×

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: Jian Lin ×
换一批
01.
arXiv (quant-ph) 2026-06-16

Exactly Solvable Quantum Model with Spin-Dependent Coulomb Interaction

arXiv:2501.05103v5 Announce Type: replace Abstract: In this work, we report an exactly solvable quantum model featuring a spin-dependent Coulomb interaction, described by the spin vector potential \(\vec{\mathcal{A}} = k (\vec{r} \times \vec{S}) / r^2\) together with a Coulomb-type scalar potential \(\varphi = \kappa / r\) . The model is governed by the Schrödinger-type Hamiltonian \(\mathcal{H}_S = \vec{\Pi}^2 / (2M) + q \varphi\) in nonrelativistic quantum mechanics and by the Dirac-type Hamiltonian \(\mathcal{H}_D = c \vec{\alpha} \cdot \vec{\Pi} + \beta M c^2 + q \varphi\) in relativistic quantum mechanics, where \(\vec{\Pi} = \vec{p} - (q/c)\vec{\mathcal{A}}\) is the canonical momentum. We demonstrate two main results: (i) Just as the Coulomb-type scalar potential \(\mathcal{S}_Maxwell = \{\vec{\mathcal{A}} = 0,\ \varphi = \kappa / r\}\) is a local exact solution of Maxwell's equations on $r\neq0$, the gauge potential \(\mathcal{S}_YM = \{\vec{\mathcal{A}} = k (\vec{r} \times \vec{S}) / r^2,\ \varphi = \kappa / r\}\) constitutes a local exact solution of the Yang–Mills equations on the punctured region $r\neq0$. (ii) Both Hamiltonians \(\mathcal{H}_S\) and \(\mathcal{H}_D\) can be solved exactly in the presence of this spin-dependent Coulomb interaction. The resulting energy spectra are derived, and they naturally reduce to those of the ordinary hydrogen atom when the spin-dependent terms are neglected. Finally, we clarify the quantization conditions and the fixed-background interpretation of the model.

02.
arXiv (CS.CL) 2026-06-11

Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory

Medical agent systems are increasingly expected to support interactive clinical decision making rather than only static question answering. In such settings, effective agents must reuse prior experience across evolving cases, yet existing memory mechanisms often retain raw historical traces that are redundant, noisy, and difficult to govern. More importantly, they rarely distinguish which memories are truly useful for future reasoning. This limits their ability to accumulate compact and reliable experience for long-horizon clinical reasoning. To close this gap, we propose SkeMex, a post-deployment self-evolution framework that improves medical agents through a skill-based memory without updating model weights. SkeMex distills informative interaction trajectories into structured skills that encode reusable procedural knowledge, and organizes them into a multi-branch repository spanning general, task-specific, and action-level experience. To determine which memories should be reused and retained, SkeMex estimates context-dependent utility from environment feedback and uses it to guide value-aware retrieval and repository governance. A closed-loop ``Read–Write–Assess–Govern" lifecycle further supports continual evolution by writing new skills, updating utilities, promoting useful memories, and removing harmful entries. Experiments across diverse clinical tasks show that SkeMex consistently outperforms representative memory-based agents in both offline and online settings. It also generalizes across model backbones and supports transferable skill memory. All data and code will be released publicly.

03.
arXiv (CS.CV) 2026-06-18

SAMA: Semantic Anchor-aligned Augmentation for Unified Low-Resource Multimodal Information Extraction

Multimodal Information Extraction (MIE)-covering tasks such as Multimodal Named Entity Recognition (MNER), Relation Extraction (MRE), and Event Extraction (MEE)-is essential for understanding multimedia content but remains constrained by severe data scarcity. Although data augmentation is a promising remedy, existing approaches are impeded by coarse cross-modal alignment and fragmented, task-specific designs that fail to exploit shared semantic knowledge. To overcome these limitations, we introduce Semantic Anchor-aligned Multimodal Augmentation (SAMA), a unified framework for generating high-fidelity, task-aware synthetic data. SAMA constructs structured semantic anchors from ground-truth labels to guide a Collaborative Multi-Experts Multimodal Large Language Model (CME-MLLM), which integrates a Universal Adapter for shared semantics with Task-Specific Adapters to produce diverse yet constraint-compliant textual samples. For image synthesis, SAMA employs an Anchor-Preserving Diffusion mechanism that uses anchor-weighted prompts and latent conditioning to maintain critical semantic anchors while diversifying visual contexts. To eliminate the need for manual verification, SAMA further introduces a Dual-Constraint Filtering module that selects synthetic samples based on both cross-modal consistency and anchor fidelity. Extensive experiments across benchmark datasets for MNER, MRE, and MEE demonstrate that SAMA consistently outperforms state-of-the-art augmentation baselines under both fully supervised and low-resource settings, underscoring its versatility, robustness, and effectiveness.

04.
arXiv (CS.CL) 2026-06-19

Token-Operations-Oriented Inference Optimization Techniques for Large Models

Large model inference optimization serves as a key foundation for supporting the scalable, low-cost, and highly stable operation of large model services. Centered on token-oriented inference optimization technology, this paper proposes for the first time a four-layer technical architecture consisting of Multi-model Fusion, Model Optimization, Compute-Model Fusion, and Compute-Network-Model Fusion. It systematically reviews the key technologies and current industry status across these four levels and analyzes the application value of related technologies in real-world business scenarios. This paper provides a practical technical path for reducing token production costs, improving token service efficiency, ensuring the stability of token supply, and driving the transition of large model services from being merely callable to being operable.

05.
arXiv (CS.CV) 2026-06-11

What Semantics Survive the Connector? Diagnosing VLM-to-DiT Alignment in Video Editing

Flow matching based video generative models have been increasingly relying on prepended Vision-Language Models (VLMs) to handle complex, instruction-based video editing. The prevailing assumption underlying this paradigm is that a connector module can seamlessly align the VLM's rich multi-modal reasoning with the original text embedding space of DiTs. However, we hypothesize that this alignment acts as a severe semantic bottleneck, degrading fine-grained structural variables. Verifying this is challenging, as end-to-end evaluations conflate alignment failures with generation errors, and natural datasets lack disentangled annotations. To rigorously investigate this, we propose a controlled data processing pipeline based on video composition that results in TRACE-Edit, a diagnostic dataset focusing on relation-based editing. Leveraging this dataset, we propose a comprehensive diagnostic protocol to analyze two important designs of meta-query and connector in the existing video editing models. Systematic evaluation of four representative model cases reveals that fine-grained structural semantics can be severely degraded during alignment. Our findings overturn the assumption of lossless semantic transfer, identifying the VLM-to-DiT alignment as a major bottleneck and providing a new diagnostic foundation for future multi-modal alignment architectures.

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

PaLMR: Towards Faithful Visual Reasoning via Multimodal Process Alignment

Reinforcement learning has recently improved the reasoning ability of Large Language Models and Multimodal LLMs, yet prevailing reward designs emphasise final-answer correctness and consequently tolerate process hallucinations–cases where models reach the right answer while misperceiving visual evidence. We address this process-level misalignment with PaLMR, a framework that aligns not only outcomes but also the reasoning process itself. PaLMR comprises two complementary components: a perception-aligned data layer that constructs process-aware reasoning data with structured pseudo-ground-truths and verifiable visual facts, and a process-aligned optimisation layer that constructs a hierarchical reward fusion scheme with a process-aware scoring function to encourage visually faithful chains-of-thought and improve training stability. Experiments on Qwen2.5-VL-7B show that our approach substantially reduces reasoning hallucinations and improves visual reasoning fidelity, achieving state-of-the-art results on HallusionBench while maintaining strong performance on MMMU, MathVista, and MathVerse. These findings indicate that PaLMR offers a principled and practical route to process-aligned multimodal reasoning, advancing the reliability and interpretability of MLLMs.

07.
arXiv (CS.CL) 2026-06-11

GraphInfer-Bench: Benchmarking LLM's Inference Capability on Graphs

Graph analysis underlies many applications whose answers cannot be looked up in a single record or retrieved along a path: laundering rings, drug repurposing, user preference, and scientific theme are all inferred from a node together with its neighbourhood. We introduce GraphInfer-Bench, a benchmark for whether LLMs can perform this graph inference: producing an open-ended answer that no single node supports and no path retrieves. Existing graph-QA protocols cannot test this capability: algorithm simulation, node classification, single-node description, KG-QA, and GraphRAG all admit answers retrievable from one node or along a path. GraphInfer-Bench defines five tasks along Description (what a region is) and Comparison (how regions differ), each constructed so the ground truth lives in no single node. The release contains 42,000 samples across six real-world graphs, produced automatically and screened by a four-layer quality-control protocol. We evaluate four method families against the same tasks: graph-token alignment models, zero-shot frontier closed-source LLMs, Graph2Text supervised fine-tuning, and plain GNNs as a structural reference. No method family closes the gap. Graph-token alignment partially handles description tasks (relational, theme) but collapses on comparison tasks. Frontier LLMs lead on outlier detection and community partition among LLM-based methods but lag on masked-node prediction. Graph2Text SFT is the strongest LLM-based method on the description side yet falls behind frontier LLMs on comparison. Across every task, plain GNNs match or beat the strongest LLM-based row, with the largest margin on community detection. GraphInfer-Bench surfaces graph inference as an open capability gap rather than a property of any one architecture.

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

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

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

09.
arXiv (CS.AI) 2026-06-12

Teach-and-Repeat: Accurately Extracting Operational Knowledge from Mobile Screen Demonstrations to Empower GUI Agents

arXiv:2606.12817v1 Announce Type: new Abstract: Understanding the digital world on mobile devices is shifting from static UI perception to dynamic action comprehension. This capability enables models to convert visual state transitions into operational knowledge, defined as short natural-language sentences that describe action types, target UI elements, textual arguments, and execution orders. However, due to the highly diverse and heterogeneous UI designs across applications, existing vision-language models (VLMs) struggle to accurately infer these underlying operations. To bridge this gap, we introduce Teach VLM, a core model designed to translate mobile screen trajectories into step-wise operational knowledge by extracting and analyzing operation-related keyframes from demonstration videos. To address the scarcity of aligned training data, we develop a systematic data flywheel for scalable data acquisition. We further introduce a novel Chinese Mobile Screen Teach Benchmark for fine-grained evaluation. Building upon Teach VLM, we propose the Teach-and-Repeat paradigm, where the generated operational knowledge serves as an interpretable procedural reference to guide downstream screen-based execution agents. Extensive evaluations demonstrate that Teach VLM significantly outperforms strong VLM baselines, achieving state-of-the-art performance in operation semantics prediction. Furthermore, experiments in Android World show that our paradigm yields consistent Task Success Rate improvements for downstream agents. Together, Teach VLM and the Teach-and-Repeat paradigm offer a practical pathway from raw demonstrations to reusable task automation.

10.
arXiv (CS.CL) 2026-06-15

AgentSpec: Understanding Embodied Agent Scaffolds Through Controlled Composition

LLM agents are increasingly built not as single model calls, but as scaffolded systems that combine reasoning, memory, reflection, action execution, and learning. While such scaffolds often improve performance, they are often embedded in tightly coupled pipelines, making it difficult to isolate component contributions, compare alternative designs, or understand how module interactions shape agent behavior. We introduce AgentSpec, a modular specification framework that represents embodied agents as typed compositions of reusable policy components with standardized interfaces. AgentSpec standardizes the interfaces among perception, memory, reasoning, reflection, action, and optional learning, enabling components to be swapped and recombined under controlled conditions. We instantiate this framework across DeliveryBench, ALFRED, MiniGrid, and RoboTHOR, and analyze reasoning, memory, reflection, and reinforcement-learning modules across model backbones. Our results show that agent performance is governed by scaffold compatibility and interaction effects rather than isolated module strength. In particular, structured multi-granularity memory improves long-horizon state tracking, reasoning and memory interact non-uniformly across environments, reflection trades off correction and cost, and RL-trained policies compose best when optimized with deployment-time scaffold structure. AgentSpec provides a controlled foundation for studying, comparing, and designing composable LLM agents. Our code, baselines and interactive playground are publicly available at https://agentspec-embodied.github.io.

11.
arXiv (CS.CV) 2026-06-17

AnnotateAnything: Automatic Annotation of 3D Assets for Robot Manipulation

Simulation enables scalable robot data collection, but raw 3D assets provide only geometry, lacking the semantic, interactive, and physical knowledge needed to specify where and how robots should act. In this work, we present AnnotateAnything, a general automatic annotation framework that converts passive 3D assets into manipulation-ready assets with structured, diverse, and executable manipulation labels. AnnotateAnything is built around two complementary pipelines. First, a unified visual-language annotation pipeline using vision-language reasoning to infer object semantics, interaction constraints, and 3D-grounded cues, providing human-prior guidance for identifying meaningful interaction regions. Second, a fully automatic and massively parallel physics annotation pipeline grounds these priors in each asset's geometry and physical constraints through candidate generation, geometry optimization and trajectory generation. This pipeline produces diverse and executable action annotations, including grasp poses, dexterous contacts, articulation waypoints, insertion directions, hanging affordances, and navigation targets. Using the generated annotations, we further build an asynchronous parallel simulation data-collection system across diverse objects, tasks, and robot embodiments. Experiments demonstrate that AnnotateAnything achieves superior annotation efficiency, data-collection efficiency, and task success rates over existing annotation and data-generation pipelines, while also supporting downstream tasks such as affordance detection, robotic VQA, and visual instruction finetuning. We provide project materials on the project page and plan to release the full code, annotations, and benchmark to facilitate future research. Videos, code, demo assets, and annotations are provided in supplementary materials Project page: https://tourmaline-caramel-169490.netlify.app.

12.
arXiv (CS.CV) 2026-06-15

3D-RFT: Reinforcement Fine-Tuning for Video-based 3D Scene Understanding

Reinforcement Learning with Verifiable Rewards ( RLVR ) has emerged as a transformative paradigm for enhancing the reasoning capabilities of Large Language Models ( LLMs), yet its potential in 3D scene understanding remains under-explored. Existing approaches largely rely on Supervised Fine-Tuning ( SFT), where the token-level cross-entropy loss acts as an indirect proxy for optimization, leading to a misalignment between training objectives and task performances. To bridge this gap, we present Reinforcement Fine-Tuning for Video-based 3D Scene Understanding (3D-RFT ), the first framework to extend RLVR to video-based 3D perception and reasoning. 3D-RFT shifts the paradigm by directly optimizing the model towards evaluation metrics. 3D-RFT first activates 3D-aware Multi-modal Large Language Models ( MLLM s) via SFT, followed by reinforcement fine-tuning using Group Relative Policy Optimization ( GRPO) with strictly verifiable reward functions. We design task-specific reward functions directly from metrics like 3D IoU and F1-Score to provide more effective signals to guide model training. Extensive experiments demonstrate that 3D-RFT-4B achieves state-of-the-art performance on various video-based 3D scene understanding tasks. Notably, 3D-RFT-4B significantly outperforms larger models (e.g., VG LLM-8B) on 3D video detection, 3D visual grounding, and spatial reasoning benchmarks. We further reveal good properties of 3D-RFT such as robust efficacy, and valuable insights into training strategies and data impact. We hope 3D-RFT can serve as a robust and promising paradigm for future development of 3D scene understanding.

13.
arXiv (CS.CL) 2026-06-18

Are LLMs Ready to Assist Physicians? PhysAssistBench for Interactive Doctor-Patient-EHR Assistance

The most plausible near-term role of medical LLMs is to assist rather than replace physicians, yet current evaluations often test isolated capabilities: clinical knowledge, EHR system interaction, or patient communication. Physician assistance instead requires coordinating these capabilities within the same interaction, where physicians issue underspecified requests, patients describe symptoms ambiguously, and EHR systems demand precise tool use. We introduce PhysAssistBench, a benchmark for interactive doctor-patient-EHR assistance. Built from real MIMIC-IV cases, PhysAssistBench uses a scalable pipeline to construct agentic patients: interactive, record-grounded agents that turn static EHR records into multi-turn clinical scenarios while preserving clinical factuality. PhysAssistBench provides a curated bilingual evaluation set of 1,296 manually reviewed and physician-validated turns. Experiments with leading LLMs show that current models remain unreliable in this setting, which exposes a key bottleneck for clinical LLMs: reliable assistance requires coordination across knowledge, communication, and systems, not isolated gains in any of them.

14.
arXiv (CS.CL) 2026-06-17

DICE: Diffusion Large Language Models Excel at Generating CUDA Kernels

Diffusion large language models (dLLMs) have emerged as a compelling alternative to autoregressive (AR) LLMs, owing to their capacity for parallel token generation. This paradigm is particularly well-suited for code generation, where holistic structural planning and non-sequential refinement are critical. Despite this potential, tailoring dLLMs for CUDA kernel generation remains challenging, obstructed not only by the high specialization but also by the severe lack of high-quality training data. To address these challenges, we construct CuKe, an augmented supervised fine-tuning dataset optimized for high-performance CUDA kernels. On top of it, we propose a bi-phase curated reinforcement learning (BiC-RL) framework consisting of a CUDA kernel infilling stage and an end-to-end CUDA kernel generation stage. Leveraging this training framework, we introduce DICE, a series of diffusion large language models designed for CUDA kernel generation, spanning three parameter scales, 1.7B, 4B, and 8B. Extensive experiments on KernelBench demonstrate that DICE significantly outperforms both autoregressive and diffusion LLMs of comparable scale, establishing a new state-of-the-art for CUDA kernel generation.

15.
arXiv (CS.AI) 2026-06-11

Grounding Computer Use Agents on Human Demonstrations

arXiv:2511.07332v2 Announce Type: replace-cross Abstract: Building reliable computer-use agents requires grounding: accurately connecting natural language instructions to the correct on-screen elements. While large datasets exist for web and mobile interactions, high-quality resources for desktop environments are limited. To address this gap, we introduce GroundCUA, a large-scale desktop grounding dataset built from expert human demonstrations. It covers 87 applications across 12 categories and includes 56K screenshots, with every on-screen element carefully annotated for a total of over 3.56M human-verified annotations. From these demonstrations, we generate diverse instructions that capture a wide range of real-world tasks, providing high-quality data for model training. Using GroundCUA, we develop the GroundNext family of models that map instructions to their target UI elements. At both 3B and 7B scales, GroundNext achieves state-of-the-art results across five benchmarks using supervised fine-tuning, while requiring less than one-tenth the training data of prior work. Reinforcement learning post-training further improves performance, and when evaluated in an agentic setting on the OSWorld benchmark using o3 as planner, GroundNext attains comparable or superior results to models trained with substantially more data,. These results demonstrate the critical role of high-quality, expert-driven datasets in advancing general-purpose computer-use agents.

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

A 3D Isovist World Model – Revealing a City's Unseen Geometry and Its Emergent Cross-City Signature

arXiv:2606.03609v3 Announce Type: replace-cross Abstract: Embodied agents that navigate cities rely on world models that predict how their surroundings will change as they move. But for navigation, what matters is not what the buildings look like; it is where the agent can go. Most world models nonetheless predict appearance, learning how a scene looks rather than the space an agent can move through. Those that do target geometry, such as bird's-eye-view occupancy grids, flatten the three-dimensional environment onto a ground plane, discarding the above-ground and multi-level structure that shapes real navigation. What is missing is a predictive target that captures the navigable geometry an agent actually traverses, without photometric entanglement and without collapsing the third dimension. Our key idea is to model the open volume between buildings, the negative space, encoded as a 3D isovist: a spherical visibility-depth map recording the distance to the nearest surface in every direction. We introduce an embodied world model that predicts the next isovist from a short history of past isovists and a movement action. The prediction is formulated as a depth residual so the decoder inherits sharp building edges, trained with self-rollout scheduled sampling to keep corrupted context on the geometry manifold, and equipped with a persistent latent bird's-eye-view spatial map for cross-path consistency. Our central finding is emergent and unexpected: a single city-blind model trained on Manhattan and Paris develops a cross-city spatial signature, with city identity linearly decodable from its temporal latents far above single-frame baselines, so the signature lives in the learned dynamics rather than in appearance. The representation is lightweight, interpretable, and reproducible, offering a geometric substrate for spatial reasoning in embodied AI, robotics, and urban analysis, released with an open dataset and pipeline.

17.
arXiv (CS.AI) 2026-06-11

Exploration Structure in LLM Agents for Multi-File Change Localization

arXiv:2606.11976v1 Announce Type: cross Abstract: Software engineering tools increasingly rely on LLM based agents to localize files to change to resolve a software issue. Most AI agents explore repositories linearly, that is, visiting one directory or file per step. We postulate that this is a structural mismatch for changes that span several subsystems. We compare linear sequential exploration against non-linear, domain-scoped parallel agentic exploration. Using SWE Bench Pro as initial benchmark, we focus on ansible as an exemplar. We construct an approach for persistent-session evaluation of GitHub issues anchored at a single base commit. We compare our non-linear domain-agent file traversal system against a base LLM without direct repository access, a single agent Recursive Language Model (RLM) baseline with a persistent Python REPL and an external CLI baseline using Codex 5.5 High. Domain scoped parallel agent spawning with a small Haiku-class model achieves the highest micro F1 among Haiku class models by a large margin. Domain-agents is the second highest behind only the much larger Codex 5.5 High on our own expanded benchmark including over more recent PRs from 2025 and 2026. On the original, curated, 2020 SWE-bench Pro benchmark, a larger Sonnet plain LLM baseline attains higher micro F1 by predicting few files, leading to higher precision, but at significantly lower all gold recall. We also present three additional findings. First, documentation evolution is a latent dependency unresolved by any approach. Second, naive file system access can degrade localization driven by test-file over prediction. Lastly, forced multi-agent consultation does not measurably help and raises token cost substantially.

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

Beyond Retrieval: Learning Compact User Representations for Scalable LLM Personalization

Personalizing large language models requires adapting model behavior to individual users while preserving robustness and deployment-scale efficiency. Existing approaches typically personalize LLMs either at the input level, by retrieving user histories or constructing profile prompts, or at the parameter level, by maintaining user-specific parameter-efficient modules. The former makes personalization sensitive to retrieval quality and prompt design, whereas the latter incurs storage and maintenance costs that grow with the user population. To address these limitations, we propose TAP-PER (Temporal Attentive Prefix for PERsonalization), a prefix-based framework that encodes user preferences as learnable representations, eliminating explicit prompt construction and replacing heavy per-user adapters with lightweight user-state prefix embeddings. Inspired by personalized recommendation systems, TAP-PER decomposes user modeling into user-state and query-conditioned components, and incorporates temporal signals to capture the evolving nature of user interests. Experiments on six LaMP tasks show that TAP-PER consistently outperforms prompt-based and model-based baselines across classification, rating, and generation settings. Moreover, TAP-PER uses 130x fewer per-user parameters than OPPU and roughly half the total parameter footprint of PER-PCS at the 1,000-user scale, demonstrating that scalable LLM personalization can be achieved without explicit prompt construction or heavy per-user adapters.

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

GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?

Game generation is an emerging application of coding agents, requiring models to transform natural-language specifications into playable interactive systems. Unlike traditional coding tasks, game generation takes place within a game engine, where scripts, scenes, assets, rendering, and runtime interactions must jointly produce coherent gameplay. We formalize end-to-end game generation as the problem of producing a complete game artifact that realizes a specification through observable player-game interaction in a target environment. We argue that evaluating this setting requires three desiderata: Engine Grounding, Artifact Completeness, and Interactive Verification. We propose an interaction-grounded evaluation framework that assesses executable gameplay through replayed demonstrations and rubric-guided multimodal judging. We instantiate this framework as GameCraft-Bench, a benchmark comprising 140 Godot tasks across 15 game families. Evaluations of frontier coding agents show that end-to-end game generation remains highly challenging: the strongest agent achieves only 41.46%, and most agents score below 40%. Further analysis reveals that while agents often implement recognizable mechanics, they struggle to deliver complete games with sufficient content, functional visual feedback, and coherent presentation. See https://tongxuluo.github.io/gamecraft-bench-website for demos, code, and data.

20.
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.

21.
arXiv (CS.AI) 2026-06-15

When Good Verifiers Go Bad: Self-Improving VLMs Can Regress on New Tasks

作者:

arXiv:2606.14629v1 Announce Type: cross Abstract: Verifier-driven self-DPO is a common recipe for self-improving production visual-language models. In this setup, a frozen verifier scores candidate generations, the top- and bottom-scoring candidates form a preference example, and DPO updates the learner. The deployment-time assumption is monotone: a stronger verifier should yield a stronger student. We show that this assumption can fail because verifier quality is highly task-specific. On a four-rung open-source verifier ladder across MathVista, MMMU, and BLINK, the same verifiers that are above-threshold and improve a Qwen-3-VL-2B student on MathVista become sub-threshold on MMMU, where their task-rubric accuracy drops to 8% to 23%. In this regime, every verifier we tested silently regresses the student, producing drops of 3.4 to 10.9 percentage points below the frozen baseline while the DPO training loss continues to decrease. The regression replicates on a second student, Qwen-2.5-VL-3B. Moreover, within the failure regime, damage is confidence-inverted: the more accurate-but-still-wrong verifier causes larger regression than a near-random verifier, suggesting that progress-gated replay amplifies confidently wrong preference pairs. We give a compact mechanistic explanation via a variance theorem for progress-gated replay and its direction-mismatch failure mode. The deployment message is operational rather than purely diagnostic: before running any verifier-driven loop, teams should measure target-task rubric accuracy, rank verifiers by target-task rubric quality rather than parameter count, and treat diminishing returns in above-threshold regimes as a verifier-side compute budget cap.

22.
arXiv (CS.AI) 2026-06-11

A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data

arXiv:2601.17717v3 Announce Type: replace Abstract: Large Language Models (LLMs) have emerged as powerful tools for generating data across various modalities. By transforming data from a scarce resource into a controllable asset, LLMs mitigate the bottlenecks imposed by the acquisition costs of real-world data for model training, evaluation, and system iteration. However, ensuring the high quality of LLM-generated synthetic data remains a critical challenge. Existing research primarily focuses on generation methodologies, with limited direct attention to the quality of the resulting data. Furthermore, most studies are restricted to single modalities, lacking a unified perspective across different data types. To bridge this gap, we propose the LLM Data Auditor framework. In this framework, we first describe how LLMs are utilized to generate data across six distinct modalities. More importantly, we systematically categorize intrinsic metrics for evaluating synthetic data from two dimensions: quality and trustworthiness. This approach shifts the focus from extrinsic evaluation, which relies on downstream task performance, to the inherent properties of the data itself. Using this evaluation system, we analyze the experimental evaluations of representative generation methods for each modality and identify substantial deficiencies in current evaluation practices. Based on these findings, we offer concrete recommendations for the community to improve the evaluation of data generation. Finally, the framework outlines methodologies for the practical application of synthetic data across different modalities.

23.
bioRxiv (Bioinfo) 2026-06-16

OmicOS: A Comprehensive Omics Ecosystem Infrastructure and Agent System for the AI Era

Biology has accumulated a vast ecosystem of omics methods, but much of this ecosystem remains built for expert humans rather than scientific agents. Methods are scattered across Python packages, R/Bioconductor and CRAN workflows, command-line tools, incompatible data containers and implicit object states, making even routine analyses difficult for an AI system to choose, execute and verify reliably. Here we introduce OmicOS, a comprehensive omics ecosystem infrastructure and agent system that turns OmicVerse V2, an open-source omics community, into an executable foundation for agentic biology. OmicVerse V2 provides the community substrate: scalable AnnDataOOM-compatible rust backends, agent-friendly Python algorithms for single-cell, spatial, bulk and multi-omics analysis, interfaces to single-cell foundation models, and Python-native reconstructions of historically R-centred Bioconductor/CRAN-style workflows. OmicOS makes this substrate actionable by registering analytical functions as state-aware capability contracts, allowing agents to inspect live data objects, select valid methods, execute controlled workflows and record provenance. The result is not a fixed pipeline, but a programmable omics environment in which agents compose real analyses from verified community methods rather than inventing tools. Across external and purpose-built benchmarks, OmicOS ranked first among the evaluated systems, reaching 81.2% on BiomniBench. Adding OmicVerse to a minimal agent improved task completion by up to 34.2 percentage points with qwen-3.6-35b, and controlled ablations showed that the gains came from registry-grounded execution rather than from larger models, documentation retrieval or unrestricted tool exposure. The same infrastructure scaled to atlas-sized data, reproduced R-centred workflows in Python and converted external pathology software into agent-usable skills. In a discovery task starting from a whole-body spatial map and the term Alzheimer disease, OmicOS composed a non-canonical workflow that integrated spatial expression, genetic association, eQTL and colocalization evidence to nominate a colon epithelial risk axis centred on PICALM, CD2AP and CR1. Together, OmicVerse and OmicOS define an open foundation for AI-era omics, showing how a community of biological methods can be transformed into a reliable, extensible and agent-operable system for discovery.

24.
arXiv (CS.AI) 2026-06-16

UXBench: Measuring the Actionability of LLM-Generated UX Critiques

arXiv:2606.16262v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as UX judges that inspect interfaces, diagnose usability problems, and propose repairs. Yet no controlled benchmark measures whether the resulting critiques are reliable and actionable across heterogeneous product surfaces. We introduce UXBench, a benchmark for evaluating LLMs as interaction-grounded UX judges. UXBench comprises local-first runnable web fixtures spanning ten product-surface families, paired with coverage-gated browser exploration that forces models to collect interaction evidence before reporting. Each judge model produces a structured UX report over seven rubric dimensions; report quality is measured by whether a fixed downstream repair agent can improve the interface based on the critique. We evaluate eight frontier models under both an automated repair-lift protocol and a blind human validation study. Results show that UX judging is neither saturated nor one dimensional: models differ meaningfully in report actionability, exhibit distinct rubric-level repair signatures, vary in fixture-level reliability, and trade leadership across surface categories

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

Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence

While LLMs have substantially advanced text-to-code synthesis, many real programming tasks specify intent through visual artifacts such as screenshots, charts, documents, vector drawings, videos, and interactive states. These tasks require models to connect visual perception to executable programs, because correctness depends not only on syntax but also on layout, geometry, data semantics, editability, interaction behavior, and domain-specific constraints that apply after execution. This survey examines Multimodal Code Intelligence, covering systems that generate, edit, refine, execute, or reason with code under visually grounded inputs and outputs. We first formulate the field by the role that code plays in each task, distinguishing code as a rendered artifact, an editable symbolic structure, a scientific representation, an intermediate reasoning trace, or an executable policy or tool interface. We then organize benchmarks and methods into four domains: Graphical User Interface, Scientific Visualization, Structured Graphics, and Frontier Tasks and Frameworks. This taxonomy connects mature artifact-generation problems to emerging agentic and unified settings and allows us to compare how different tasks treat evidence of correctness. Looking ahead, we argue that future research may benefit from four verification-centered directions. Multi-signal validation can combine complementary evidence of correctness, multi-state verification can test behavior across execution trajectories, cross-task transfer testing can probe reusable visual-code skills, and verifiable agent traces can reveal whether agent actions are grounded in visual evidence. Together, these directions may move multimodal code generation from single-output imitation toward evidence-grounded executable systems.