×

Academic Intelligence · Curated Daily

探索全球前沿学术脉络

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

作者: Chen Si ×
换一批
01.
arXiv (quant-ph) 2026-06-12

Trading symmetry for Hilbert-space dimension in Bell-inequality violation

arXiv:2601.02893v3 Announce Type: replace Abstract: In quantum information, asymmetry, i.e., the lack of symmetry, is a resource allowing one to accomplish certain tasks that are otherwise impossible. Similarly, in a Bell test using any given Bell inequality, the maximum violation achievable using quantum strategies respecting or disregarding a certain symmetry can be different. In this work, we focus on the symmetry involved in the exchange of parties and explore when we have to trade this symmetry for a lower-dimensional quantum strategy in achieving the maximal violation of given Bell inequalities. For the family of symmetric Collins-Gisin-Linden-Massar-Popescu inequalities, we provide evidence showing that there is no such trade-off. However, for several other Bell inequalities with a small number of dichotomic measurement settings, we show that symmetric quantum strategies in the minimal Hilbert space dimension can only lead to a suboptimal Bell violation. In other words, there exist symmetric Bell inequalities that can only be maximally violated by asymmetric quantum strategies of minimal dimension. In contrast, one can also find examples of asymmetric Bell inequalities that are maximally violated by symmetric correlations. The implications of these findings on the geometry of the set of quantum correlations and the possibility of performing self-testing therefrom are briefly discussed.

02.
arXiv (CS.CV) 2026-06-17

Looped World Models

Current world models face a fundamental tension: faithful long-horizon simulation demands deep computation, but deeper models are expensive to deploy and prone to compounding errors. We resolve this by introducing Looped World Models (LoopWM), which are the first looped architectures for world modelling. Our method iteratively refines latent environment states through a parameter-shared transformer block. This yield up to 100x parameter efficiency over conventional approaches with adaptive computation that automatically scales depth to match the complexity of each prediction step. Orthogonal to scaling model size and training data, LoopWM establishes iterative latent depth as a new scaling axis for world simulation, which might significantly push the community forward.

03.
arXiv (CS.CL) 2026-06-17

Evaluating Large Language Models Abilities for Addressee, Turn-change, and Next Speaker Prediction in Meetings

We investigate turn-taking in multimodal multi-party conversations using large language models (LLMs). We construct an evaluation framework for three tasks: addressee detection, turn-change prediction, and next speaker prediction. We compare supervised models trained for these tasks, text-based LLMs, multimodal LLMs (MM-LLMs), and human subjects. Experiments on the AMI corpus showed that LLMs outperformed supervised models and humans in next speaker prediction, despite not being trained on the target domain and without access to audio or visual information. An MM-LLM performed better than text-based LLMs on addressee detection and turn-change prediction but remained below human performance, indicating difficulty leveraging raw audio-visual signals. Ablation analyses revealed that conversational context was critical, particularly for next speaker prediction. We observed that human and LLM prediction patterns were similar, and intervals with frequent turn changes were difficult for both.

04.
arXiv (CS.AI) 2026-06-18

How Well Do Large Language Models Capture Human Personality?

arXiv:2606.18263v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to simulate human populations via persona prompting, often under the assumptions that richer persona descriptions improve behavioral fidelity, similarly sized attribute combinations are equally simulatable, and persona definitions generalize across tasks. In this work, we formalize these assumptions and systematically evaluate them across multiple architectures, scales, and simulation settings. We identify a fundamental limitation we term persona manifold collapse, where increasingly expressive persona specifications lead to systematic contraction of representational and behavioral diversity. Across models, increasing persona complexity consistently reduces inter-persona separation in latent space and weakens behavioral differentiation in downstream simulation tasks. These effects persist across multiple analyses as richer personas fail to preserve human subgroup disagreement, performance varies across attribute combinations of similar size, and adding descriptive detail often degrades rather than improves simulation fidelity. Surprisingly, simple Age-Gender personas consistently outperform richly specified Ideal Customer Profiles (ICPs) across industries, achieving substantially higher downstream prediction accuracy. We find that collapse is not uniform across attributes. Certain combinations remain behaviorally stable and preserve stronger alignment with human responses, forming localized regions we term alignment bridges. Together, our results provide empirical and conceptual foundations for understanding the limits of persona-conditioned simulation, highlighting the need for representation-aware persona construction rather than increasing persona expressivity alone.

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

Integrating Reasoning and Generalization in Text-to-SQL via Self-Enhanced Fine-Tuning

arXiv:2606.15598v1 Announce Type: new Abstract: Text-to-SQL aims to translate natural language questions into executable SQL queries over structured databases, enabling non-expert users to access data intuitively. While recent advances in large language models (LLMs) have shown promise in this task, existing LLM-based approaches often struggle to strike a balance between strong reasoning capabilities and robust generalization. To address these limitations, we propose CoTE-SQL to enhance the LLM-based text-to-SQL generation with three key innovations: (i) self-enhanced reasoning traces distilled from LLMs without human annotation, (ii) structured chain-of-thought (CoT) prompting with modular decomposition and examples retrieval, and (iii) error-aware revision based on SQL execution feedback. Extensive experiments on the Spider and Bird benchmarks demonstrate that CoTE-SQL achieves new state-of-the-art performance among methods built on open-source LLMs with comparable model sizes on Bird (53.39% EX / 59.02 VES) and strong results on Spider (79.60% EX / 77.19 VES), with especially significant gains on complex queries. Results highlight the effectiveness of combining self-enhancement, structured reasoning, and execution-time feedback within an LLM-based framework for text-to-SQL design.

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

Beyond Parallel Sampling: Diverse Query Initialization for Agentic Search

arXiv:2606.17209v1 Announce Type: new Abstract: Test-time scaling for agentic search typically increases depth (i.e., more turns and tokens per trajectory) or breadth (i.e., more parallel rollouts). Here we focus on breadth scaling, showing that standard parallel sampling yields diminishing returns, tracing this to query redundancy at the first turn. When models issue similar first queries across rollouts, the threads retrieve overlapping evidence, and subsequent turns are conditioned on this shared retrieval. We address this limitation with DivInit, a training-free intervention at the first turn. Rather than sampling k independent first queries, DivInit draws n candidates from a single call, picks k < n diverse seeds, and runs them as parallel trajectories. Across five open-weight models and eight benchmarks, DivInit consistently improves over standard parallel sampling, with average gains of five to seven points on multi-hop QA at matched compute. Code available at https://github.com/cxcscmu/diverse-query-initialization

07.
arXiv (CS.AI) 2026-06-15

GAGPO: Generalized Advantage Grouped Policy Optimization

arXiv:2605.13217v1 Announce Type: cross Abstract: Reinforcement learning has become a powerful paradigm for post-training large language model agents, yet credit assignment in multi-turn environments remains a challenge. Agents often receive sparse, trajectory-level rewards only at the end of an episode, making it difficult to determine which intermediate actions contributed to success or failure. As a result, propagating delayed outcomes back to individual decision steps without relying on costly auxiliary value models remains an open problem. We propose Generalized Advantage Grouped Policy Optimization (GAGPO), a critic-free reinforcement learning method for precise, step-aligned temporal credit assignment. GAGPO constructs a non-parametric grouped value proxy from sampled rollouts and uses it to compute TD/GAE-style temporal advantages, recursively propagating outcome supervision backward through time. Combined with group-wise advantage normalization and an action-level importance ratio, GAGPO extracts stable, localized optimization signals directly from multi-turn trajectories. Experiments on ALFWorld and WebShop show that GAGPO outperforms strong reinforcement learning baselines. Further analyses demonstrate faster early-stage learning, improved interaction efficiency, and smoother optimization dynamics, suggesting that GAGPO offers a simple yet effective framework for multi-turn agentic reinforcement learning.

08.
arXiv (CS.AI) 2026-06-16

BRIDGE: Biological Evidence Refinement and Heterogeneous Dynamic Gating for Gene Regulatory Networks

arXiv:2606.14734v1 Announce Type: cross Abstract: Motivation: Gene regulatory network inference from single-cell RNA sequencing (scRNA-seq) data is important for uncovering cell-state-specific transcriptional programs. However, scRNA-seq measurements are sparse and noisy, and experimentally validated TF-target interactions remain limited, making reliable inference challenging. Although graph neural networks have advanced GRN prediction, existing methods often rely on biologically unconstrained graph augmentation, such as random edge perturbation, and insufficiently control information transfer between genes and cells. These limitations may distort regulatory structures and weaken robustness under noisy and weakly supervised settings. Results: To address these issues, we propose an innovative framework named Biological Evidence Refinement and Heterogeneous Dynamic Gating for Gene Regulatory Networks (BRIDGE). BRIDGE extracts gene and cell representations from the expression matrix and its matrix dual, and performs contrastive learning in the gene space and cell space between self and neighbors across the co-expression-refined regulatory view and the original graph. It then applies heterogeneous gated encoding to adaptively regulate information transfer between genes and cells, enabling robust transcription factor-to-target gene prediction. Experiments on benchmark datasets spanning three network types and seven cell types show that BRIDGE achieves state-of-the-art AUROC and AUPRC in most settings. In particular, on Specific networks, BRIDGE improves average AUPRC by 5% over the second-best baseline, GCLink. In cross-cell-type few-shot transfer, BRIDGE consistently outperforms GCLink and GENELink across all six target cell types. A case study on hESC further supports the biological relevance of the predictions, with 9 of the top 10 and 46 of the top 100 novel TF-target interactions validated by ChIPBase.

09.
arXiv (CS.LG) 2026-06-11

TacCoRL: Integrating Tactile Feedback into VLA via Simulation

arXiv:2606.11743v1 Announce Type: cross Abstract: Vision-language-action (VLA) models provide strong visual, language, and action priors for robot manipulation, but visual observations alone often miss the local contact state required for contact-rich tasks. We present TacCoRL, a scalable framework that injects Tactile feedback into VLA policies and improves them through sim-real Co-training and simulation-based reinforcement learning (RL), without requiring large-scale tactile pretraining or extensive real-world contact exploration. The key idea is not only adding touch as an input, but learning how contact readings should modulate action responses in near-failure states that are rare in demonstrations and risky to collect on hardware. We use a real-aligned simulator as a closed-loop training environment for contact interaction. Mixed simulated and real trajectories first warm-start tactile-conditioned actions in the pretrained policy. Reinforcement learning with verifiable task rewards then optimizes the policy using simulated contact rollouts. It reinforces tactile-conditioned actions that lead to task completion, while a supervised objective on real trajectories keeps the refined policy anchored to deployment visual, tactile, and action distributions. The resulting policy transfers directly to the real robot without privileged simulation state or online real-world RL. Across four bimanual contact-rich tasks, the final visuo-tactile policy achieves an average success rate of 72.5%, compared to baseline of 50.0%. Result videos and more details are available at https://tac-corl.github.io/

10.
arXiv (CS.AI) 2026-06-16

FORTIS: Benchmarking Over-Privilege in Agent Skills

arXiv:2605.09163v3 Announce Type: replace Abstract: Large language model agents increasingly operate through an intermediate skill layer that mediates between user intent and concrete task execution. This layer is widely treated as an organizational abstraction, but we argue it is also a privilege boundary that current models routinely exceed. We present FORTIS, a benchmark that evaluates over-privilege in agent skills across two stages: whether a model selects the minimally sufficient skill from a large overlapping library, and whether it executes that skill without expanding into broader tools or actions than the skill permits. Across ten frontier models and three domains, we find that over-privileged behavior is the norm rather than the exception. Models consistently reach for higher-privilege skills and tools than the task requires, failing at both stages at rates that remain high even for the strongest available models. Failure is especially severe under the ordinary conditions of real user interaction: incomplete specification, convenience framing, and proximity to skill boundaries. None of these requires adversarial construction. The results indicate that the skill layer, far from containing agent behavior, is itself a primary source of privilege escalation in current systems.

11.
arXiv (CS.AI) 2026-06-12

AgentBeats: Agentifying Agent Assessment for Openness, Standardization, and Reproducibility

arXiv:2606.13608v1 Announce Type: new Abstract: Agent systems are advancing quickly across domains, but their evaluation remains fragmented. Most benchmarks rely on fixed, LLM-centric harnesses that require heavy integration, create test-production mismatch, and limit fair comparison across diverse agent designs. The root problem is the lack of an open, agent-agnostic assessment interface. We advocate Agentified Agent Assessment (AAA), where evaluation is performed by judge agents and all participants interact through standardized protocols: A2A for task management and MCP for tool access. Conventional benchmarking defines two separate interfaces, one for the benchmark and one for the agent, while AAA only needs one; this yields a generic, unified framework that separates assessment logic from agent implementation and enables reproducible, interoperable, and multi-agent evaluation. We further introduce AgentBeats as a concrete realization of AAA: we identify five practical operation modes that make standardized assessment compatible with real-world constraints on openness, privacy, and reproducibility. To evaluate our design at scale, we conduct two studies: a five-month open competition that drew 298 judge agents across 12 categories together with 467 subject agents from independent participants, showing that AAA applies across a heterogeneous range of benchmarks; and a case study on coding agents that confirms agentified evaluation preserves fidelity with the public record while surfacing previously missing head-to-head results, yielding research insights about agent design. Combining a community-scale field study and a controlled coding case study, we verify that AAA delivers coverage, practicality, and fidelity across heterogeneous scenarios at scale. Together, AAA and AgentBeats offer a clear path toward open, standardized, and reproducible agent assessment.

12.
medRxiv (Medicine) 2026-06-16

Optimal Clinical Trials Platform for Progressive Multiple Sclerosis (OCTOPUS): protocol for an international, multi-arm, multi-stage, platform, randomized controlled, double-blind, phase 3 clinical trial.

Introduction Current treatments for multiple sclerosis (MS) do not address the pathological processes of neurodegeneration and chronic demyelination. This, coupled with the significant challenges of translating promising phase 2 results to phase 3 trial success, highlights the need for more efficient trial designs, such as platform multi-arm multi-stage (MAMS) trial approaches. MAMS trials have demonstrated success in areas such as oncology and infectious diseases. They are typified by a statistically robust core trial design that allows the addition of further treatment arms and utilisation of interim outcome analyses at pre-defined timepoints, to determine whether to terminate a treatment arm early or proceed to the final outcome analysis. To address the challenges in progressive multiple sclerosis (PMS) treatment discovery, the Optimal Clinical Trials Platform for PMS (OCTOPUS) trial was developed. It currently utilises MRI whole-brain atrophy as its interim outcome measure and the clinically relevant composite Expanded Disability Status Scale Plus (EDSS-Plus) as its final outcome measure. A rigorous and systematic drug selection process that assessed preclinical in vitro and animal model evidence, along with additional human data, led to the prioritisation of R/S-alpha lipoic acid (R/S-ALA) and metformin for testing against placebo, targeting pathobiological mechanisms relevant to PMS. All participants will be eligible to receive the current standard of care, including disease-modifying treatments (DMTs). Method and analysis OCTOPUS will be a multi-centre, randomised, placebo-controlled, double-blind, phase 3, MAMS trial of participants aged 25 to 70 years (inclusive) with PMS and an EDSS score of 4.0 to 8.0 (inclusive). Steady progression must be the major cause of increasing disability rather than relapse in the preceding 2 years. In the trial s first candidate drug cycle, participants will be allocated to R/S-ALA, metformin, or placebo in a 1:1:1 ratio. Cycle 1 active treatments will start as R/S-ALA 600 mg once daily, increased after 4 weeks to 600 mg twice daily, or metformin 1 g once daily, increased after 4 weeks to 1 g twice daily. The trial will be multinational, with participation from 28 hospitals across the UK and 10 hospitals in Australia. Clinician-reported measures will include: the EDSS-Plus and the individual components: EDSS, Timed 25 Foot Walk (T25FW); 9 Hole Peg Test (9HPT); Symbol Digit Modalities Test (SDMT); Sloan Low Contrast Visual Acuity (SLCVA); and Relapse assessment. Patient-reported outcomes include MS specific walking, fatigue, pain, and impact scales. We will include a health economic analysis. Analysis stage 1 will require randomisation of 125 participants per arm and utilise MRI percentage brain volume change (PBVC) with the Structural Image Evaluation using Normalisation of Atrophy (SIENA) technique from baseline to 78 weeks. A positive outcome in analysis stage 1 will detect a 0.15% per year whole brain atrophy difference with a one-sided alpha of 0.35 and power of 95%, ensuring a low probability of erroneously rejecting a treatment arm at this stage. Any arms that show a positive effect will proceed to final analysis stage 2. Analysis stage 2 will require 600 participants per arm. Participants included in stage 1 will also be included in the stage 2. Analysis stage 2 will evaluate time to 6-month confirmed disability progression in the EDSS-Plus, in order to detect a 25% hazard ratio reduction with 90% power and an alpha of 0.05. Assuming one treatment arm proceeds to analysis stage 2, the trial will recruit approximately 1,200 participants and last about 6 years. This is approximately two-thirds the size and half the duration of separately conducted two-arm phase 2 and 3 trials. Ethics and dissemination The protocol was approved by the London Hampstead REC (22/LO/0622). This manuscript is based on protocol version 8.0, 28th August 2025. The findings of this trial will be disseminated through peer-reviewed publications and conference presentations. There will be a close communication strategy developed with the UK MS Society (MSS) and full patient and public involvement and engagement (PPIE). Trial registration ISRCTN: 14048364 EudraCT number: 2021-003034-37 CTA 20363/0445 IRAS number: 1003943 Secondary identifying numbers: ND001, CPMS 54274 Strengths and limitations - The OCTOPUS trial will be the first platform multi-arm multi-stage phase 3 trial in PMS, offering the potential to significantly expedite clinical trial processes with advantages in cost- and time-efficiency, focusing specifically on the poorly treated pathobiological processes of chronic neurodegeneration and demyelination - It will begin by assessing two promising drug candidates, immediate-release metformin and R/S-ALA, and will expand over the duration of the trial to include more drug arms under the same trial master protocol - The flexible and statistically robust trial design means that several components of the design (such as the early analysis stage 1 interim outcome) can be updated in line with evolving scientific knowledge - It will ultimately be the largest ever investigator-initiated phase 3 trial in PMS - It will include a range of national and international trial sites, including neuroscience centres and district general hospitals - It will have a high inclusion limit for age (up to 70 years) and disability (up to EDSS 8.0) - Several components (the telephone EDSS and virtual patient-reported outcome measures) will be amenable to remote collection increasing inclusivity and thus addressing public and participant suggestions, while minimising the risk of missing data - The main challenges in this trial design are the statistical and methodological complexity involved in design and implementation, and interpretation of interim trial results. Conclusion The trial launched cycle 1 in January 2023. Analysis stage 1 recruitment of 375 participants was achieved in November 2024, enabling planned interim analysis stage 1 to be conducted by late 2026 (Figure 1). On the 1st of June 2026, in the UK, 24 sites are active with a further 4 in set-up as part of stage 2, and in the Australian extension, Platform Adaptive Trial for Remyelination and Neuroprotection in Multiple Sclerosis (PLATYPUS), 1 site is active, with 9 additional sites in set-up.

13.
arXiv (CS.CV) 2026-06-19

MMD-SLAM: Structure-Enhanced Multi-Meta Gaussian Distribution-Guided Visual SLAM

3D Gaussian Splatting (3DGS) has significantly boosted novel view synthesis and high-fidelity scene reconstruction, expanding the potential of 3DGS-based Visual Simultaneous Localization and Mapping (SLAM) methods. However, most existing systems fail to fully exploit the underlying structural information, which limits rendering quality and often leads to inconsistent maps. To address these limitations, we propose MMD-SLAM, a structure-enhanced Visual SLAM framework that leverages the Atlanta World (AW) assumption to guide a Multi-Meta Gaussian representation for photorealistic mapping. First, we introduce a point-line fusion strategy for pose optimization, where 3D line segments are incorporated to improve tracking robustness and provide additional constraints for mapping. Second, we design a Multi-Meta Gaussian representation with dominant directions, explicitly encoding structural priors from the AW hypothesis. Finally, we propose a Gaussian evolution strategy that adapts to scene geometry and incorporates structural cues into global optimization. Extensive experiments demonstrate that these innovations enable MMD-SLAM to achieve state-of-the-art performance in both tracking accuracy and mapping quality. e.g., our method achieves a 48.56% reduction in ATE RMSE on ScanNet and a 5.71% improvement in PSNR on Replica, compared with MonoGS.

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

Text-Vision Co-Instructed Image Editing

Existing image editing methods can be generally categorized into textual instruction-based and visual prompt-based ones. Textual instructions are semantically expressive, but are limited by the coarse granularity of spatial control of the editing results. In contrast, visual prompts such as drag and point can provide precise spatial guidance, but are limited by the inherent ambiguity in semantic intent. To unify the strength of textual and visual prompts, we present Text-Vision Co-Instructed Image Editing, which jointly models textual instructions as semantic intent and sparse visual instructions as spatial guidance, aiming to achieve precise and intent-faithful image manipulation. To this end, we first construct a textual-visual instruction paired dataset with more than 23K samples derived from dynamic videos, enabling aligned supervision for cross-modal instruction. We then propose TV-Edit, a Textual-Visual instruction unified Editing framework to contextualize drag or point-based visual instructions with image-text semantics and lift them into semantic-aware control representations for pretrained editing backbones. By integrating semantic intent and spatial constraints, TV-Edit leads to more precise spatial control, less instruction ambiguity, and stronger structural consistency than text-only or drag-based alternatives. Finally, we establish TV-Edit-Bench, a deliberately designed benchmark to evaluate semantic faithfulness, spatial alignment, and visual consistency with ground-truth references and controlled textual-visual variations for reliable assessment. Our experiments across multiple editing backbones demonstrate that TV-Edit consistently yields more precise and intent-faithful edits, significantly outperforming state-of-the-art instruction-based and drag-based baselines.

15.
arXiv (CS.AI) 2026-06-17

Visored: A Controlled-Natural-Language Prover for LLM-Generated Mathematics

arXiv:2606.17581v1 Announce Type: cross Abstract: We present a dependent-type-based prover designed around the way LLMs (and humans) tend to write mathematics, complementing existing systems such as Lean and Rocq. Its core design choices are a surface that imitates mathematical natural language and a rule-driven automation layer that closes the routine steps a textbook would omit, so that an accepted proof can be re-emitted as a checked Lean file. Early experiments suggest that, even without any prover-specific training data, LLMs can learn to use it effectively on the miniF2F benchmark. Lean output excerpts: https://github.com/xiyuzhai-husky-lang/visored/

16.
medRxiv (Medicine) 2026-06-18

Evaluating Deep-Learning Based Quantification of Breast Arterial Calcification on Mammography for Cardiovascular Risk Assessment

Purpose: To develop and evaluate a deep learning model for automated quantification of breast arterial calcification (BAC) on screening mammography and to assess whether AI-derived BAC burden predicts major adverse cardiovascular events (MACE) in women. Methods: In this retrospective study, 202,006 women who underwent screening mammography without history of MACE were included. A BAC segmentation model was trained on an expert-annotated dataset using a multi-task U-Net with a ResNet-18 encoder to detect and segment BAC. BAC burden was quantified as area (mm{superscript 2}) from model-generated masks using DICOM pixel spacing and categorized by tertiles into low, intermediate, and high. The PREVENT score and incident MACE were identified from electronic health records. Cox proportional hazards models were developed to evaluate AI-derived BAC burden and PREVENT score alone, and combined models for 5 - and 10-year cardiovascular risk prediction. Results: Among 202,006 women (mean age 54.8{+/-}11.7 years), 23.1% had AI-detected BAC, and 7,701 (3.8%) developed incident MACE during a median follow - up of 7.5 years. On the geographically held-out test set, the BAC model achieved an AUROC of 0.97, Dice score of 0.6678, and Pearson correlation of 0.961 between AI-derived and manually annotated BAC burden. BAC burden increased with age and was higher among women who developed MACE. Five - year MACE incidence increased across BAC categories from 1.5% in women without BAC to 6.9% in those with high BAC burden. BAC burden alone showed modest prediction of MACE, with 5-year and 10-year AUROCs of 0.661 and 0.650, respectively, while PREVENT achieved AUROCs of 0.781 and 0.771. Adding BAC to PREVENT produced minimal improvement in discrimination. Conclusion: Deep learning-based BAC quantification from routine mammography is feasible, accurate, and associated with future cardiovascular risk. Although BAC added little to PREVENT for overall discrimination, it may serve as a scalable opportunistic imaging biomarker to identify women at elevated cardiovascular risk and support preventive care.

17.
arXiv (CS.CL) 2026-06-15

MASLab: A Unified and Comprehensive Codebase for LLM-based Multi-Agent Systems

LLM-based multi-agent systems (MAS) have demonstrated significant potential in enhancing single LLMs to address complex and diverse tasks in practical applications. Despite considerable advancements, the field lacks a unified codebase that consolidates existing methods, resulting in redundant re-implementation efforts, unfair comparisons, and high entry barriers for researchers. To address these challenges, we introduce MASLab, a unified, comprehensive, and research-friendly codebase for LLM-based MAS. (1) MASLab integrates over 20 established methods across multiple domains, each rigorously validated by comparing step-by-step outputs with its official implementation. (2) MASLab provides a unified environment with various benchmarks for fair comparisons among methods, ensuring consistent inputs and standardized evaluation protocols. (3) MASLab implements methods within a shared streamlined structure, lowering the barriers for understanding and extension. Building on MASLab, we conduct extensive experiments covering 10+ benchmarks and 8 models, offering researchers a clear and comprehensive view of the current landscape of MAS methods. MASLab will continue to evolve, tracking the latest developments in the field, and invite contributions from the broader open-source community.

18.
arXiv (CS.AI) 2026-06-16

TS-Memory: Plug-and-Play Memory for Time Series Foundation Models

arXiv:2602.11550v2 Announce Type: replace-cross Abstract: Time Series Foundation Models (TSFMs) achieve strong zero-shot forecasting through large-scale pre-training, but adapting them to downstream domains under distribution shift remains challenging. Existing solutions face a trade-off: Parametric Adaptation can cause catastrophic forgetting and requires costly multi-domain maintenance, while Non-Parametric Retrieval improves forecasts but incurs high inference latency due to datastore search. We propose Parametric Memory Distillation and implement it as TS-Memory, a lightweight memory adapter that augments frozen TSFMs. TS-Memory is trained in two stages. First, we construct an offline, retrieval-leakage-safe kNN teacher that synthesizes confidence-aware quantile targets from retrieved futures. Second, we distill this retrieval-induced distributional correction into a lightweight memory adapter via confidence-gated supervision. During inference, TS-Memory fuses memory and backbone predictions with constant-time overhead, enabling retrieval-free deployment. Experiments across diverse TSFMs and benchmarks demonstrate consistent improvements in both point and probabilistic forecasting over representative adaptation methods, with efficiency comparable to the frozen backbone. Code: https://github.com/sisuolv/TS-Memory.

19.
arXiv (CS.AI) 2026-06-17

First, do NOHARM: towards clinically safe large language models

arXiv:2512.01241v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are routinely used by physicians and patients for medical advice, yet their clinical safety profiles remain poorly characterized. We present NOHARM (Numerous Options Harm Assessment for Risk in Medicine), a 1,100-task benchmark of primary care-to-specialist consultation cases to measure the frequency and severity of harm from LLM-generated medical recommendations. NOHARM covers 10 specialties, with 12,747 expert annotations for 4,249 clinical management options. Across 28 LLMs, recommendations carried the potential for severe harm in up to 22.6% of cases, with errors of omission accounting for more than 80% of severe errors. In a randomized trial of 101 generalist physicians, human benchmark performance significantly improved with AI assistance, yet physicians remained far from realizing the potential of AI tools, frequently ignoring essential advice surfaced by AI. Safety performance tracked general-intelligence and medical-knowledge benchmarks across the full range of models but decoupled at the frontier. Despite strong performance on existing evaluations, widely used AI models can produce medical advice with the potential for severe harm at non-trivial rates, highlighting the importance of explicit measurement of clinical safety.

20.
arXiv (CS.CV) 2026-06-17

Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization

Group Relative Policy Optimization has emerged as essential for aligning video diffusion models with human preferences, but faces a critical computational bottleneck: training a 14B parametered model typically demands hundreds of GPU days per experiment. Existing efficiency methods reduce costs through sliding window subsampling training timesteps, but fundamentally compromise optimization, exhibiting severe instability and failing to reach full trajectory performance. We present Flash-GRPO, a single-step training framework that outperforms full trajectory training in alignment quality under low computational budgets while substantially improving training efficiency. Flash-GRPO addresses two critical challenges: iso-temporal grouping eliminates timestep-confounded variance by enforcing prompt-wise temporal consistency, decoupling policy performance from timestep difficulty; temporal gradient rectification neutralizes the time-dependent scaling factor that causes vastly inconsistent gradient magnitudes across timesteps. Experiments on 1.3B to 14B parameter models validate Flash-GRPO's effectiveness, demonstrating substantial training acceleration with consistent stability and state-of-the-art alignment quality.

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

CEO-Bench: Can Agents Play the Long Game?

Language model agents are becoming proficient executors at isolated, short-horizon tasks such as software engineering and customer service. Yet real-world challenges require a combination of sophisticated skills that remain largely untested in agents: (1) navigating long horizons amid uncertainty; (2) acquiring information in noisy environments; (3) adapting to a changing world; (4) orchestrating multiple moving parts toward a coherent goal. We introduce CEO-Bench, which evaluates these capabilities together by simulating a representative real-world task: operating a startup for 500 days. An agent manages pricing, marketing, budgeting, and many other aspects of a fictional company through a programmable Python interface, operating in the same environment and facing the same challenges as a human CEO. Success demands analyzing noisy, interconnected business databases, translating signals into sound strategy, and coordinating many decisions with programming. The strongest agents write sophisticated code that simulates customer cohorts to forecast future cash and mines negotiation history to uncover hidden customer preferences. Even so, most state-of-the-art models struggle in this environment. Only Claude Opus 4.8 and GPT-5.5 finish above the $1M starting balance, and neither consistently turns a profit. CEO-Bench takes a first step toward measuring the intelligence required to drive sustained, adaptive progress over time.

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

How fast can you find a good hypothesis?

arXiv:2509.03734v3 Announce Type: replace-cross Abstract: In the hypothesis selection problem, we are given sample and query access to finite set of candidate distributions (hypotheses), $\mathcal{H} = \{H_1, \ldots, H_n\}$, and samples from an unknown distribution $P$, both over a domain $\mathcal{X}$. The goal is to output a distribution $Q$ whose distance to $P$ is comparable to that of the nearest hypothesis in $\mathcal{H}$. Specifically, if the minimum distance is $\mathsf{OPT}$, we aim to output $Q$ such that, with probability at least $1-\delta$, its total variation distance to $P$ is at most $C \cdot \mathsf{OPT} + \varepsilon$. The optimal approximation for proper algorithms (where $Q \in \mathcal{H}$) is $C=3$ using $\Theta(\log(n/\delta)/\varepsilon^2)$ samples from $P$ and for improper algorithms (where $Q$ is not necessarily in $\mathcal{H}$) is $C=2$ using $\tilde{\Theta}(\log(n/\delta)/\varepsilon^2)$ samples from $P$. In the improper setting, the algorithm achieving $C=2$ [Bousquet, Braverman, Kol, Efremenko, Moran, FOCS 2021] runs in time which grows polynomially with $|\mathcal{X}|$ – it does not run in finite time for real-valued distributions. A promising path towards improved runtime is to consider improper algorithms which output a mixture $Q$ of the hypotheses as such a distribution can be represented in $n$ words of memory. We show (1) a lower bound that no algorithm which outputs a mixture can achieve approximation better than $C = 3-2/n$ unless the number of samples is polynomial in $|\mathcal{X}|$, as well as (2) an algorithm which runs in time $poly(n)$ and achieves the same approximation guarantee. In the proper setting, [Aliakbarpour, Bun, Smith, NeurIPS 2024] provided an algorithm with $C=3$ running in $\tilde{O}(n/(\delta^3\varepsilon^3))$ time. We improve this time complexity to $\tilde{O}(n/(\delta \varepsilon^2))$, significantly reducing the dependence on the confidence and error parameters.

23.
arXiv (CS.CV) 2026-06-11

Seeing What Matters: Perceptual Wrapper with Common Randomness for 3D Gaussian Splatting

While 3D Gaussian Splatting (3DGS) achieves impressive real-time rendering, it frequently struggles to synthesize high-frequency textures, a limitation heavily exacerbated in memory-constrained and rate-distortion-optimized (RDO) pipelines. To address this, we propose a versatile 2D perceptual wrapper that enhances the rendered outputs of existing 3DGS representations in a content- and view-dependent manner. Our method leverages a lightweight synthesis network conditioned on pseudo-random Gaussian noise to synthesize perceptually plausible textures. Supervised by Wasserstein Distortion, the network learns to match local feature statistics rather than strictly enforcing pixel-wise reconstruction fidelity, effectively mitigating the blurriness inherent in standard frameworks. We demonstrate the broad applicability of our plug-and-play approach across vanilla, memory-constrained, and RDO 3DGS methods. Comprehensive subjective and objective experiments confirm that our method significantly improves over existing baselines, yielding superior perceptual quality at sharply reduced file or model sizes.

24.
arXiv (CS.AI) 2026-06-15

Elastic Queries Reinforcement Learning: Self-Aware Policy Execution for VLA Models

arXiv:2606.14375v1 Announce Type: cross Abstract: Vision-language-action (VLA) models are powerful action generators for robot manipulation, but they are typically executed with fixed inference and replanning schedules. This rigidity ignores the uneven difficulty of robot control: contact-rich or uncertain states may need more computation and fresher feedback, while easier states can often be handled with fewer inference steps and longer open-loop execution. We propose Elastic Queries Reinforcement Learning (EQRL), a framework that makes each VLA policy query elastic. A lightweight latent-schedule adaptor jointly selects the latent input, denoising budget, and action chunk length, without fine-tuning the underlying VLA model. To make scheduling difficulty-aware, EQRL trains a critic over the joint latent-schedule action and derives a state difficulty signal from critic ensemble disagreement. This signal guides compute toward difficult states, while a learned residual allows task-driven correction. We formulate variable chunk execution as query-level macro-action RL with chunk-dependent discounting and an amortized number-of-function-evaluations (NFE) budget. Across simulation and real-robot manipulation, EQRL reduces amortized inference cost while preserving or improving task success.

25.
arXiv (CS.CL) 2026-06-16

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 trillion text tokens, then extended the context length to 1M tokens, and post-trained using Supervised Fine Tuning (SFT), Reinforcement Learning (RL), and Multi-teacher On-Policy Distillation (MOPD). Nemotron 3 Ultra is our most capable model yet, employing multiple key technologies - LatentMoE, Multi Token Prediction (MTP), NVFP4 pre-training, multi-environment RLVR, MOPD, and reasoning budget control. Nemotron 3 Ultra achieves up to ~6x higher inference throughput as compared to state-of-the-art publicly available LLMs while attaining on-par accuracy. The state-of-the-art accuracy, high inference throughput, and 1M token context length make Nemotron 3 Ultra ideal for long-running autonomous agentic tasks. We open-source the base, post-trained, and quantized checkpoints, along with the training data and recipe on HuggingFace.