AI 速览：提出一个基于 SMT 的可扩展 Lean 证明自动化框架 crush，用去函数化桥接高阶构造与一阶求解器，并支持可扩展的翻译与证明重建。
Lean's rich expressiveness supports higher-order functions, inductive datatypes, and user-defined abstractions, making it challenging to translate proof obligations into first-order Satisfiability Modulo Theory (SMT) queries and reconstruct kernel checked proofs. We present crush, an extensible SMT-backed proof automation framework for Lean. To bridge the gap between Lean's higher-order constructs and the solver's first-order logic, crush uses defunctionalization to encode function values and their applications. We formalize this translation for a supported higher-order fragment and prove its soundness. Moreover, crush provides metaprogramming interfaces for extending both Lean-to-SMT translation and the reconstruction of Lean proofs from solver certificates without modifying the translation pipeline. We implement crush as both a tactic and a backend for other third-party automation systems. We show that across four such use cases that target verification and general proof automation, crush discharges more obligations than the competing backends and reconstructs more kernel-checked proofs than the baselines.
Minyan Luo, Yuxin Zhang, Meng Zhao, Xincan Wang, Fuzhang Wu, Tong-Yee Lee, Oliver Deussen, Fan Tang 等 9 位作者
An outstanding creative advertising image should both attract attention and communicate a product's positioning. How to choose a persuasive conceptual bridge before rendering begins is challenging for advertising generation. We present AdMuse, a skill-guided multi-agent framework that distills high-quality advertisements into reusable creative skills for cross-domain advertising strategy. Rather than retrieving isolated exemplars, AdMuse abstracts recurring bridge patterns into a skill library that can guide new product briefs. At generation time, AdMuse coordinates skill routing, multi-candidate ideation and selection, and VLM-guided visual refinement: diverse skills propose alternative concepts, relative judgment selects the most promising direction, and vision-language feedback helps realize the selected intent in the final image. This design treats advertising creativity as a structured decision process rather than a single prompt-writing step. Experiments across diverse product and brand positionings show that AdMuse produces visually compelling advertisements that faithfully communicate product positioning.
Ruijie Du, Hao Chen, Xin Zhang, Dongjing Wang, Ze Zhang, Xudong Shen, Runze Wu, Dongjin Yu
In multi-behavior recommendation, auxiliary behaviors such as clicks, add-to-cart, and purchases can provide richer supervisory information for predicting target behaviors. Although existing graph and hypergraph methods are capable of modeling high-order relationships among users, items, and behaviors, they still have limitations in heterogeneous semantics, user-specific weighting, and sequence dependency modeling. While standard Transformers excel at sequence modeling, their shared feedforward mapping struggles to accommodate the differentiated requirements of heterogeneous latent patterns in multi-behavior scenarios. To address this, this paper proposes the Personalized Hypergraph-enhanced Kolmogorov-Arnold Network Transformer (PHKT). Specifically, we design a personalized dynamic hypergraph module that performs behavior-aware weighting of item similarities based on users' historical behavior sequences to capture user-specific heterogeneous high-order relationships. Meanwhile, a Transformer is used as the temporal backbone to model the evolution of short- and long-term preferences, and KAN is introduced to replace the traditional MLP in the feedforward network to enhance fine-grained modeling capability for nonlinear responses to different latent patterns. Experiments on three real datasets, Tmall, RetailRocket, and IJCAI, show that PHKT consistently outperforms nine strong baseline models across multiple evaluation metrics, demonstrating its effectiveness in multi-behavior preference modeling and target behavior prediction.
The ability to navigate outdoors safely and independently is crucial yet challenging for people with low vision (PLV). While various augmented reality (AR) systems for low vision have been designed and evaluated in ideal lab environments, no research has investigated their real-world feasibility and challenges. We present NavSight, a mobile AR application that assists PLV in outdoor navigation by recognizing important outdoor objects (e.g., curb, vehicle) and rendering real-time visual augmentations. Through a seven-day diary study with 12 PLV in real-world settings, we characterize the impact of NavSight on scene perception, users' configuration strategies on what objects to augment and how to augment them across scenarios, how users made sense of and responded to recognition errors, and the social acceptability of using NavSight in public. We further identify environmental factors affecting recognition, such as weather conditions, lighting and shadows, and nonstandard road markings and textures, as well as usability issues in daily use. We discuss these real-world challenges and derive design implications for future AI-powered assistive AR systems for outdoor use.
Linear attention and state space models (SSMs) offer efficient alternatives to softmax attention by maintaining a fixed-size recurrent state, but this design requires careful management to preserve useful historical associations and limit interference. The delta rule helps reduce interference through correction of the value associated with each key, but it does not explicitly account for how related value features are distributed across the state. We observe that a state $\boldsymbol{S}\in\mathbb{R}^{d_k\times d_v}$ can be viewed as a bank of $d_k$ addresses storing $d_v$-dimensional values. While a key-side read $\boldsymbol{S}^\top\boldsymbol{k}$ retrieves the value associated with $\boldsymbol{k}$, a value-side read $\boldsymbol{S}\boldsymbol{e}$ aggregates addresses whose stored value features match the selector $\boldsymbol{e}$. Based on this observation, we propose Dual DeltaNet (DDN), which extends Kimi Delta Attention (KDA) with a two-sided delta rule. The key-side delta rule reads with the current key to correct its associated value, while the complementary value-side delta rule reads with selected features of the current value to reorganize the addresses it occupies. We derive a chunkwise parallel training algorithm and a rank-2 recurrence that increases arithmetic intensity during inference. Compared with KDA, GDN-2, and Mamba-3, DDN achieves the strongest overall performance across language modeling, zero-shot downstream tasks, and retrieval, while incurring modest training and inference overhead relative to KDA. Code: https://github.com/ReichtumQian/DualDeltaNet
Reinforcement learning (RL) has substantially improved the ability of large language model (LLM) agents to interact with environments and solve multi-turn tasks. However, effective agentic RL remains challenging: sparse outcome-only rewards provide limited guidance for assigning credit to individual steps within long interaction trajectories. Existing approaches often introduce dense intermediate supervision, such as process reward models or auxiliary self-supervised signals, which increases supervision and tuning complexity and may limit generalization across tasks and domains. We present AEM, a supervision-free credit assignment method that adaptively modulates entropy dynamics during RL training to improve the exploration-exploitation trade-off. Since in agentic RL the environment is typically affected by a complete response, rather than an individual token, our analysis lifts entropy dynamics from the token level to the response level, aligning uncertainty estimation with the effective action granularity of LLM agents and reducing sensitivity to token-level sampling noise. We further show that entropy drift under natural-gradient updates is governed by the interaction between the sampled-response advantage and its relative surprisal. Motivated by this result, AEM derives a practical response-level uncertainty proxy and uses it to rescale advantages, leveraging the evolving balance between positive and negative samples to naturally transition from exploration to exploitation. Extensive experiments on ALFWorld, WebShop, and SWE-bench-Verified with models ranging from 1.5B to 32B demonstrate that AEM consistently improves strong RL baselines, including a +1.4\% gain when integrated into a state-of-the-art software-engineering RL training framework.
Continuous visual world simulation requires coupling evolving scene geometry with temporally persistent appearance. We present UniWorld, a unified framework that integrates depth trajectories and reference appearance within a shared video generation model. The central design maintains visual and geometric histories on a common timeline. Noise-aligned overlapping continuation places generated history at the prescribed sampling noise level and commits only newly generated latents. Rolling depth latent state preserves the corresponding geometric controls, incrementally reads newly available geometry, and keeps the conditioning fixed within each sampling window. Together, these mechanisms ensure exact preservation of latent history while bounding the active depth state by the window size. We evaluate continuous generation, paired history interventions, and long-horizon behavior across diverse scene categories. The same generator supports estimated, native, and on-demand simulator depth, while cached and incremental execution paths produce bitwise-identical outputs. Appearance changes and geometric control branches operate through the same interface without modifying committed history. The measured steady-state DiT execution path achieves real-time generation throughput, demonstrating the efficiency of UniWorld for continuous visual world simulation. Project page: https://zephipage.github.io/UniWorld.
Subjective judgments such as offensiveness often vary substantially across individuals, motivating pluralistic modeling approaches that incorporate annotators' socio-demographic information to capture this variation. However, prior findings on the benefits of socio-demographic information for pluralistic modeling are mixed, calling for a systematic analysis of both its effectiveness and the mechanisms through which it improves prediction. In this work, we study $\textbf{when}$ and $\textbf{where}$ socio-demographics benefit pluralistic offensiveness modeling, as well as $\textbf{the role of explicit reasoning}$ in leveraging this information. Across three multi-annotator datasets with prompted and trained LLMs, we first show that demographic gains are small and inconsistent for individual predictions but become clearer at the group and population levels, because aggregation attenuates the idiosyncratic variation that masks small but systematic demographic signals. Second, using a reasoning and prediction format that explicitly decomposes individual judgment into an overall baseline and a demographic-specific deviation, we show that the gains arise from both components: demographic information improves baseline estimation and enables meaningful demographic-specific shifts, and interventions show that better component estimates improve final predictions. Finally, comparing direct demographic conditioning with explicit reasoning about how the text interacts with annotator demographics, we find that reasoning yields more accurate baseline and shift estimates as well as final predictions, whereas conditioning alone rarely produces informative shifts. These results suggest that the mixed evidence in prior work may partly stem from individual-level evaluation, and that the value of socio-demographic information depends on both how it is evaluated and how models are guided to use it.
Self-driving laboratories (SDLs) are laboratory systems that couple experimental planning, automated execution, and measurement feedback in a closed loop. Integrating flexible robot control with the typed application programming interfaces (APIs) and continuous measurements exposed by laboratory instruments remains an execution-interface challenge. To address this challenge, we propose a traceable framework comprising four components: LAM (Lab Action Model), OpenSDL, Safe-SDL, and L3-Bench. LAM is a proposed measurement-conditioned policy architecture that extends vision-language-action paradigms to generate both continuous robot trajectories and typed instrument API calls. OpenSDL is an execution substrate with an initial control implementation, designed to map role-level operations to heterogeneous devices, coordinate execution, and record timestamped causal events. The proposed Safe-SDL runtime gate combines pre-dispatch schema and resource checks with signal temporal logic monitoring during execution, including extended waiting periods. L3-Bench (Level-3 Laboratory Benchmark) specifies an episode-level evaluation protocol covering physical outcomes, timing, reproducibility, safety violations, and fault recovery. Together, these components provide an end-to-end design for linking hybrid action generation, monitored device execution, measurement feedback, and experimental evaluation, addressing coordination and traceability challenges in SDL workflows.
Motivation: DNA data storage offers high information density and long-term stability, but accurate sequence reconstruction remains challenging under limited sequencing coverage and strong insertion, deletion, and substitution (IDS) noise. Existing reconstruction methods mainly rely on local evidence within individual read clusters. When sequencing coverage is low or indel-induced phase shifts become pronounced, such local evidence may be insufficient to distinguish closely competing candidate sequences. Results: We present Cross-Cluster Context-Guided Phase Dynamic Programming (CCP-DP), which uses dataset-level cross-cluster information to complement cluster-local evidence and selectively refines ambiguous provisional consensuses. Under the main benchmark settings, CCP-DP achieved exact reconstruction rates of 95.36%-99.98% and outperformed existing methods on multiple datasets. At $5\times$ coverage, CCP-DP improved exact reconstruction by 6.2-17.5 percentage points over the stronger of BBS and CPL across the tested IDS conditions, while maintaining low reconstruction error and computational overhead. Overall, CCP-DP introduces cross-cluster shared information as a complementary source of evidence for DNA sequence reconstruction under challenging conditions. Availability: Source code is available at https://github.com/ZixinZ3899/CCP-DP.
Zhuohang Li, Yiding Ma, Yu Shang, Lei Jin, Shengyuan Wang, Jianjie Fang, Zhaolu Wang, Xvyuan Liu 等 29 位作者
World models have emerged as a central paradigm for embodied intelligence, enabling agents to predict action-conditioned future and reason about environmental dynamics. However, existing embodied world model benchmarks are still largely confined to vision-only prediction, offline embodied applications, and simulator-based evaluation, making them insufficient for assessing increasingly comprehensive world models. In this work, we introduce WorldArena 2.0, an expanded benchmark that systematically broadens embodied world model evaluation along three dimensions: modality, functionality, and platform. Along the modality dimension, WorldArena 2.0 extends evaluation from vision-only to visuotactile modalities, enabling assessment of multimodal perception and prediction. Along the functionality dimension, it extends beyond policy evaluation and planning to assess world models as interactive RL environments for policy optimization. Along the platform dimension, it moves beyond simulator-only evaluation to a diverse suite of simulated and real-world robotic settings across multiple embodiments. Under a standardized protocol, WorldArena 2.0 comprehensively evaluates perceptual quality, interactive utility, and cross-platform performance, providing a comprehensive testbed for tracking progress toward embodied world models. The project page including codes and demos is available at: https://world-arena.ai/.
General-purpose embodied intelligence requires robots to coordinate diverse skills over long horizons, track task progress, and recover from failures. Specialist policies alone do not ensure task-level reliability, while powerful multimodal agents rely on costly reasoning and external experience that compact models struggle to reproduce. We introduce OmniBrain-0, a lightweight unified embodied agent that coordinates manipulation and navigation through a shared high-level decision model, integrating task understanding, planning, progress tracking, and feedback-driven recovery. Our progressive training framework combines embodied pretraining, domain-specialized agent distillation, and multi-teacher on-policy distillation (MOPD). It distills powerful teachers' interaction experience into manipulation and navigation experts, then consolidates their decision capabilities into OmniBrain-0. Unification therefore occurs within the learned decision model rather than only at the tool interface. We further introduce Rubric-Guided Recursive Self-Improvement (RSI), a data flywheel in which a Meta-Agent turns execution evidence into refined rubrics, step-level reminders, and verified trajectories for domain-expert updates before their reconsolidation into OmniBrain-0 through MOPD. We evaluate OmniBrain-0 on LIBERO-Pro, LIBERO-Plus, RoboCasa365, RoboTwin 2.0, and R2R-CE Val-Unseen, as well as multiple real-world manipulation tasks. OmniBrain-0 combines strong cross-domain task performance with substantially lower inference and execution overhead than its closed-source teacher, demonstrating efficient transfer and consolidation of embodied capabilities into a compact unified agent.
Social media enables cross-lingual communication, yet the meaning of user-generated content (UGC) is often distributed across text, images, and cultural knowledge, making translation challenging. Existing evaluations typically treat images as optional and assume textual information is sufficient, obscuring whether errors stem from missing visual evidence or inadequate cultural adaptation. We introduce \textbf{Culture-MMT}, a diagnostic benchmark for \textbf{distributed-evidence pragmatic reconstruction} in social-media translation. It contains 498 curated, de-identified UGC instances across 20 domains, categorized into Symbol, Visual, and Hybrid by their required evidence. We also develop a human-aligned domain-specific judge, Judger, and a controlled evaluation framework that systematically varies the evidence available to translators. Across 17 model configurations, real images improve performance by +0.280 on Visual and +0.197 on Hybrid, but only +0.050 on Symbol, while random images provide no comparable gains. Human-authored descriptions further show that jointly dependent cases remain more challenging even when visual facts are explicit. These results characterize culturally effective social-media translation as {meaning reconstruction from distributed evidence}, highlighting visual grounding and cultural-pragmatic adaptation as distinct model bottlenecks.
A camera-controlled video world model must keep a scene consistent when the camera returns to it. Memories that render stored features into the target frame can turn depth and pose errors into ghosting or duplicated structure. Positional transport avoids that resampling by relocating a historical patch's address rather than its content, but assigns full positional precision even to inaccurate projections. We present GLIMPSE, a global-local memory interface with band-wise multi-precision coordinates and geometry-conditioned spectral attenuation to reduce sensitivity to inaccurate projected addresses. Local patch memory supplies view-specific appearance, while recurrent global memory provides scene context. Footprint-guided retrieval selects historical patches under a fixed local read budget. Under matched retrieval and read budgets, GLIMPSE improves geometric correspondence and photometric consistency over deterministic positional transport.
Graph attention networks learn neighbor importance through data-dependent coefficients, but standard layers lack explicit control over unreliable feature dimensions and use fixed sharpness of attention coefficient distributions. This paper proposes gated graph attention and learnable temperature for common graph attention mechanisms. Gated graph attention filters feature or message responses to reduce the influence of unreliable dimensions, while learnable temperature dynamically adjusts the sharpness of the attention coefficient distribution. We conduct experiments on five standard node classification benchmarks and five heterophilic benchmarks. On most of these benchmarks, our two modifications improve upon the corresponding graph attention backbones, and combining them can yield further gains. Controlled noise experiments further verify the behavior of the proposed mechanisms under feature perturbations. Theoretical analysis explains these results by showing that gating improves robustness when only part of the feature coordinates are reliable, while temperature is beneficial when global noise weakens the discriminability of node features.
Zheng Lin, Zhanwei Wang, Yuxin Zhang, Yafei Wang, Ons Aouedi, Zihan Fang, Jinfeng Xu, Jing Yang 等 12 位作者
The proliferation of orbital sensing data and the real-time demands of emerging global services are pushing low Earth orbit (LEO) satellite networks from bent-pipe relays toward intelligent onboard processing. This shift confronts a fundamental tension, where modern artificial intelligence (AI) training paradigms require intensive computation, abundant memory, and stable connectivity, all of which are scarce under the dynamic topologies, intermittent links, and severe size, weight, and power (SWaP) constraints of satellite networks. Addressing this tension demands rethinking AI workflows, from training and inference to the emerging deployment of large language models (LLMs), under a constraint-aware design philosophy. To the best of our knowledge, this paper provides the first survey that jointly covers all three, whereas prior surveys examine these aspects in isolation. We begin by identifying the deployment challenge of satellite intelligence (SI) and deriving design principles for SI. We then examine three advancing paradigms: i) distributed training, where federated learning (FL) and split learning (SL) enable satellite-ground co-training under resource limitations; ii) collaborative inference, which exploits single-satellite, multi-satellite, and satellite-ground architectures to meet real-time service demands; and iii) on-orbit LLM adaptation and serving, which tackles the frontier challenge of deploying LLMs under severe orbital constraints and resource-aware serving. Finally, we identify open challenges and future directions. By bridging the AI and satellite networks, this paper provides a research roadmap for the implementation of space-native AI technologies.
Scaling coding agents requires a continuing supply of executable data for training, benchmarking, and continuous evaluation. Each task must couple a realistic software state with a specification, development tools, and reliable verification. To expand this supply, we present Change2Task, a system grounded in repository history that converts merged pull requests (PRs) into verified tasks on healthy modern revisions of the same repository. It aligns historical evidence with evolved code, reconstructs task states through Patch Reversal, Code Mapping, or Agent Reconstruction, and validates the lifecycle from a healthy base to a task state and a restored state. By deriving multiple tasks grounded in developer evidence from maintained environments, Change2Task provides executable data for coding agent training and evaluation while reducing repeated environment setup, storage, and task construction effort. We evaluate five coding agent task families: Bug Fix, Feature Addition, Test Generation, Application Programming Interface (API) Migration, and Security Repair. Starting from 1,130 source changes eligible for construction, Change2Task achieves 79.6% verified task construction success across these task families. On a matched candidate set, it recovers 29.2% more verified tasks than a construction baseline based on PRs. Historical and reconstructed cases achieve 89.7% aggregate matched outcome agreement under agent evaluation, while reuse of modern bases reduces measured expenditure across the complete pipeline by 10.8%. Four matched studies examine construction stages, semantic review, branch consistency, and resource trade-offs. An industrial deployment further constructs 1,000 tasks from private PR histories and evaluates four models on a fixed 500-task cohort.
Long-video generators increasingly retrieve past visual observations to prevent identity drift. The intuition is compelling: more access to history should make future video more consistent. But an image can be faithful to the past and wrong for the present. Does visual memory always improve the generated story? We investigate this question through VMem-Bench, a two-track diagnostic study. Track-A measures which references are selected from 92 real films (16,548 segments), before generation and without generator confounds. Track-B compares four retrieval policies with no-memory and gold-informed last-seen controls on 30 causally generated stories (2,824 segments) using a shared generator. Retrieval increases entity recall from 0.559 to 0.628-0.693 and improves similarity to past appearances, but decreases precision from 0.977 to 0.915-0.938 and forbidden-entity avoidance from 0.968 to 0.845-0.898. It can also reinforce obsolete appearances after the story changes them. Conversely, high long-gap recall can arise without memory when the prompt itself supplies the appearance; an appearance-stripping analysis exposes this confound. These results distinguish historical fidelity from current-story correctness and show why retrieval relevance or final-video consistency alone does not establish memory utility.
Agent harnesses enable large language models to act through tools, observe the results, and iteratively work toward a task goal. Verification checks and revises agents' work to improve output quality. Yet there is limited guidance on how harnesses should organize this effort. We study verification as an axis of test-time scaling by examining when to intervene, who checks the work, and how checking leads to revision. Our framework spans four layers of the agent lifecycle: initial instructions, mid-turn reminders, completion gates, and independent review. We compare 17 designs across seven frontier coding models on Terminal-Bench (TB) and SWE-bench Verified (SWE), and introduce VisualBench for expert evaluation of visual and interactive artifacts. Initial instructions and execution-time reminders yield modest, model-dependent average gains on the coding benchmarks, without substantially increasing average output token use. Completion gates can yield larger gains but may substantially increase cost. Independent review by a critic offers a more favorable accuracy-cost tradeoff, improving average accuracy by 5.9-9.5 percentage points on TB and 3.9-6.6 on SWE at 1.13-1.25 and 1.00-1.04 times baseline cost, respectively. On VisualBench, independent review achieves net preferences of 13.2-23.8 points over the baseline across its four designs, exceeding the evaluated L0-L2 designs. Additional review rounds or independent critics further improve average TB accuracy by up to 3.5 percentage points. Together, these results provide empirical guidance for verification design in agent harnesses and support independent review as a practical axis of test-time scaling.
The Voynich manuscript is a fifteenth-century book in a script that no one can read. One account holds that its text means nothing and that a scribe made it by copying his own words and changing them a little. The other holds that a real language lies hidden behind a cipher. We write each account as a program that fills the pages of the manuscript, fit every program with the same budget, and check it on statistics the fit never saw. The copying process of Timm and Schinner predicts these statistics far better than any cipher with one key. But ciphers that switch keys between the manuscript's two dialects, or that encode only the word classes of a real text, predict them equally well. Word statistics alone cannot decide. We look for a trace of language that needs no decipherment. In 28 texts in 16 languages the same word pairs keep sharing a line. The manuscript shows this pattern at half the strength of the weakest of these texts. A word code keeps the pattern above the manuscript unless its plaintext has a weak pattern or many words are miscopied. Solvers that decipher control texts find no readable text in the manuscript under a letter cipher, a word code or 28 codes with one letter, letter pair or syllable per word. Word codes of abbreviated Latin, the plaintext their fits prefer, show which word follows which more clearly than the manuscript unless two words in five are miscopied. One cipher remains possible, a nomenclator with a second key whose scribe miscopies more than half of the words, and our solvers cannot exclude it in 9 of 16 languages. Most of the structure a solver finds comes from how the end of one word shapes the start of the next, which reflects how tightly glyphs are bound to each other. Planted messages are found reliably only when they are long, each letter always becomes the same word and these words are adjacent, so other messages could hide.
Large-scale vision, language, and video pretraining has substantially improved the perception and generalization capabilities of robotic manipulation models, but action generation for complex dexterous manipulation remains constrained by the scarcity of robot demonstrations. Limited robot demonstrations must be used to learn both action representations and task-conditioned action distributions, making it difficult to adequately learn action representations and, in turn, limiting the ability of downstream generative models to generate complex dexterous actions. To address this limitation, we propose ARPG (Action Representation Pretraining and Generation), which explicitly separates action representation learning from action generation: we first pretrain an action representation encoder on large-scale human manipulation data. We then freeze the encoder and train a compact generative backbone (130M parameters) to learn task-conditioned action distributions in the encoder's representation space. Experimental results show that ARPG achieves state-of-the-art performance on the DexJoCo benchmark and improves the average success rate on bimanual dexterous manipulation from 10.1% for $π_{0.5}$ to 44.7%. Scaling experiments further show that broader coverage of human manipulation behaviors effectively improves downstream performance. These results indicate that action representation pretraining provides an independent scaling dimension for improving complex dexterous manipulation capabilities.
Xiaowei Yuan, Lei Jin, Haoxin Zhang, Ziyang Huang, Yan Gao, Yiwu, Yao Hu, Jun Zhao 等 9 位作者
Retrieval-augmented generation (RAG) plays a critical role in user-generated content (UGC) platforms, but its effectiveness critically depends on accurate query–document relevance assessment. Despite recent advances in applying large language models (LLMs) to relevance modeling, UGC platforms present unique challenges: 1) ambiguous user intent due to sparse user feedback in RAG scenarios, and 2) asymmetric relevance, where relevance is driven by localized answer-bearing content rather than global query–document similarity. To address these issues, we propose the Reinforced Reasoning model for Relevance Assessment (R³A), which decomposes relevance assessment into intent inference and evidence grounding. R³A leverages auxiliary high-clicked documents to infer latent query intent, and extracts verbatim evidence fragments to ground relevance decisions, reducing noise sensitivity and improving asymmetric relevance modeling. Experimental results demonstrate that R³A substantially outperforms strong baselines on offline benchmarks, while the distilled R³A-1.5B model achieves significant gains in large-scale online A/B testing, effectively balancing performance and practical deployability.
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 6: Industry Track) · 2026 · 正式发表
Enterprise deep research often fails to produce decision-ready reports due to uneven information coverage, context explosion, and premature stopping. We propose a scalable Enterprise Deep Research (EDR) architecture to address these failures. Our system (i) decomposes requests into coverage-driven objectives via outline generation with reflection, (ii) localizes context with dependency-guided execution and explicit information sharing, and (iii) enforces evidence-based completion criteria so agents iteratively collect information until sufficiency conditions are met. We evaluate on an internal sales enablement task and the public DeepResearch Bench benchmark, where our proposed system design achieves the strongest overall performance compared with competitive deep-research baselines. The results show that dependency-controlled context and explicit evidence sufficiency criteria reduce premature stopping and improve the consistency and depth of enterprise research outputs.
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 6: Industry Track) · 2026 · 正式发表
Traditional industrial agents rely on modular pipelines, including Router, Retriever, Planner, Executor, Responder, Reviewer and so on, which inevitably fracture into a labyrinth of ad-hoc patches, leading to cascading errors and high latency. We propose OneModel, an applicable paradigm shift from external workflows to internalized knowledge representation. Unlike modular systems that slice fluid user intents into static steps, OneModel consolidates complex business logic and SOPs directly into the model’s parameters.Through Continual Pre-training (CPT) and logic-compilation SFT, we transform fragmented business rules into the model’s intuitive reasoning within a unified attention space. Deployed in our global financial service system, OneModel effectively breaks the impossible triangle of latency, accuracy, and complexity. Online A/B testing demonstrates end-to-end latency reduction of more than 50% (18.7s \rightarrow 8s) while the Intelligent Resolution Rate (IRR) jumps from 64.3% to 83.3%. The results demonstrate our paradigm OneModel effectively replaces brittle engineering logic with internalized cognitive intuition, offering a scalable and future-proof blueprint for transitioning industrial agents from complex, error-prone workflow to unified model architectures.
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 6: Industry Track) · 2026 · 正式发表
Yixin Xiang Nanjing University of Science and Technology, Yunshan Ma Singapore Management University, Xiaoyu Du Nanjing University of Science and Technology, Yibing Chen Nanjing Pami Intelligent Technology Co., Ltd., Yanxin Zhang NVIDIA, Jinhui Tang Nanjing Forestry University
Document Question Answering (DQA) involves generating answers from a document based on a user’s query, representing a key task in document understanding. This task requires interpreting visual layouts, which has prompted recent studies to adopt multimodal Retrieval-Augmented Generation (RAG) that processes page images for answer generation. However, in multimodal RAG, visual DQA struggles to utilize a large number of images effectively, as the retrieval stage often retains only a few candidate pages (e.g., Top-4), causing informative but less visually salient content to be overlooked in favor of common yet low-information pages. To address this issue, we propose a Multi-Armed Bandit–based DQA framework (MAB-DQA) to explicitly model the varying importance of multiple implicit aspects in a query. Specifically, MAB-DQA decomposes a query into aspect-aware subqueries and retrieves an aspect-specific candidate set for each. It treats each subquery as an arm and uses preliminary reasoning results from a small number of representative pages as reward signals to estimate aspect utility. Guided by an exploration–exploitation policy, MAB-DQA dynamically reallocates retrieval budgets toward high-value aspects. With the most informative pages and their correlations, MAB-DQA generates the expected results. On four benchmarks, MAB-DQA shows an average improvement of 5%-18% over the state-of-the-art method, consistently enhancing document understanding. Codes are available at https://github.com/ElephantOH/MAB-DQA.
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
Large Language Models (LLMs) have revolutionized various fields, yet their training efficiency is heavily reliant on effective data curation. While data selection has been widely studied, the strategic data organization for enhanced training remains an underexplored area, particularly since current LLMs are often trained for only one or a few epochs. This paper systematically explores the influence of data organization on LLM training by reusing pre-computed sample-level scores originally generated for data efficiency, thereby incurring minimal additional computational overhead. We identify and formalize four key guidances for optimizing data organization: Boundary Sharpening, Cyclic Scheduling, Curriculum Continuity, and Local Diversity. Guided by them, we introduce two novel data ordering methods termed STR and SAW. Extensive experiments across different model scales and data sizes, encompassing both pre-training and SFT stages, validate the effectiveness of our summarized guidances. They also demonstrate the robustness of our proposed data ordering methods in enhancing the stability and performance of LLM training.
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
Hengwei Liu, Haoyuan Ma, Qingqing Lyu, Daoxin Zhang, Yao Hu Xiaohongshu, Yongliang Shen Zhejiang University, Yin Zhang Zhejiang University, Weiming Lu Zhejiang University
Long-form outline generation requires satisfying multiple competing objectives simultaneously: outlines must be engaging, well-organized, topically relevant, and comprehensive while maintaining logical consistency across hierarchical structures. Current approaches either rely on expensive multi-turn interactions with large language models or employ procedural refinement pipelines that cannot systematically learn from critique. We present Logic-RL, a framework that transforms critique-guided outline refinement into a learnable policy through reinforcement learning. Our approach constructs refinement trajectories from teacher demonstrations, synthesizes explicit reasoning chains that decompose the critique-revision process, and optimizes a refinement policy using group relative policy optimization with structure-aware rewards. Experiments on FreshWiki and WikiOutline demonstrate that Logic-RL achieves substantial improvements over strong baselines, with the 0.6B model obtaining 79.17% relative gain and the 1.7B model achieving 8.67% improvement in average rubric scores compared to the best existing methods. Further analysis reveals that learned refinement policies generalize across domains and can be iteratively applied, with quality continuing to improve through three refinement rounds before diminishing returns.
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
Yu Fu University of California, Riverside, Chen Luo Amazon, Josef Valvoda Google, Xin Zhang, Xuejing Lei Amazon, Xiao Pan, Hui Liu Amazon, Yue Dong University of California, Riverside
Key-Value (KV) cache compression techniques have improved the efficiency of long-context summarization in Large Language Models (LLMs), but their impact on model hallucination remains underexplored. In this paper, we present the first systematic study of how KV cache compression affects hallucination in long-context summarization, demonstrating that aggressive compression can increase hallucination scores by up to 3.36× compared to the baseline. To mitigate this issue, we propose HalluKV, a decoding-phase strategy that selectively removes generated KV pairs from retrieval heads responsible for retrieving critical information from source context, thereby anchoring their attention on the preserved source information. Our approach maintains computational efficiency while significantly reducing hallucination across multiple models and datasets, achieving up to 5.48 average point reductions on Llama-3-8B-Instruct, enabling more trustworthy long-context summarization.
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
Shiyao Cui, QingLin Zhang, Di Wang, Yida Lu Tsinghua University, Tsinghua University, Zhexin Zhang, Jinhua Gao Institute of Computing Technology, Chinese Academy of Sciences, Jinglin Yang Institute of Information Engineering, Chinese Academy of Sciences, Min He CNCERT/CC 等 10 位作者
Neologisms, emerging terms in meaning or form, can serve as new vehicles for toxic expression, like “田园女” (“country girl”) as a stigmatizing label targeting feminism. Such toxic neologisms appear benign but have evolved into toxic usage in public consensus, posing challenges to moderation systems and remaining underexplored. In this paper, we investigate how to detect implicit toxicity expressed via neologisms. We first propose a taxonomy that captures the origins and consensus-verification criteria of toxic neologisms, followed by the construction of a lexicon spanning widely observed risk categories. To capture toxicity grounded in public consensus, we introduce SeTox, a search-augmented framework that enables static large language models (LLMs) to incorporate real-time web context for neologism toxicity detection. Experiments show that SeTox, even with 3B-scale models, outperforms recent large-scale models, demonstrating its scalability to incorporate real-world knowledge for toxic neologism detection. Disclaimer: this paper has offensive contents that may be disturbing to some readers.
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
Large language models (LLMs) have demonstrated better safety performance in high-resource languages than in low-resource languages. We attribute this issue as a mismatch gap between language-agnostic semantic understanding ability and language dominant safety alignment biased toward high-resource languages. Based on above insights, we empirically identify the semantic bottleneck in LLMs: intermediate layers in which the geometry of model representations is governed primarily by shared semantic content rather than language identity. Then, we propose Language-Agnostic Semantic Alignment (LASA), which anchors safety alignment directly in semantic bottlenecks. Experiments show that LASA substantially improves safety across all languages: average attack success rate (ASR) drops from 24.7% to 2.8% on LLaMA-3.1-8B-Instruct and remains within 3–4% across Qwen2.5 and Qwen3 Instruct models (7B–32B). Besides, our analysis and method offer a representation-level perspective on LLM safety, suggesting that safety alignment requires anchoring safety understanding not in surface text, but in the model’s language-agnostic semantic space.
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