Teng Pan, Zixuan Wang, Yuchen Yan, Qifei Wu, Yao Chen, Yingqi Qu, Ruiqing Zhang, Yongliang Shen
Large language models have made rapid progress in agentic reasoning and tool use, raising expectations for agents that can take over realistic productivity work from humans. However, current agents still struggle to finish such tasks, where success requires following long-horizon professional workflows, understanding heterogeneous file contexts, and producing usable deliverables under fine-grained requirements. A key bottleneck is the lack of scalable post-training data that reflects real work intent, authentic file environments, and deliverable-level evaluation. To close this gap, we introduce Agent-R$^2$, a $\textbf{r}$eal-source data synthesis framework that scales training data for $\textbf{r}$ealistic productivity work. Instead of relying on manually specified workflows or LLM-generated files, Agent-R$^2$ grounds synthesis throughout the pipeline in real occupational seeds, corpus-derived workflow evidence, and authentic web-sourced files. From 10k web-corpus candidates, Agent-R$^2$ distills 4k task instances that pair real multi-format attachments with fine-grained, deliverable-level rubrics. On this data, we train Agent-R$^2$-4B via supervised fine-tuning and rubric-based reinforcement learning, improving both end-to-end productivity performance and file-grounded reasoning. Trained on only 4k instances, Agent-R$^2$-4B surpasses Qwen3-235B-A22B-Thinking-2507 on both GDPval (51.0$\%$ vs. 48.0$\%$) and OfficeQA (14.8$\%$ vs. 13.8$\%$). Further analysis shows that Agent-R$^2$ mitigates shortcut behavior, where agents produce superficially plausible deliverables before sufficiently grounding, constructing, or verifying them, while promoting sustained exploration.
The rapid proliferation of LLM-based autonomous agents in real operating system environments introduces a new category of safety risk beyond content safety: behavior jailbreak, where an adversary induces an agent to execute dangerous OS-level operations with irreversible consequences. Existing benchmarks either evaluate safety at the semantic layer alone, missing physical-layer harms, or fail to isolate test cases, letting earlier runs contaminate later ones. We present LITMUS (LLM-agents In-OS Testing for Measuring Unsafe Subversion), a benchmark addressing both gaps via a semantic-physical dual verification mechanism and OS-level state rollback. LITMUS comprises 819 high-risk test cases organized into one harmful seed subset and six attack-extended subsets covering three adversarial paradigms (jailbreak speaking, skill injection, and entity wrapping), plus a fully automated multi-agent evaluation framework judging behavior at both conversational and OS-level physical layers. Evaluation across frontier agents reveals three findings: (1) current agents lack effective safety awareness, with strong models (e.g., Claude Sonnet 4.6) still executing 40.64% of high-risk operations; (2) agents exhibit pervasive Execution Hallucination (EH), verbally refusing a request while the dangerous operation has already completed at the system level, invisible to every prior semantic-only framework; and (3) skill injection and entity wrapping attacks achieve high success rates, exposing pronounced agent vulnerabilities. LITMUS provides the first standardized platform for reproducible, physically grounded behavioral safety evaluation of LLM agents in real OS environments.
Speech large language models retain audio history to support multi-turn conversations. Yet remembering an event does not ensure that its information is used only when relevant. We investigate why irrelevant historical audio changes answers even when the queried event remains represented. Controlled experiments on MOSS-Audio and MiMo-Audio show that historical values direct errors toward specific competing answers, beyond a generic effect of context length. Causal interventions distinguish two paths. In open-ended question answering, most history-value errors disappear when subsequent computation cannot directly access the irrelevant source. In multiple-choice answering, many errors persist: early historical influence is carried by question-candidate states even after direct source access is blocked. Low-dimensional interventions further separate source-role information from answer-value information. Their effects peak at different depths, and changing the source-role signal does not eliminate the causal influence of competing values. On naturally occurring errors, strengthening the queried role and counteracting the historical value each improve answers; their joint intervention gives the greatest recovery. These findings support a failure of downstream evidence use beyond source identification alone: source-role information can influence a decision without exclusively controlling which historical values affect it. Reliable conversational memory therefore requires not only retention and retrieval, but also control over how retained information enters answer computation.
The emergence of programmable switches has brought in-network computing (INC) into the spotlight in recent years. By offloading computation directly onto the data transmission process, INC improves network utilization, reduces latency to sub-RTT levels, saves link bandwidth, and maintains throughput. However, INC disrupts the transparency of traditional networks, forcing developers to consider network exceptions like packet loss and out-of-order. If not properly handled, these exceptions can lead to violations of application properties, such as cache consistency and lock exclusion. Usual testing cannot exhaustively cover these exceptions, raising doubts about the correctness of INC systems and hindering their deployment in the industry. This paper presents VeriNC, the first general-purpose tool for verifying INC systems. VeriNC provides a high-level specification language and saves developers 67.2% lines of code on average. To help better understand the behavior of the system, VeriNC offers configurable network environments. VeriNC enables developers to express INC-specific correctness properties. VeriNC translates developer-specified systems into state transition representations, performs model checking to detect potential design risks, and reports violation traces to developers. We propose optimizations for INC-specific scenarios to address the challenge of state space explosion. We modeled INC systems across four application domains and identified design risks with VeriNC in seconds. VeriNC has also been adopted to guide the design of a new INC protocol. Based on our verification experience, we summarize lessons that help develop a correct INC protocol. We further reproduce them in real systems to confirm the validity of our verification result.
Multimodal fusion is studied under hybrid federation, where data are partitioned across samples and feature blocks. The proposed two-dimensional federated smooth multiple-kernel large-margin learning method (2D-FedSMKL) integrates availability-corrected modality scores, group-kernel regularization, and smooth worst-site risk aggregation. For fixed maps and propensities, the objective is convex and smooth. Curvature bounds and exact synchronous block-gradient equivalence are established for binary and multiclass scores, giving a conditional accelerated rate. An oracle-propensity binary risk bound and a propensity-perturbation result are also derived. Simulations and two public activity-recognition benchmarks assess site heterogeneity and modality absence. Worst-site aggregation improves worst-site performance under heterogeneity, including reversed and size-balanced designs. On the benchmarks, validation selects the correction; the selected model is not significantly worse than the strongest reference at the worst site, and group-regularization benefits vary by dataset.
We study \textsc{Capacitated Facility Location}, a fundamental clustering problem, in the setting of uniform opening costs and non-uniform capacities. We give a polynomial-time $(3+ε)$-approximation for this problem. Our algorithm is a multiple-swap generalization of the local search algorithm by Dabas, Garg, and Gupta (2024), who obtained a $3.732$-approximation. The main technical contribution is the analysis of this natural multiple-swap local-search method: variants of this approach have been analyzed previously, but allowing larger swaps requires new grouping and counting arguments. We also show that a multiple-swap local search algorithm provides a $(3+ε)$-approximation for \textsc{Capacitated Facility Location with Outliers}, again in the same setting of uniform opening costs and non-uniform capacities. This is an improvement over the $6.372$-approximation, again by Dabas, Garg, and Gupta. Finally, we show that the factor $3$ is tight for our local-search framework, and that the same multiple-swap idea does not improve the known locality gap for the non-uniform opening-cost setting.
The spatial intelligence of large vision-language models (LVLMs) requires the ability to combine local visual observations into a geometrically consistent representation of the physical world. Many static benchmarks assess isolated spatial judgments, such as relative direction or distance, while interactive embodied evaluations combine perception with exploration, planning, control, and simulator-specific execution. To bridge this gap, we introduce RECONSPATIAL, a benchmark centered on multi-view 3D scene reconstruction across indoor, tabletop, and outdoor environments. Given real multi-view images and target-object queries, LVLMs are required to jointly predict oriented 3D bounding boxes in a shared, camera-anchored metric coordinate frame. Reconstructions are evaluated along two complementary axes: Structure for relative layout and Metric for physical scale and camera-anchored placement. Nine atomic spatial QA tasks, grouped into Geometric Perception and Spatial Relations, probe spatial capabilities involved in joint reconstruction. Offline navigation extends evaluation to path planning. Evaluation of 18 frontier LVLMs reveals a consistent gap between relative scene structure and metric reconstruction; even GPT-6-Astra scores 81.4% on Structure but only 58.7% on Metric. Tracing this gap, diagnostic analyses link atomic spatial capabilities to reconstruction quality and show that relational consistency alone does not ensure metric accuracy. Experiments with 3D map injection further separate scene construction from path planning, revealing how these geometric errors limit navigation success. Finally, spatial fine-tuning yields broad transfer across both spatial and general vision-language benchmarks.
Large language models are typically adapted to a task either by placing knowledge in the input context, which keeps it external and re-encodes it on every call, or by fine-tuning, which internalizes it but demands a costly round of optimization per task. We aim to internalize the knowledge carried by a context directly into model parameters, without per-task optimization and without keeping the context in the input at inference time. To this end, we propose CLIK, a context-conditioned parameter generator that maps a given context to LoRA parameters for internalizing knowledge in a single forward pass through a Transformer encoder with cross-attention, requiring no test-time gradient updates. Once the generated LoRA is inserted into a frozen base model, the model answers downstream queries from the query alone, having internalized the context into its weights rather than re-reading it. Because the adapter depends only on the context, it is generated once and reused for every query on the same document, so the cost of reading that document is amortized across queries. On document question answering, CLIK substantially improves over the no-context base model and outperforms existing hypernetwork-based generators, while remaining behind a base model that reads the context directly, and it carries over to multi-turn dialogue without any multi-turn-specific training. Analysis further shows that the context-dependent part of the generated adapter concentrates in a compact and specific substructure.
We present Youtu-Parsing-Omni, an omni-modal parser that converts documents, images, audio, and video into structured records grounded in space and time, providing a perception layer for agents that read, locate, and cite evidence across modalities. Its design rests on one encoder for every modality and one schema for every task. Youtu-Omni-Encoder, initialized from a pre-trained language model to strengthen text reading, encodes all modalities with shared weights in a unified space-time coordinate system, and a few fusion layers let video frames attend to concurrent audio, bringing cross-modal fusion and temporal alignment into perception itself. OmniSchema unifies the outputs of all ten parsing tasks, allowing a single self-evolving post-training procedure, OmniSchema-Aware On-Policy Distillation (OSAD), to provide a shared token-role-based objective across tasks. In each round, the model is trained on its own rollouts against token-level targets from a reference-conditioned copy of itself, which is then refreshed with the trained weights, so that the parser and its supervision co-evolve. With a single 5 B-parameter checkpoint, Youtu-Parsing-Omni achieves state-of-the-art performance on OmniDocBench v1.6 (96.96 Overall) and leads all open-weight models on OmniParsingBench (75.08 Avg.), with its advantage concentrated on audio and video. It also achieves the best overall chart-parsing score (95.02) and the highest exact chemical-fingerprint agreement among compared systems, and matches a dedicated optical-music model in character-level transcription of typeset sheet music while staying far ahead of general-purpose systems. Code and model weights are publicly available.
Continuous Conditional Generative Modeling (CCGM) aims to synthesize high-dimensional data conditioned on continuously valued scalar labels. However, existing continuous diffusion models face severe data sparsity under imbalanced and long-tailed label distributions, which can lead to visual artifacts and condition inconsistency. Moreover, inference-time classifier-free guidance and dense pixel-space integration introduce substantial sampling overhead, limiting practical deployment. To address these challenges, we propose CAViLD, an efficient latent diffusion framework for continuous conditional generation. CAViLD first constructs a purified condition-aware latent space through density-adaptive vicinal learning, auxiliary semantic regularization, and NIQE-guided negative data augmentation. It then internalizes the conditional guidance direction through an EMA teacher, enabling single-branch conditional inference, and introduces covariance-aware progressive distillation for label-dependent probability-flow ODEs, supporting sampling down to four NFEs. Experiments on RC-49, UTKFace, and Steering Angle demonstrate a favorable trade-off among generation fidelity, continuous condition consistency, and sampling efficiency.
Large language models (LLMs) are advancing in multimodal understanding and reasoning, accelerating medical model development. Traditional Chinese medicine (TCM) uses evidence from the four examinations to determine disease location and nature, differentiate syndromes and guide treatment. This diagnostic process constitutes a complete chain of reasoning. We present Fu-TCM, a multimodal TCM LLM trained on data retained after cleaning and filtering an initial collection of approximately 7.12 million examples derived from classical texts, textbooks, medical images, clinical cases and publicly available datasets. The model was further optimized using Bianzheng-Grounded Policy Optimization (BGPO), which explicitly targets syndrome differentiation through rewards for response format, intermediate TCM reasoning fields and final syndrome predictions. Fu-TCM-27B led all six benchmarks spanning TCM reasoning, text and vision, achieving a macro-average accuracy of 81.01% and surpassing the strongest reference model with complete results across all six benchmarks by 7.13 percentage points. Its largest margin was 11.90 points on Fu-bianzheng. Case-level analyses further showed a positive association between intermediate-field accuracy and final syndrome-selection accuracy in most evaluated models. These findings suggest that TCM syndrome differentiation may be computationally learnable and that structured reasoning supervision can improve performance across TCM tasks.
Standard tokenizers over-fragment domain terms, disrupting morpheme semantics. We characterize this representational misalignment as Structural Knowledge Collapse (SKC), where attention mechanisms fail to reconstruct coherent concepts from fragmented inputs. While existing input-centric solutions like vocabulary expansion address this, they necessitate expensive embedding retraining and neglect internal attention compositionality. To this end, we introduce Morpheme-aware KV-aggregation Attention (MorphKA), a lightweight adapter that dynamically consolidates fragments without tokenizer changes. Bypassing tokenizer retraining, MorphKA employs a dual-phase strategy, Input-Level Morpheme Aggregation (IMA) and Context-Aware KV-Aggregation (AMRF), to stabilize morpheme spans and synthesize higher-order concepts. Experiments on medical and legal benchmarks show MorphKA outperforms vocabulary adaptation baselines by 3.2–4.6%, reaching 7.9% on high-fragmentation terms. Moreover, MorphKA reduces catastrophic interference on general capabilities by 18–22% with ~80% fewer parameters than embedding retraining approaches.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Vision-Language Models (VLMs) have demonstrated impressive capabilities in code generation across various domains. However, their ability to replicate complex, multi-panel visualizations from real-world data remains largely unassessed. To address this gap, we introduce RealChart2Code, a new large-scale benchmark with over 2,800 instances grounded in authentic datasets and featuring tasks with clear analytical intent. Crucially, it is the first benchmark to systematically evaluate chart generation from large-scale raw data and assess iterative code refinement in a multi-turn conversational setting. Our comprehensive evaluation of 14 leading VLMs on RealChart2Code reveals significant performance degradation compared to simpler benchmarks, highlighting their struggles with complex plot structures and authentic data. Our analysis uncovers a substantial performance gap between proprietary and open-weight models and confirms that even state-of-the-art VLMs often fail to accurately replicate intricate, multi-panel charts. These findings provide valuable insights into the current limitations of VLMs and guide future research directions.
尚无 AI 解读，展示原文摘要
cs.CL · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Mobile GUI agents powered by LMMs can perceive screens and follow instructions, yet existing benchmarks largely target short, linear workflows and step-level accuracy, offering limited insight into long-horizon planning and decision-making under branching structures. We present DAC-Bench, a decision-aware benchmark with compositional tasks comprising 830 episodes and 11,345 action steps across 35 applications on Android and iOS. Tasks are organized into Sequential, Conjunctive, Conditional, and Hierarchical structures, reflecting real-world multi-step and branching interaction patterns. To complement standard step-level evaluation, we introduce weighted longest common subsequence to capture length-sensitive progress and decision accuracy for branch correctness. Evaluations across 7 diverse agents show substantial performance degradation compared to prior benchmarks, with success rates dropping below 5% on 6–8 step tasks and branch accuracy averaging 38%, highlighting challenges in conditional decision-making. By exposing these failure modes, DAC-Bench provides a challenging and diagnostic benchmark for advancing decision-aware mobile GUI agents. Our code and dataset are available at: https://github.com/YuqingZhangMirror12/DAC-Bench.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Tao Wu, Jingyuan Chen Zhejiang University, Wang Lin, Jian Zhan, Mengze Li The Hong Kong University of Science and Technology, Fangzhou Jin, Min Zhang East China Normal University, Kun Kuang Zhejiang University 等 9 位作者
Distractors—incorrect yet plausible answer choices in multiple-choice questions (MCQs)—are vital in educational assessments, as they help identify student misconceptions by presenting potential reasoning errors. Current distractor generation methods typically produce shared distractors for all students, ignoring the individual variations in reasoning, which limits their diagnostic effectiveness. To tackle this challenge, we introduce the task of Personalized Distractor Generation, which tailors distractors to each student’s specific cognitive flaws, inferred from their past question-answering (QA) history. While promising, this task is particularly demanding due to the limited number of QA records available for each student, which are insufficient for training, as well as the absence of their underlying reasoning process. To overcome this, we propose a novel, training-free two-stage framework. In the first stage, Monte Carlo Tree Search (MCTS) is used to reconstruct the student’s reasoning process from past errors, creating a student-specific misconception prototype. In the second stage, this prototype guides the simulation of the student’s reasoning on new questions, generating personalized distractors that resonate with their individual misconceptions. Our experiments, conducted on 1,361 students across 6 subjects, demonstrate that this approach outperforms existing methods in generating plausible, personalized distractors, and also effectively adapts to group-level settings, highlighting its robustness and versatility.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表