRPO under a rule-based reward; and a graphanything CLI, a tri-source agent interface that unifies web search, multimodal graph retrieval, and cross-document traversal. On top of this, we process 2.46 million scientific papers across six subjects to produce Scholar-KG, of which we release a one-million-paper subset, and the full Scholar-KG is accessible via the SCP link below. The same pipeline can be extended to general-domain corpora and to schema-conformant data synthesis. Extensive experiments demonstrate that Agents-K1 achieves superior performance in scientific information extraction, knowledge graph construction, and multi-hop scientific reasoning.

Read & Discuss → View Source →

07.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.18203

RubricsTree: Scalable and Evolving Open-Ended Evaluation of Personal Health Agents across Health Memory and Medical Skills

Authors:

Weizhi Zhang↗Zechen Li↗Hamid Palangi↗Ben Graef↗A. Ali Heydari↗Simon A. Lee↗Salman Rahman↗Ray Luo↗Zeinab Esmaeilpour↗Erik Schenck↗Chloe Zhang↗Yamin Li↗…

The LLM-empowered personal health agents with user health (sensor) metrics have offered a promising pathway to alleviate global disparities in healthcare access. However, large-scale clinical deployment remains constrained by an open-ended evaluation bottleneck: physician annotation is reliable but costly and unscalable, while LLM-as-a-judge evaluators are scalable but subjective, inconsistent, and sometimes clinically misaligned. We introduce RubricsTree, a scalable evaluation framework with an expert-aligned hierarchical taxonomy of over 100 atomic, clinically-verifiable Boolean rubrics, evolving from the insights of 4,000 real user queries through an iterative human-in-the-loop curation protocol with an expertise panel led by an experienced physician. A context-aware adaptive router activates only the relevant auto-weighted rubric subset per query, providing the throughput needed for scalable evaluation with expert-aligned quality. Through a systematic meta-evaluation, we show that RubricsTree (i) substantially exceeds a strong large-scale evaluation baseline in expert alignment on challenging open-ended queries; (ii) reliably penalizes contextually degraded responses; and (iii) when used as structured instructions, text feedback, or training rewards for performance optimization, yields up to ~66% relative gains on HealthBench for Gemini, GPT, and Qwen model families. RubricsTree thus provides a scalable, auditable, and evolving evaluation infrastructure required for the continuous optimization of product-level personal healthcare AI.

Read & Discuss → View Source →

08.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.13192

Reasoning for Mobile User Experience with Multimodal LLMs: Task, Benchmark, and Approach

Authors:

Ruichao Mao↗Zhou Fang↗Teng Guo↗Hao Yang↗Yaping Li↗Shaohua Peng↗Maji Huang↗Xiaoyu Lin↗Shuoyang Liu↗Xuepeng Li↗Yuyu Zhang↗Hai Rao↗…

arXiv:2606.13192v1 Announce Type: new Abstract: User experience (UX) centered on usability, perceived consistency, and functional clarity is fundamental to real-world user interfaces (UI). The application of multimodal large language models (MLLMs) in the field of user interfaces is evolving rapidly, such as visual element grounding, graphical user interface (GUI) agents, and design-to-code generation. However, research efforts on evaluating UX based on UI screenshots are still immature. To address this, we propose UXBench, a novel multimodal benchmark consisting of 2,000 VQA data samples designed to assess MLLMs' ability to perform UI-based reasoning. UXBench includes 8 tasks based on real-world UI screenshots that require fine-grained diagnosis of UX issues across layout relationships, visual hierarchy, and content consistency. Our extensive evaluation of mainstream MLLMs shows that they remain fundamentally limited in their capacity for UI-based reasoning. The results underscore the need for further advancements in this area. To bridge this gap, we propose UI-UX, an MLLM based on Qwen3-VL-4B-Thinking foundation model and enhanced via reinforcement learning with two key innovations: a reward routing mechanism that dynamically balances perceptual understanding and logical reasoning during inference, and an asymmetric transition reward that suppresses redundant or insufficient reasoning steps. Experiments demonstrate that UI-UX achieves state-of-the-art (SOTA) performance on UXBench, attaining an accuracy of 0.7963 – surpassing Claude-4.5-Sonnet's 0.6550 – while exhibiting strong generalization across diverse UI tasks and maintaining low inference latency.

Read & Discuss → View Source →

09.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2605.20708

Rethinking Cross-Layer Information Routing in Diffusion Transformers

Authors:

Chao Xu↗Maohua Li↗Qirui Li↗Yixuan Xu↗Yanke Zhou↗Yunhe Li↗Cuifeng Shen↗Hanlin Tang↗Kan Liu↗Tao Lan↗Lin Qu↗Shao-Qun Zhang↗…

Diffusion Transformers (DiTs) have become a de facto backbone of modern visual generation, and nearly every major axis of their design – tokenization, attention, conditioning, objectives, and latent autoencoders – has been extensively revisited. The residual stream that governs how information accumulates across layers, however, has been directly inherited from the original Transformer. In this paper, we present a systematic empirical analysis of cross-layer information flow in DiTs, jointly along depth and denoising timestep, and identify three concrete symptoms of traditional residual addition, namely monotonic forward magnitude inflation, sharp backward gradient decay, and pronounced block-wise redundancy. Motivated by this diagnosis, we propose Diffusion-Adaptive Routing (\textsc{DAR}), a drop-in residual replacement that performs learnable, timestep-adaptive, and non-incremental aggregation over the history of sublayer outputs. Moreover, the proposed \textsc{DAR} is compatible with many modern Transformer enhancement methods, such as REPA. On ImageNet $256\times256$, \textsc{DAR} improves SiT-XL/2 by $2.11$ FID ($7.56$ vs.\ $9.67$) and matches the baseline's converged quality with $8.75\times$ fewer training iterations. Stacked on top of REPA, it yields a $2\times$ training acceleration in the early stage, suggesting cross-layer information routing as an underexplored design axis in diffusion modeling, one that operates orthogonally to existing representation-alignment objectives. Beyond pretraining, \textsc{DAR} can also be applied during the fine-tuning stage of large-scale T2I models and preserves high-frequency details during Distribution Matching Distillation.

Read & Discuss → View Source →

10.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.17250

Rethinking Groups in Critic-Free RLVR

Authors:

Yihong Wu↗Liheng Ma↗Lingfeng Xiao↗Muzhi Li↗Xinyu Wang↗Yingxue Zhang↗Jian-Yun Nie↗

Reinforcement learning (RL) has become a central paradigm for post-training large language models. Existing critic-free RL methods typically generate a group of rollouts for the same question to estimate value baselines for advantage computation. However, this design suffers from data inefficiency, group synchronization barriers, and inflexibility with structured rollouts. In this work, we revisit the role of the ``group'' and show that its underlying function is not merely to estimate baselines but to prevent false penalties on negative samples. Building on this insight, we propose negative token filtering, a simple and effective strategy that enables stable single-rollout training. We apply it to two batch-level advantage methods, achieving comparable performance on reasoning tasks and stronger performance on agentic tasks relative to group-based RL techniques.

Read & Discuss → View Source →

11.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11709

RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation

Authors:

Leyi Pan↗Shuchang Tao↗Yunpeng Zhai↗Lingzhe Zhang↗Zhaoyang Liu↗Bolin Ding↗Aiwei Liu↗Lijie Wen↗

On-policy self-distillation (OPSD) provides dense, token-level supervision for reasoning models by aligning a model's own distribution with the distribution it produces under privileged context, typically a verified solution. However, we show that the learning signal drawn from this distributional gap concentrates on style tokens rather than task-bearing ones, as the hinted model tends to produce more direct, shorter outputs. We term this pathology privilege-induced style drift, which destabilizes training or causes response length to shrink. To address this, we propose RLCSD (Reinforcement Learning with Contrastive on-policy Self-Distillation), which mitigates this drift by contrasting the teacher-student gap under a correct hint against that under a wrong hint, suppressing the style shift that conditioning on a hint tends to induce regardless of correctness, and yielding a signal that is more concentrated on task-bearing tokens. Experiments on Qwen3 (1.7B/4B/8B) and Olmo-3-7B-Think across mathematical and logical reasoning show that RLCSD consistently outperforms GRPO and prior OPSD methods. We further show that the contrastive principle is general: it plugs into existing OPSD methods to improve them, and its underlying insight extends to the broader cross-model on-policy distillation setting.

Read & Discuss → View Source →

12.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.12942

PRISMR: Overcoming Parse Collapse in Multimodal Listwise Ranking via Parameterized Representation Internalization

Authors:

Hao Jiang↗Xin Li↗Annan Wang↗Zhi Yang↗Haoxiang Zhang↗Yichi Zhang↗Weisi Lin↗

arXiv:2606.12942v1 Announce Type: new Abstract: Generative listwise ranking with Large Multimodal Models (LMMs) aims to capture global list context in a single forward pass, but its effectiveness degrades in long-context multimodal scenarios. We identify a recurring failure mode, parse collapse, where the autoregressive decoder produces fluent yet incomplete rankings by silently omitting candidates and terminating early. This failure stems from limited context utilization rather than simple formatting mistakes, making prompt engineering and constrained decoding insufficient. We propose PRISMR (Parameterized Representation Internalization for Semantic Multimodal Ranking), a framework that replaces transient in-context list processing with parametric structural conditioning. PRISMR uses a lightweight hypernetwork to encode multimodal candidates in parallel and generate item-specific LoRA weights, which are synthesized into an instance-specific adapter for a LMM. This paradigm enables more robust internalization of list structure while preserving the base model. We further introduce a large-scale multimodal review-ranking benchmark for evaluation. Experiments demonstrate that PRISMR substantially reduces parse collapse, improves listwise ranking performance, and transfers effectively across domains and instruction-tuned backbones.

Read & Discuss → View Source →

13.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.12837

LoHoSearch: Benchmarking Long-Horizon Search Agents Beyond the Human Difficulty Ceiling

Authors:

Jiarui Zhao↗Rongzhi Zhang↗Lingchuan Liu↗Hao Yang↗Xunliang Cai↗Xi Su↗

Search agent benchmarks exemplified by BrowseComp have rapidly saturated over the past year, with the strongest models surpassing 90% accuracy. Since these benchmarks are predominantly human-authored, annotators lack a global perspective on entity statistics and cannot systematically maximize search space size and structural complexity. This creates a difficulty ceiling that is hard to break. To address this, we introduce LoHoSearch (Long-Horizon Search Agents), a challenging benchmark comprising 544 human-verified questions across 11 domains. LoHoSearch is constructed via an automated pipeline built upon a knowledge graph covering over 7 million Wikipedia entities, which selects relations with large search spaces and assembles them into structurally complex questions with KG-verified unique answers. Our evaluation demonstrates that even the strongest model achieves only 34.74% accuracy, and existing context management strategies (best +6.8%) yield far smaller gains than on prior benchmarks. LoHoSearch provides a more demanding standard for evaluating long-horizon reasoning and context management in search agents.

Read & Discuss → View Source →

14.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19980

ENPIRE: Agentic Robot Policy Self-Improvement in the Real World

Authors:

Wenli Xiao↗Jia Xie↗Tonghe Zhang↗Haotian Lin↗Letian "Max" Fu↗Haoru Xue↗Jalen Lu↗Yi Yang↗Cunxi Dai↗Zi Wang↗Jimmy Wu↗Guanzhi Wang↗…

arXiv:2606.19980v1 Announce Type: new Abstract: Achieving dexterous robotic manipulation in the real world heavily relies on human supervision and algorithm engineering, which becomes a central bottleneck in the pursuit of general physical intelligence. Although emerging coding agents can generate code to automate algorithm search, their successes remain largely confined in digital environments. We conjecture that the missing abstraction to automate robotics research is a repeatable feedback loop for real-world policy improvement: reset the scene, execute a policy, verify the outcome, and refine the next iteration. To bridge this gap, we introduce ENPIRE, a harness framework for coding agents that instantiates this physical feedback routine with four core modules: an Environment module (EN) for automatic reset and verification, a Policy Improvement module (PI) that launches policy refinement, a Rollout module (R) to evaluate policies with one or multiple physical robots operating in parallel, and an Evolution module (E) in which coding agents analyze logs, consult literature, improve training infrastructure and algorithm code to address failure modes. This closed-loop system transforms real-world manipulation learning into a controllable optimization procedure, minimizing human effort while allowing fair ablations across training recipe and agent variants. Powered by ENPIRE, frontier coding agents can autonomously train a policy to achieve a 99% success rate on challenging, dexterous manipulation tasks, such as organizing a pin box, fastening a zip tie, and tool use, a process that further accelerates when we dispatch an agent team on a robot fleet. Our results suggest a practical and scalable path toward deploying coding agents to autonomously advancing robotics in the physical world.

Read & Discuss → View Source →

15.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.12871

DailyReport: An Open-ended Benchmark for Evaluating Search Agents on Daily Search Tasks

Authors:

Jingxuan Han↗Wei Liu↗Mingyang Zhu↗Youpeng Wang↗Ziwen Wang↗Lin Qiu↗Xuezhi Cao↗Xunliang Cai↗Zheren Fu↗Licheng Zhang↗Zhendong Mao↗

arXiv:2606.12871v1 Announce Type: new Abstract: Search Agents (SAs) typically leverage large language models (LLMs) to support complex information-seeking tasks by autonomously exploring web sources and synthesizing information into comprehensive responses. For SAs evaluation, prior benchmarks mainly focus on specialized tasks that are unlikely to arise in real-world user scenarios. Moreover, their reliance on coarse task-level rubrics often limits evaluation interpretability. To bridge this gap, we introduce DailyReport, an open-ended benchmark to evaluate SA capabilities on daily search tasks. It contains 150 open-ended tasks with 3,546 associated rubrics, capturing widely discussed and timely information demands of real-world users. Each task is decomposed into subtasks and evaluated with cascade rubrics across disentangled dimensions. Through cascade performance attribution and user-centric aggregation, we derive highly interpretable scores for each dimension, along with a user preference score. Our results on 17 agentic systems show that current systems still fall short of users' expectations. To facilitate future research, our dataset and code are made publicly available at https://github.com/AGI-Eval-Official/DailyReport.

Read & Discuss → View Source →

16.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2509.25787

Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking

Authors:

Wen Wen↗Tianwu Zhi↗Kanglong Fan↗Yang Li↗Xinge Peng↗Yabin Zhang↗Yiting Liao↗Junlin Li↗Li Zhang↗

Improving vision-language models (VLMs) in the post-training stage typically relies on supervised fine-tuning or reinforcement learning, methods that necessitate costly, human-annotated data. While self-supervised techniques have proven effective for enhancing reasoning capabilities, their application to perceptual domains such as image quality assessment (IQA) remains largely unexplored. In this work, we introduce EvoQuality, a novel framework that enables a VLM to autonomously refine its quality perception capabilities without any ground-truth labels. EvoQuality adapts the principle of self-consistency to the ranking-based nature of IQA. It generates pseudo-labels by performing pairwise majority voting on the VLM's own outputs to establish a consensus on relative quality. These pseudo-rankings are then formulated into a fidelity reward that guides the model's iterative evolution through group relative policy optimization (GRPO). By iteratively leveraging its own predictions, EvoQuality progressively refines the VLM's perceptual capability. Extensive experiments show that EvoQuality boosts the base VLM's zero-shot performance by 31.8% on PLCC across diverse IQA benchmarks. Remarkably, despite being entirely self-supervised, EvoQuality achieves performance that is competitive with, or even surpasses, state-of-the-art supervised VLM-based IQA models, outperforming these models on 5 out of 7 IQA benchmarks. Furthermore, the framework demonstrates significant flexibility, allowing it to be stacked with pre-trained IQA models to bolster generalization on unseen datasets. Codes and checkpoints will be available at https://github.com/bytedance/EvoQuality.

Read & Discuss → View Source →

17.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11806

External Experience Serving in Production LLM Systems: A Deployment-Oriented Study of Quality-Cost Trade-offs

Authors:

Lin Sun↗Heming Zhang↗Xiangzheng Zhang↗

Production LLM systems accumulate reusable operational experience, but the practical deployment issue is not merely whether such experience can help. It is how different serving strategies trade off quality against online cost under realistic constraints. Injecting external experience can improve task quality, yet it also increases prompt burden, latency, and serving pressure. We study external experience serving as a deployment-oriented quality-cost trade-off problem. We evaluate this question in a real production moderation setting, with tool-use and GPQA as supporting contrast tasks that expose different output-cost regimes. We compare no-experience baselines, random experience controls, global prompt injection, and retrieval-based selective injection, and analyze both task quality and serving cost. The results show that, once experience becomes case-dependent, selective retrieval provides a stronger operating point than unconditional global injection. They further show that retrieval quality matters more than simply increasing Top-$K$, and that the same serving policy can exhibit substantially different cost-benefit profiles across short-output and decode-heavy regimes. These findings suggest that external experience is best treated as a selective, cost-aware serving decision rather than as a universal add-on. Overall, in the settings studied here, external experience pays off only when both the serving interface and the task-specific cost structure make its quality gains worth the online cost.

Read & Discuss → View Source →

18.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2503.07459

MedicalAgentsBench for Complex Medical Reasoning: Comparing Internalized Reasoning Models versus Externalized Agent-based Frameworks

Authors:

Yanjun Shao↗Xiangru Tang↗Jiwoong Sohn↗Jiapeng Chen↗Yuxuan Liao↗Jiayi Zhang↗Jinyu Xiang↗Fang Wu↗Yilun Zhao↗Chenglin Wu↗Wenqi Shi↗Arman Cohan↗…

Complex medical reasoning requires integrating heterogeneous clinical evidence across multiple inference steps. Large language models (LLMs) now approach this through two routes: internalized reasoning and externalized agent scaffolding (frameworks that decompose problems collaboratively amongst multiple LLMs). To determine whether these routes are exclusive or complementary, we introduce MedicalAgentsBench, a filtered benchmark of 862 complex clinical questions drawn from the union of eight medical datasets via difficulty-aware curation and contamination screening. Evaluating three internalized reasoning models (DeepSeek-R1, o1-mini, and o3-mini), seven base models, and nine externalized agent-based methods, we find that internalized and externalized approaches each independently improve performance, and that their benefits compound: the highest accuracy is achieved by layering agent workflows onto an internalized reasoning model (i.e., o3-mini + MDAgents with 35.1%). Pareto analysis shows this combination dominates the cost-performance frontier; moreover, lightweight optimization on inexpensive models offers an entry point for resource-constrained settings. Our benchmark is at https://github.com/gersteinlab/MedicalAgentsBench.

Read & Discuss → View Source →

19.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16175

PAL-Bench: Evidence-Grounded Profile Reconstruction from Longitudinal Personal Albums

Authors:

Qiwei Yan↗Zhiqiang Yuan↗Zexi Jia↗Nanxing Hu↗Kailin Lyu↗Jie Zhou↗Jinchao Zhang↗

arXiv:2606.16175v1 Announce Type: new Abstract: Longitudinal personal albums are weak-schema multimodal databases: noisy perceptual records whose key facts require joins across faces, text, timestamps, locations, and repeated events. Existing visual, video, document, and lifelog benchmarks test sub-problems, but not album-scale profile reconstruction with social identity binding and evidence citation. Benchmarking this task is difficult because the ground truth needed for evaluation–owner profiles, social graphs, face-name maps, and evidence provenance–is private state that real albums cannot safely release. We introduce PAL-Bench, a controlled benchmark for evidence-grounded reconstruction under a public-record contract. Its Evidence Compiler builds latent private worlds, programs target-level evidence paths, renders album pixels, re-measures them through perception pipelines, and exports audited public/private views. Agents receive only perception-derived public records; targets, identifier maps, and evidence paths remain hidden. PAL-Bench contains 50 synthetic users, 36,659 public photo records, and 2,799 targets over owner facts, identities, and relations. A privacy-preserving audit with 10 participants confirms that PAL-Bench evidence structures match real private albums, though equivalent releases remain privacy-prohibitive. Across seven systems and two compute-matched diagnostics, a seven-metric protocol reveals a gap between plausible profile summarization and faithful social reconstruction: systems recover some owner facts but struggle with recurring identities and evidence citation. PAL-TRACE, a reference framework that freezes identity bindings before owner-fact mining, performs best but leaves hard identity resolution far from solved. PAL-Bench provides a testbed for perceptual entity resolution, multimodal data integration, temporal evidence aggregation, and provenance-aware structured prediction.

Read & Discuss → View Source →

20.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2509.22050

BrainPro: Towards Large-scale Brain State-aware EEG Representation Learning

Authors:

Yi Ding↗Muyun Jiang↗Weibang Jiang↗Shuailei Zhang↗Xinliang Zhou↗Chenyu Liu↗Shanglin Li↗Yong Li↗Cuntai Guan↗

arXiv:2509.22050v2 Announce Type: replace Abstract: Electroencephalography (EEG) reflects underlying brain states, whose activities are distributed across brain regions and manifest as spatial patterns on the scalp. Learning these spatially structured, state-related patterns requires consistent spatial representations across datasets. However, existing EEG foundation models are typically based on self-attention, which does not preserve location-specific information and struggles to align signals recorded with different channel configurations. Moreover, brain states contain both shared and state-specific regional activity, suggesting that learning neurophysiologically plausible, state-aware representations can complement the shared representations targeted by current models and improve downstream decoding. To address these limitations, we propose BrainPro, a large EEG model that combines a retrieval-based spatial learning mechanism for cross-layout spatial alignment with a brain state-decoupling module that learns both shared and state-specific representations through parallel encoders and region-aware reconstruction. Pre-trained on a large EEG corpus, BrainPro achieves state-of-the-art performance across nine public BCI datasets spanning emotion, motor, speech, stress, mental disease, and attention tasks. Analyses of spatial filters, channel-drop robustness, and encoder contributions further validate the effectiveness of its spatial alignment and state-aware pathways. These results show that BrainPro achieves improved interpretability of learned spatial patterns and produces representations that benefit diverse EEG decoding tasks.

Read & Discuss → View Source →

21.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2606.18609

Hallucination Detection and Correction in Medical VLMs via Counter-Evidence Verification

Authors:

Nan Zhou↗Ke Zou↗Meng Liu↗Linchao He↗Jiaqi Zhu↗Yi Zhang↗Hu Chen↗Huazhu Fu↗

Vision-Language models (VLMs) reliability in medical diagnosis is challenged by trust-undermining hallucinations. Existing hallucination detection approaches mainly focus on identifying factual inconsistencies between generated text and reference data. While some studies analyze where models attend in images, they seldom verify whether such attention truly reflects the visual evidence supporting the generated text. To address this gap, we propose Co}unter-Evidence Verification (CoEV), a training-free plug-and-play framework that detects and corrects hallucinations through evidence-based factual consistency verification. CoEV performs bidirectional verification between textual assertions and visual evidence, testing whether each statement is supported by its corresponding evidence region, and assigns each statement into a four-quadrant diagnostic map capturing combinations of text factuality and visual grounding. CoEV detects hallucinated content and serves as a post hoc refinement tool, correcting hallucinations without retraining. Extensive experiments on four medical datasets show that CoEV combats hallucinations in VLMs.For hallucination detection, CoEV consistently outperforms existing methods, improving average PR-AUC and ROC-AUC by 3.0% and 3.9% absolute points respectively, with notable gains of up to 18.5% in specific VQA scenarios. For hallucination correction, it improves Micro-F1 by up to 12.5%, reduces hallucination rates by over 11.9% on medical report generation, and also boosts medical VQA accuracy. These results show that CoEV enables reliable detection and correction of hallucinations, providing clinicians with dependable, evidence-based cues for diagnosis. Code will be released upon acceptance.

Read & Discuss → View Source →

22.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.16801

The Art of Mixology: Mixup-based Obfuscation for Privacy-Preserving Split Learning in Large Language Models

Authors:

Chen Chen↗Xiang Gao↗Xianshun Wang↗Chengran Li↗Shengyu Xia↗Xueluan Gong↗Linru Zhang↗Qian Wang↗Kwok-Yan Lam↗

Split learning provides a practical paradigm for resource-constrained users to train Large Language Models (LLMs) by offloading computation-intensive layers to a server while keeping raw data local. However, existing privacy-preserving split learning methods still face a difficult trade-off among utility, privacy, efficiency, and stability. Specifically, these methods often suffer from substantial utility degradation, remain vulnerable to advanced data reconstruction attacks, incur prohibitive computational and communication overhead, or exhibit unstable performance across different tasks. In this paper, we propose MIXGUARD, a novel mixup-based privacy-preserving split learning framework for LLMs. MIXGUARD introduces token-level obfuscation, representation-level obfuscation, and adaptive gradient perturbation mechanisms, which operate jointly to preserve useful learning signals while preventing privacy leakage to the server. Technically, MIXGUARD first constructs a lightweight calibration model on a public dataset to refine the approximated target representation, and then applies this model during privacy-preserving fine-tuning on private data. We conduct extensive experiments on four classification tasks and four text generation tasks across multiple LLM families, model sizes, architectures, and fine-tuning strategies. The results show that MIXGUARD preserves model utility comparable to non-split training baselines, consistently achieves stronger privacy protection than existing split learning defense methods against state-of-the-art data reconstruction attacks, and remains robust under adaptive attack settings.

Read & Discuss → View Source →

23.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16465

When Agent Automation Becomes Profitable: Quantifying and Insuring Autonomous AI Risk through Trace-Economic Underwriting

Authors:

Binyan Xu↗Xilin Dai↗Fan Yang↗Kehuan Zhang↗

arXiv:2606.16465v1 Announce Type: new Abstract: AI agents can now take irreversible actions in operational systems, but agent-caused losses are still not clearly assigned, priced, or transferred. Providers often disclaim consequential damages, users are left with uncompensated losses, and default human review limits the efficiency gains of automation. We ask when autonomous AI deployment can become economically acceptable despite failure risk. Our answer is to quantify risk at the customer-task-trace episode level and transfer it through insurance. Automation is acceptable when its expected benefit exceeds the premium, control cost, and remaining risk. This requires a defined role with bounded permissions and comparable traces. We introduce trace-economic underwriting, which maps tool-use traces to customer exposure and claimable loss, then uses this representation for pricing, control, and risk transfer. It uses deterministic economic labels rather than an LLM judge. In our trace-to-loss testbed, trace-economic pricing reduces pricing MAE from $17.7K to $569 and removes regressive cross-subsidy. A 300-trace expert audit accepts 295 labels unchanged. On 1,000 real SWE-smith traces, trace-conditioned controls reduce CVaR95 by 72%. Theorem~1 gives a finite-sample scope condition. We release code, labels, and audit sheets.

Read & Discuss → View Source →

24.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15874

LLM-as-Code Agentic Programming for Agent Harness

Authors:

Junjia Qi↗Zichuan Fu↗Jingtong Gao↗Wenlin Zhang↗Hanyu Yan↗Xian Wu↗Xiangyu Zhao↗

arXiv:2606.15874v1 Announce Type: new Abstract: Every major LLM agent framework gives the LLM the role of orchestrator; the model decides what to do next, when to call tools, and when to stop. We argue that token explosion, control-flow hallucination, and unreliable completion are not implementation bugs but architectural consequences of assigning the deterministic work of looping, branching, and sequencing to a probabilistic system. A better prompt or a stronger model cannot guarantee the reliability of the LLM agent. We therefore propose Agentic Programming, in which the program governs all control flow, and the LLM is itself part of it, an adaptive component we call LLM-as-Code and invoke only where a task calls for reasoning or generation. Within each call the model keeps full flexibility, but it cannot alter the program's execution path. With control in the program, the LLM's context is built from the execution history's call tree and forms a directed acyclic graph (DAG). Each call's context length is then determined by its call depth rather than by accumulation over steps. A case study of computer-use agents shows that the design is practical, not just a theoretical stance, substantially improving the stability of long visual operation sequences.

Read & Discuss → View Source →

25.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.15129

EyeMVP: OCT-Informed Fundus Representation Learning via Paired CFP–OCT Pretraining

Authors:

Zhuo Deng↗Ruiheng Zhang↗Ziheng Zhang↗Weihao Gao↗Yitong Li↗Qian Wang↗Lei Shao↗Jiaoyue Dong↗Zhixi Zeng↗Lijian Fang↗Haibo Wang↗Xiaobin Lin↗…

Color fundus photography (CFP) is the mainstay for large-scale retinal screening, yet its diagnostic capacity is constrained by the lack of depth-resolved structural information. Optical coherence tomography (OCT) provides cross-sectional retinal anatomy, but is less accessible in population-level screening. Here, we present EyeMVP, a cross-modal retinal foundation model that uses paired CFP–OCT pretraining to learn OCT-informed CFP representations. EyeMVP is pretrained on 674,893 strict same-eye same-day paired CFP–OCT image triples from 112,642 patients across eight hospitals in China. The model uses cross-modal masked reconstruction to enrich CFP representations with OCT-associated supervision, while requiring only CFP images at inference. To accommodate the non-aligned imaging geometry between en-face CFP and cross-sectional OCT, EyeMVP combines source-constrained cross-attention with CFP-derived structural masks. Across 16 downstream tasks, including classification, segmentation, few-shot adaptation, and cross-modal retrieval, EyeMVP outperforms representative retinal foundation models and shows consistent gains on tasks involving macular and optic nerve structure. For CFP-challenging macular diseases, EyeMVP achieves an AUROC of 0.948 for macular edema (vs.~0.852 for EyeCLIP) and 0.825 for myopic macular schisis. In an exploratory reader study, EyeMVP exceeds junior and intermediate ophthalmologist groups but does not reach senior ophthalmologist performance on macular edema, while showing numerically higher balanced accuracy than all reader groups on myopic macular schisis. These results suggest that pixel-level cross-modal reconstruction can enrich CFP representations with OCT-associated supervision, providing a practical route toward stronger CFP-based retinal analysis in screening settings.

Read & Discuss → View Source →