×

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: Xiang Song ×
换一批
01.
arXiv (quant-ph) 2026-06-12

Asymmetric quantum steering harvested near a Lorentz-violating BTZ black hole

arXiv:2606.12766v1 Announce Type: cross Abstract: We investigate the harvesting of quantum steering and its directional asymmetry between two Unruh-DeWitt detectors in a Lorentz-violating BTZ black hole spacetime. Since the detectors are located at different radial positions outside the black hole, they experience inequivalent local environments induced by gravitational redshift, causing Alice to undergo stronger effective thermal noise than Bob. Remarkably, we uncover a counterintuitive phenomenon in which the detector subjected to a higher effective temperature exhibits stronger steerability than the other one, revealing a nontrivial inversion of thermal intuition in curved spacetime. Furthermore, quantum steering survives only within a finite window of detector energy gaps and reaches its maximum within an optimal regime. We find that Lorentz violation suppresses steering most strongly near this optimal energy gap, indicating an enhanced sensitivity of maximal correlation extraction to symmetry breaking effects. Our results demonstrate that Lorentz violation acts as a geometric constraint on the quantum information capacity of spacetime, simultaneously restricting both the strength and the directionality of quantum correlations.

02.
arXiv (CS.CL) 2026-06-16

Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale

Efficient and scalable agentic intelligence requires models that can deliver both low-latency responses and strong reasoning capabilities while remaining practical to train, serve, and deploy. In this report, we present Ling-2.6 and Ring-2.6, a family of models designed to address this challenge at scale. Ling-2.6 is optimized for instant response generation and high capability per output token, whereas Ring-2.6 is tailored for deeper reasoning and more advanced agentic workflows. Instead of training from scratch, we upgrade the Ling-2.0 base model through architectural migration pre-training and large-scale post-training. This upgrade is guided by a unified co-design of model architecture, optimization objectives, serving systems, and agent training environments, enabling improvements in both model capability and deployment efficiency. At the architectural level, we introduce a hybrid linear attention design that integrates Lightning Attention with MLA, improving the efficiency of long-context training and decoding. To further enhance token efficiency, we optimize capability per output token through Evolutionary Chain-of-Thought, Linguistic Unit Policy Optimization, bidirectional preference alignment, and shortest-correct-response distillation. For agentic capabilities, we propose KPop, a reinforcement learning framework designed to support stable training of Ring-2.6-1T on large-scale environment-grounded data. KPop improves training efficiency through asynchronous scheduling across coding, search, tool use, and workflow execution, enabling scalable learning from complex agent-environment interactions. Together, Ling-2.6 and Ring-2.6 provide a practical pathway toward efficient, scalable, and open agentic systems. We open-source all checkpoints in the 2.6 family to support further research and development in practical agentic intelligence.

03.
arXiv (CS.CL) 2026-06-16

MosaicQuant: Inlier-Outlier Disaggregation for Unified 4-Bit LLM Quantization

4-bit quantization significantly reduces the memory footprint and accelerates the inference of large language models (LLMs). However, its limited bit-width representation struggles to faithfully capture both dense common values (inliers) and rare large-magnitude values (outliers), causing substantial accuracy degradation. Existing mixed-precision methods mitigate this by retaining outliers in high precision, but at the cost of breaking the uniformity of low-bit execution, introducing precision conversion and extra data movement that undermine practical speedup. We propose MosaicQuant, a unified 4-bit LLM quantization paradigm built on a novel principle of inlier–outlier disaggregation. Rather than elevating outlier precision, MosaicQuant quantizes the full weight matrix into a dense 4-bit base component, where inliers are captured faithfully while outlier are inevitably quantized. A sparse 4-bit residual component is then introduced to compensate for these quantization errors, selectively targeting the most error-critical weight blocks where output distortion is shown to be concentrated. However, a unified representation alone is insufficient, as naïvely executing the sparse residual as a separate kernel still breaks the unified low-bit inference pipeline. To bridge this gap, we introduce ZipperEngine, which fuses sparse block computation into the dense 4-bit GEMM kernel via an overlapped pipeline, unifying not only the representation but also the execution into a single coherent low-bit inference pipeline. Extensive experiments on LLaMA3 and Qwen3 demonstrate that MosaicQuant preserves near-FP16 accuracy while achieving up to $1.24\times$ speedup over the W16A16 baseline.

04.
arXiv (CS.CV) 2026-06-12

Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning

Multimodal agents, which integrate a controller e.g., a vision language model) with external tools, have demonstrated remarkable capabilities in tackling complex multimodal tasks. Existing approaches for training these agents, both supervised fine-tuning and reinforcement learning, depend on extensive human-annotated task-answer pairs and tool trajectories. However, for complex multimodal tasks, such annotations are prohibitively expensive or impractical to obtain. In this paper, we propose an iterative tool usage exploration method for multimodal agents without any pre-collected data, namely SPORT, via step-wise preference optimization to refine the trajectories of tool usage. Our method enables multimodal agents to autonomously discover effective tool usage strategies through self-exploration and optimization, eliminating the bottleneck of human annotation. SPORT has four iterative components: task synthesis, step sampling, step verification, and preference tuning. We first synthesize multimodal tasks using language models. Then, we introduce a novel trajectory exploration scheme, where step sampling and step verification are executed alternately to solve synthesized tasks. In step sampling, the agent tries different tools and obtains corresponding results. In step verification, we employ a verifier to provide AI feedback to construct step-wise preference data. The data is subsequently used to update the controller for tool usage through preference tuning, producing a SPORT agent. By interacting with real environments, the SPORT agent gradually evolves into a more refined and capable system. Evaluation in the GTA and GAIA benchmarks shows that the SPORT agent achieves 6.41% and 3.64% improvements, underscoring the generalization and effectiveness introduced by our method. The project page is https://SPORT-Agents.github.io.

05.
arXiv (CS.CL) 2026-06-19

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models – DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated) – both supporting a context length of one million tokens. DeepSeek-V4 series incorporate several key upgrades in architecture and optimization: (1) a hybrid attention architecture that combines Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA) to improve long-context efficiency; (2) Manifold-Constrained Hyper-Connections (mHC) that enhance conventional residual connections; (3) and the Muon optimizer for faster convergence and greater training stability. We pre-train both models on more than 32T diverse and high-quality tokens, followed by a comprehensive post-training pipeline that unlocks and further enhances their capabilities. DeepSeek-V4-Pro-Max, the maximum reasoning effort mode of DeepSeek-V4-Pro, redefines the state-of-the-art for open models, outperforming its predecessors in core tasks. Meanwhile, DeepSeek-V4 series are highly efficient in long-context scenarios. In the one-million-token context setting, DeepSeek-V4-Pro requires only 27% of single-token inference FLOPs and 10% of KV cache compared with DeepSeek-V3.2. This enables us to routinely support one-million-token contexts, thereby making long-horizon tasks and further test-time scaling more feasible. The model checkpoints are available at https://huggingface.co/collections/deepseek-ai/deepseek-v4.

06.
arXiv (CS.CL) 2026-06-11

ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research

AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify. We present ResearchClawBench, a benchmark for evaluating autonomous scientific research across 40 tasks from 10 scientific domains. Each task is grounded in a real published paper, provides related literature and raw data, and hides the target paper during evaluation. Expert-curated multimodal rubrics decompose the target scientific artifacts into weighted criteria, enabling evaluation of target-paper-level re-discovery while leaving room for new discovery. We evaluate seven autonomous research (auto-research) agents under a unified protocol and seventeen native LLMs through the lightweight ResearchHarness. Current systems remain far from reliable re-discovery: the strongest autonomous agent, Claude Code, averages 21.5, and the strongest ResearchHarness LLM, Claude-Opus-4.7, averages 20.7, with an LLM frontier mean of only 26.5. Error analysis shows that failures concentrate in experimental protocol mismatch, evidence mismatch, and missing scientific core. ResearchClawBench provides a reproducible evaluation frontier for measuring progress toward autonomous scientific research.

07.
bioRxiv (Bioinfo) 2026-06-13

PertDiffBench: Benchmarking Diffusion Models for Single-Cell Perturbation Response Prediction

Diffusion models are increasingly used to predict transcriptional responses to perturbations, but whether they improve on simpler generative and representation-based baselines remains unclear. Existing evaluations often do not separate the effects of model architecture, input representation, biological context and metric choice, making it difficult to determine where diffusion-based methods are useful. Here we introduce PertDiffBench, a standardized benchmark for diffusion-based transcriptomic perturbation prediction across single-cell and bulk RNA-seq datasets. PertDiffBench evaluates diffusion-based models across three complementary evaluation settings: standard prediction in known single-cell contexts and bulk perturbation conditions, generalization to unseen cell types, species, drugs and intermediate time points, and stress tests of feature dimensionality, input representation, noise type and gene ordering. Across these settings, diffusion models did not show a consistent advantage. scGen remained a strong baseline in common prediction tasks, whereas scDiffusion was the most competitive diffusion-based method in several generalization settings. Temporal imputation showed a different pattern, with a simple DDPM operating directly in expression space outperforming more specialized models. Stress tests showed that performance was model dependent and sensitive to feature dimensionality, encoder choice, noise type and gene ordering. Pretrained encoders did not consistently improve performance, with the classical scVI representation slightly exceeding STATE in seen-condition and unseen-cell-type settings. These results indicate that diffusion-model performance in perturbation response prediction depends strongly on task design and representation choice. PertDiffBench provides a practical framework for evaluating these models under biologically varied and stress-tested conditions.

08.
arXiv (CS.AI) 2026-06-18

Scaling Learning-based AEB with Massive Unlabeled Data

arXiv:2606.18864v1 Announce Type: cross Abstract: This paper studies how to scale learning-based automatic emergency braking (AEB) with massive unlabeled fleet data under production constraints. Our approach is based on meta-feedback semi-supervised learning (MF-SSL), where a teacher generates pseudo labels for unlabeled driving data and is updated using a small labeled anchor set as safety-critical feedback. In production, anchor ambiguity and labeled-unlabeled mismatch can amplify systematic pseudo-label errors, leading to spurious triggers. We propose a stabilized MF-SSL framework with (i) Noise-Aware Decoupling, which removes ambiguity-prone anchors from the teacher's supervised update path, and (ii) kinematics-gated pseudo-labeling with a teacher conflict penalty to suppress mismatch-induced risk hallucinations on unlabeled data while maintaining broad coverage. Extensive experiments show consistent gains as unlabeled data scale from 1M to 1B windows, improving safety while keeping comfort stable. The 1B-trained student model is deployed to hundreds of thousands of vehicles and validated over \$10^9$ km of driving, achieving a positive-to-false activation ratio exceeding 100:1 and a 35% improvement in accident-free driving mileage over a production rule-only baseline.

09.
arXiv (CS.CL) 2026-06-16

SAAS: Self-Aware Reinforcement Learning for Over-Search Mitigation in Agentic Search

Agentic search enables LLMs to solve complex multi-hop questions through iterative reasoning and external search. Despite the effectiveness, these systems often suffer from a critical limitation in practice: agents fail to recognize their own knowledge boundaries, blindly triggering searches when internal knowledge suffices and failing to terminate search even when adequate evidence has been collected. The lack of self-awareness leads to severe over-search, incurring substantial inference latency and prohibitive computational cost. To this end, we propose SAAS, a novel RL framework designed to cultivate dynamic self-awareness that precisely regulates search behavior without compromising accuracy. SAAS introduces three key components: (i) a search boundary modeling mechanism, which identifies the search boundary under the evolving policy by contrasting search-disabled and search-enabled rollouts; (ii) a boundary-aware reward module, which translates this boundary awareness into trajectory-level penalties, suppressing unnecessary and redundant searches; and (iii) a stage-wise optimization strategy, which leverages a sequential curriculum to prioritize reasoning over search regularization, thereby avoiding reward hacking. Extensive experiments demonstrate that SAAS substantially reduces over-search, while maintaining accuracy. Our code and implementation details are released at https://github.com/XMUDeepLIT/SAAS.

10.
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.

11.
arXiv (CS.CV) 2026-06-16

DreamX-World 1.0: A General-Purpose Interactive World Model

DreamX-World 1.0 is a general-purpose interactive text/image-to-video world model for controllable long-horizon generation. It supports camera navigation, revisits to previously observed regions, and promptable events across photorealistic, game-style, and stylized domains. Our data engine combines camera-accurate Unreal Engine rendering, action-rich gameplay recordings, and real-world videos with recovered camera geometry. For camera control, we introduce E-PRoPE, a lightweight variant of projective positional encoding that retains PRoPE's projective camera geometry while applying camera-aware attention to spatially reduced tokens. We convert a bidirectional video generator into a few-step autoregressive world model using causal forcing, DMD-style distillation, and long-rollout training. Training on self-generated long-horizon contexts exposes the model to its own generated history and reduces the style and color drift that accumulates across autoregressive chunks. Memory-Conditioned Scene Persistence retrieves earlier views through camera-geometry-based retrieval, while residual recycling makes the conditioning path less sensitive to imperfect memory latents. Event Instruction Tuning adds composable event control, and reinforcement learning alignment recovers camera control and visual quality after distillation. With mixed-precision DiT execution, residual reuse, 75\%-pruned VAE decoding, and asynchronous pipeline parallelism, DreamX-World 1.0 reaches up to 16\,FPS on eight RTX\,5090 GPUs. On our 5-second basic evaluation, DreamX-World 1.0 achieves a camera-control score of 73.75 and an overall score of 84.76, outperforming HY-WorldPlay 1.5 and LingBot-World in overall score, which achieve 80.79 and 80.45, respectively.

12.
arXiv (CS.CL) 2026-06-16

Depth-Attention: Cross-Layer Value Mixing for Language Models

Self-attention selects information freely across the sequence, but across depth, Transformers merely add each layer's output to the residual stream, so later layers cannot selectively reuse earlier-layer representations. Recent cross-layer methods improve this flow but operate on hidden states outside attention, adding state beyond the key-value cache at inference–a cost that becomes increasingly salient as modern LLMs compress the cache with grouped-query and multi-head latent attention. We introduce Depth-Attention, which performs this selection inside the attention module itself: before a layer attends over the sequence, its query attends over the keys of earlier layers at the same token position and mixes their values into the value that self-attention then reads. Because Depth-Attention reuses the standard attention queries, keys, and value-cache slots, storing depth-mixed values in place of the original values, it adds no parameters and introduces no persistent inference state beyond the standard key-value cache–the same cache size as a vanilla decoder and less than hidden-state-based cross-layer methods. On Qwen3-style decoders at 1.5B and 3B parameters, Depth-Attention attains the lowest perplexity and the highest average downstream accuracy, improving over the vanilla Transformer by up to 2.3 accuracy points and surpassing strong cross-layer baselines in perplexity and average accuracy, while adding under 0.01% extra arithmetic FLOPs and no additional persistent inference state. The gains hold from 360M to 3B parameters and extend to looped Transformers.

13.
arXiv (CS.CV) 2026-06-12

Where, What, Why, and Importance: Structured Defect Grounding for Text-to-Image Feedback

Despite generating increasingly photorealistic images, text-to-image (T2I) models still exhibit localized, subtle, and structurally complex failures. Diagnosing these failures requires instance-level feedback that answers where a defect occurs, what type it is, why it is defective, and its importance to overall image quality. While recent dense-feedback methods move beyond scalar supervision, their heatmap-centric representations still formulate diagnosis as pixel-field regression, making it difficult to localize variable-cardinality defects and bind semantic reasons to individual failures. To address this representation bottleneck, we propose Structured Defect Grounding (SDG), which casts T2I diagnosis as structured set prediction by modeling each defect as a (location, type, reason, importance) tuple. To make this formulation trainable and measurable, we introduce SDG-30K, a 30K-image dataset with box-grounded annotations across four modern T2I generators, together with a dedicated evaluation protocol, SDG-Eval. Building on this structured representation, we further present a diagnosis-to-alignment framework in which a Vision-Language Model (VLM) serves as the SDG detector, and BoxFlow-GRPO converts predicted defect sets into box-derived, importance-weighted spatial rewards for diffusion model alignment. Extensive experiments show that our SDG detector outperforms leading proprietary VLMs on structured defect grounding, while SDG-guided rewards consistently improve T2I alignment and support localized image refinement. These results establish SDG as a unified, instance-level interface for diagnosing, evaluating, and enhancing modern generative models.

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

STRIDE: Strategic Trajectory Reasoning via Discriminative Estimation for Verifiable Reinforcement Learning

arXiv:2606.15866v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective post-training paradigm for improving the reasoning abilities of large language models. However, existing RLVR methods typically rely on final-answer correctness to assign trajectory-level rewards, providing sparse supervision and treating all tokens uniformly regardless of their actual contribution to reasoning. Although recent studies introduce intermediate signals such as process rewards, high-entropy tokens, and semantic uncertainty, these signals are often not inherently verifiable and may fail to distinguish beneficial strategic patterns from harmful ones. To address this limitation, we propose STRIDE (Strategic Trajectory Reasoning with Discriminative Estimation), a fine-grained RLVR framework that derives strategic reasoning supervision from verifiable outcomes. STRIDE contrasts successful and failed trajectories within each response group to estimate the outcome-discriminative preference of each $n$-gram strategic pattern, and further combines this signal with reasoning saliency entropy to identify decision-relevant strategic patterns. These patterns are assigned differentiated advantage values during RL optimization, enabling more precise credit assignment while preserving the verifiability of RLVR. Extensive experiments demonstrate that STRIDE consistently improves reasoning performance across diverse models, tasks, and extended settings, including VLMs and agent-based systems.

15.
arXiv (CS.CV) 2026-06-19

HEad and neCK TumOR (HECKTOR) 2025: Benchmark of Segmentation, Diagnosis, and Prognosis in Multimodal PET/CT

Head and neck cancers (HNC) represent a significant global health burden, with accurate tumor delineation being essential for effective radiotherapy planning. The complexity of the oropharyngeal anatomy, combined with the heterogeneous appearance of tumors on imaging, makes manual segmentation time-intensive and subject to inter-observer variability. Beyond segmentation, predicting long-term clinical outcomes, such as recurrence-free survival (RFS), and determining human papillomavirus (HPV) status from noninvasive imaging, remain challenging yet clinically valuable goals. The HECKTOR 2025 challenge addresses these needs by establishing a comprehensive benchmark for automated HNC analysis using multimodal PET/CT imaging and electronic health records. Building on previous editions (2020-2022), this challenge features an expanded multi-institutional dataset comprising over 1,100 patients from 10 centers worldwide. Participants were tasked with three complementary objectives: (1) segmenting primary gross tumor volumes (GTVp) and metastatic lymph nodes (GTVn), (2) predicting recurrence-free survival, and (3) classifying HPV status. The challenge attracted 35 registered teams, with 15 final submissions evaluated on a held-out test set. Top-performing algorithms achieved a mean Dice similarity coefficient of 0.75 for segmentation, a concordance index of 0.66 for survival prediction, and a balanced accuracy of 0.56 for HPV classification. This paper presents a comprehensive analysis of the submitted methodologies, evaluates their performance across different lesion characteristics, and discusses their implications for clinical translation in automated oncology workflows and decision support systems.

16.
arXiv (CS.LG) 2026-06-17

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning

arXiv:2606.18089v1 Announce Type: new Abstract: Post-training pipelines that combine supervised fine-tuning (SFT) with reinforcement learning (RL) have emerged as the key recipe for transforming large language models (LLMs) into robust reasoners. We argue that this combined success is driven by compositional generalization, which we formalize through a hierarchical latent selection model. In this framework, reasoning traces are generated by a cascade of discrete latent selection variables corresponding to reusable atomic modules, including both skills (local operations) and routing mechanisms (how intermediate information is selected, reused, and composed). Within this model, we theoretically show that SFT and RL play asymmetric, complementary roles: SFT supplies the raw module materials in compositional traces, and RL decomposes those traces to identify the latent atomic modules and enable compositional generalization. We design controlled experiments to validate this theory. Our results demonstrate that RL can extract atomic modules from compound traces supplied by SFT and recombine them to solve new configurations. Moreover, we find that training on compound traces yields stronger generalization than training on isolated atomic modules. Finally, we investigate the relationship between SFT and RL data and identify an effective protocol in which SFT ensures coverage of all atomic modules through compositional traces, while RL focuses on novel compositions outside the SFT support to drive exploration.

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

MagicSim: A Unified Infrastructure for Executable Embodied Interaction

Robot learning and embodied agents now require simulation to serve as a shared execution substrate linking control, skills, and planning, not only as a renderer, controller testbed, or fixed task environment. Existing pipelines split these layers with "magic" actions, disconnected training environments, or forward-only renders that cannot reproduce, evaluate, and annotate the same episode. We present MagicSim, an embodied interaction infrastructure built around one deterministic batched runtime and a shared Markov decision process (MDP). From YAML-first specifications that decouple contents, placement, behavior, and agent exposure, MagicSim constructs diverse executable worlds spanning task families, interaction regimes, physics, layouts, sensors, avatars, and robot embodiments in one reset-and-step loop. A common execution interface grounds high-level commands through controllers, atomicskills, planner primitives, and asynchronous planning, realizing them as robot actions rather than simulator-side state edits. One task definition supports three capabilities: benchmark and RL evaluation, an autocollect interface that automatically turns commands into grounded trajectories, and agent/VLM-facing interaction. For automatic execution, commands flow through a Command->Skill->Planner->Robot->Record pipeline, while per-environment command, skill, planning, retry, annotation, and episode states advance independently above the shared physics tick. Successful rollouts are saved as structured multimodal trajectories aligning language supervision, action representations, visual/geometric representations, and task-level status with the executed episode. MagicSim thus unifies diverse world construction, embodied execution, task evaluation, automatic rollout generation, and interactive agent interfaces in one planner-in-the-loop runtime.

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

MORTAR: Multi-turn Metamorphic Testing for LLM-based Dialogue Systems

With the widespread application of LLM-based dialogue systems in daily life, quality assurance has become more important than ever. Recent research has successfully introduced methods to identify unexpected behaviour in single-turn testing scenarios. However, multi-turn interaction is the common real-world usage of dialogue systems, yet testing methods for such interactions remain underexplored. This is largely due to the oracle problem in multi-turn testing, which continues to pose a significant challenge for dialogue system developers and researchers. In this paper, we propose MORTAR, a metamorphic multi-turn dialogue testing approach, which mitigates the test oracle problem in testing LLM-based dialogue systems. MORTAR formalises the multi-turn testing for dialogue systems, and automates the generation of question-answer dialogue test cases with multiple dialogue-level perturbations and metamorphic relations (MRs). The automated MR matching mechanism allows MORTAR more flexibility and efficiency in metamorphic testing. The proposed approach is fully automated without reliance on LLM judges. In testing six popular LLM-based dialogue systems, MORTAR reaches significantly better effectiveness with over 150\% more bugs revealed per test case when compared to the single-turn metamorphic testing baseline. Regarding the quality of bugs, MORTAR reveals higher-quality bugs in terms of diversity, precision and uniqueness. MORTAR is expected to inspire more multi-turn testing approaches, and assist developers in evaluating the dialogue system performance more comprehensively with constrained test resources and budget.

19.
arXiv (CS.AI) 2026-06-16

FreeSonic: Training-Free Temporal-Aware Decoupled Attention for Precise Audio Editing

arXiv:2606.15186v1 Announce Type: cross Abstract: Text-to-audio (TTA) generation has made significant strides, yet achieving precise and consistent audio editing remains a major challenge. However, existing methods struggle to balance temporal consistency with background preservation. In this paper, we propose FreeSonic, a training-free framework leveraging the state-of-the-art Rectified Flow-based TangoFlux model. FreeSonic utilizes an optimized inversion-reverse process and joint text-audio attention maps for precise target segment extraction. For content editing, a novel scheduled attention decoupling confines modifications to target regions while preserving original acoustic context. Furthermore, task-oriented noise injection enhances versatility for tasks such as audio removal and non-rigid replacement. Extensive experimental results demonstrate that FreeSonic achieves a superior balance by providing a high-fidelity and efficient solution for precise and consistent audio editing. Project and demos: https://free-sonic.github.io/

20.
arXiv (CS.AI) 2026-06-16

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

arXiv:2602.12670v4 Announce Type: replace Abstract: Agent Skills are structured packages of procedural knowledge that augment large language model (LLM) agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark whose current inventory contains 87 tasks across 8 domains paired with curated Skills and deterministic verifiers. Our latest aggregate evaluation runs the 87-task benchmark under matched no-Skills and curated-Skills conditions for 18 model-harness configurations. Curated Skills raise the average pass rate from 33.9% to 50.5% (+16.6 percentage points; 25.5% normalized gain), with configuration-level gains ranging from +4.1 to +25.7 pp. Focused Skills with at most three modules outperform larger or exhaustive bundles, and smaller models with Skills can match larger models without them. SkillsBench establishes paired evaluation as the foundation for rigorous measurement of Skill efficacy on agentic, expertise-heavy work.

21.
arXiv (CS.AI) 2026-06-17

Agentic Discovery of Non-Canonical Antimicrobial Peptides with AMPGAN v3

arXiv:2606.17127v1 Announce Type: cross Abstract: Antimicrobial resistance causes to over a million deaths annually. Antimicrobial peptides (AMPs) are a promising solution, but generative AMP models are not yet ready to design peptides with non-natural amino acids and/or chemical modifications, which are essential for real-world peptide drugs. We present AMPGAN v3, a multi-objective conditional GAN that expands the generative vocabulary to D-amino acids and N/C-terminus modifications such as amidation. By separating adversarial and activity-aware supervision across two specialized discriminators, AMPGAN v3 substantially improves training stability and outperforms prior generative AMP models on external classifiers. We validated five candidates spanning three structural classes in vitro; two showed activity against Gram-positive strains, with the best candidate reaching MIC 8 {\mu}g/mL against B. subtilis. To support downstream curation, we further present PepCraft, a multi-agent framework for end-to-end AMP discovery in which a Planning Agent orchestrates specialized executors for generation, filtering, and verification. Its prioritization recommendations align with our in vitro outcomes. Together, these contributions let us examine, on a small but real scale, how generative and agentic AI compose in therapeutic peptide discovery. Code: https://github.com/marszzibros/AMPGANv3

22.
arXiv (CS.AI) 2026-06-16

HoloRec: Holistic Encoding and Interleaved Reasoning for Generative Recommendation

arXiv:2606.15331v1 Announce Type: cross Abstract: Generative recommendation models that formulate the task as sequence generation overcome the objective fragmentation problem of traditional cascade architectures, yet existing approaches still suffer from flat semantic representations lacking hierarchical structure for multi-step reasoning and an externally constructed chain-of-thought (CoT) that requires expensive annotations and remains disconnected from the generation objective. We propose HoloRec, an endogenous chain-of-thought recommendation mechanism that unifies representation, reasoning, and generation by constructing a hierarchical semantic encoding matrix via multi-granularity nested residual quantization optimized by a holistic reconstruction loss. HoloRec supports two inference modes: a non-thinking mode that uses lightweight multi-granularity supervised alignment for fast prediction, and a thinking mode that employs an interleaved reasoning scheme to generate CoT steps on the fly, directly embedding reasoning into the generation process without external data. Experiments on multiple public recommendation datasets demonstrate that HoloRec consistently outperforms baselines, with especially significant gains in sparse scenarios, and the thinking mode achieves better accuracy than the non-thinking mode with only modest inference overhead.

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

MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios

arXiv:2602.22638v2 Announce Type: replace Abstract: Route-planning agents powered by large language models (LLMs) have emerged as a promising paradigm for supporting everyday human mobility through natural language interaction and tool-mediated decision making. However, systematic evaluation in real-world mobility settings is hindered by diverse routing demands, non-deterministic mapping services, and limited reproducibility. In this study, we introduce MobilityBench, a scalable benchmark for evaluating LLM-based route-planning agents in real-world mobility scenarios. MobilityBench is constructed from large-scale, anonymized real user queries collected from Amap and covers a broad spectrum of route-planning intents across multiple cities worldwide. To enable reproducible, end-to-end evaluation, we design a deterministic API-replay sandbox that eliminates environmental variance from live services. We further propose a multi-dimensional evaluation protocol centered on outcome validity, complemented by assessments of instruction understanding, planning, tool use, and efficiency. Using MobilityBench, we evaluate multiple LLM-based route-planning agents across diverse real-world mobility scenarios and provide an in-depth analysis of their behaviors and performance. Our findings reveal that current models perform competently on Basic information retrieval and Route Planning tasks, yet struggle considerably with Preference-Constrained Route Planning, underscoring significant room for improvement in personalized mobility applications. We publicly release the benchmark data, evaluation toolkit, and documentation at https://github.com/AMAP-ML/MobilityBench.

24.
arXiv (CS.CV) 2026-06-11

InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning

Recent progress in foundation models has shifted toward agentic behavior involving multi-step reasoning and tool use. However, open-source efforts largely focus on text-dominant settings, leaving long-horizon multimodal tasks underexplored. This gap is evident in video tasks requiring sustained temporal understanding and iterative interaction. We present InternVideo3, a framework enhancing these capabilities via Multimodal Contextual Reasoning (MCR). MCR treats understanding as a closed-loop process over a shared, evolving context containing observations, instructions, reasoning, tool actions, and memory. This frames long-video understanding as evidence accumulation and verification. To ensure efficiency, we introduce Multimodal Multi-head Latent Attention (M^2LA), a token-preserving reparameterization compressing KV-cache states while retaining the full token stream. Our staged training includes continued pretraining, short-to-long supervised fine-tuning, rule-based reinforcement learning, and on-policy distillation. Experiments show InternVideo3 achieves strong performance on benchmarks like Video-MME, MLVU, and EgoSchema. We further instantiate the model as a video agent with retrieval tools, demonstrating robust evidence-grounded behavior. Our results suggest that efficient context handling and closed-loop reasoning are vital for adapting open multimodal models toward long-horizon visually grounded agency.

25.
arXiv (CS.LG) 2026-06-18

Learning to Annotate Delayed and False AEB Events: A Practical System for Extreme Class Imbalance and Asymmetric Label Noise

arXiv:2606.19186v1 Announce Type: cross Abstract: Autonomous Emergency Braking (AEB) optimization relies on accurately annotated real-world trigger events, particularly rare but critical delayed and false AEB triggers that expose system deficiencies. However, these minority samples comprise less than 5% of thousands of daily triggers, making manual annotation prohibitively expensive at scale. We present the first automated AEB annotation framework to address this problem. During development, we identified two fundamental challenges that severely impair delayed/false trigger annotation accuracy: (1) Extreme class imbalance where delayed/false triggers are overwhelmed by true triggers; (2) Asymmetric label noise where mislabeled majority samples (true triggers) suppress minority samples (delayed/false triggers) learning. To overcome these challenges, we propose two key innovations: (1) Specific data augmentation that synthesizes realistic samples by manipulating focal target attributes, transplanting ego-vehicle dynamics, and masking non-focal agents; (2) noise suppression using stable hardness estimation and probe-guided adaptive threshold to clean mislabeled true trigger samples. Crucially, we deploy our model as a practical annotation system with full-stack architecture, efficiently identifying critical delayed/false triggers from thousands of daily AEB events. Production results demonstrate 80% improvement in recall of delayed/false triggers and 50% reduction in manual workload. Beyond immediate gains, the system enables continuous self-improvement through accumulated high-quality annotations, establishing a necessary data foundation for on-vehicle AEB system optimization