探索全球前沿学术脉络

01.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2602.09326

Priority-Aware Shapley Value

作者:

Kiljae Lee↗Ziqi Liu↗Weijing Tang↗Yuan Zhang↗

arXiv:2602.09326v2 Announce Type: replace Abstract: Shapley values are widely used for model-agnostic data valuation and feature attribution, yet they implicitly assume contributors are interchangeable. This can be problematic when contributors are dependent (e.g., reused/augmented data or causal feature orderings) or when contributions should be adjusted by factors such as trust or risk. We propose Priority-Aware Shapley Value (PASV), which incorporates both hard precedence constraints and soft, contributor-specific priority weights. PASV is applicable to general precedence structures, recovers precedence-only and weight-only Shapley variants as special cases, and is uniquely characterized by natural axioms. We develop an efficient adjacent-swap Metropolis-Hastings sampler for scalable Monte Carlo estimation and analyze limiting regimes induced by extreme priority weights. Experiments on data valuation (MNIST/CIFAR10) and feature attribution (Census Income) demonstrate more structure-faithful allocations and a practical sensitivity analysis via our proposed "priority sweeping".

阅读与讨论 → 访问原文 →

02.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15207

Controlled Dynamics Attractor Transformer

作者:

Cheng Zhang↗Minnan Luo↗Zesheng Yang↗Ming Li↗Yong-Jin Liu↗Qinghua Zheng↗

arXiv:2606.15207v1 Announce Type: cross Abstract: Transformer architectures have dramatically advanced representation learning and inference in deep models through self-attention mechanisms. In parallel,associative memory (AM) frameworks map representations onto energy landscapes, offering interpretable retrieval mechanisms. However, their continuous-time inference dynamics lack the biological plausibility of classical Continuous Attractor Neural Networks (CANNs). To bridge this gap, we propose Controlled Dynamics Attractor Transformer (CDAT), which couples a mixture von Mises-Fisher (Mo-vMF) attention energy with a Hopfield refinement energy, while augmenting energy descent with a CANN-inspired excitation-inhibition modulation. CDAT instantiates a topology-constrained dynamical system whose couplings encode relational structure among tokens, thereby linking attractor-style dynamics to modern energy-based attention. We further provide a constructive dissipation analysis to formally establish their controlled inference dynamics. Benefiting from these robust and structured dynamics, CDAT achieves state-of-the-art performance across multiple benchmarks in graph anomaly detection and graph classification.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.05922

Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference

作者:

Wenbo Pan↗Shujie Liu↗Chin-Yew Lin↗Jingying Zeng↗Xianfeng Tang↗Xiangyang Zhou↗Yan Lu↗Xiaohua Jia↗

AI agents rely on a harness of skills, tools, and workflows to solve complex problems. Continually improving this harness is essential for adapting to new tasks. However, existing optimization methods typically require ground-truth validation sets, yet such labeled data is difficult to acquire in practical deployment settings. To address this problem, we introduce Retrospective Harness Optimization (RHO), a self-supervised method that optimizes the agent harness using only past trajectories. Specifically, RHO selects a diverse coreset of challenging tasks from past trajectories and re-solves them in parallel. The agent analyzes these rollouts using self-validation and self-consistency, then generates candidate harness updates and selects the most effective one by its own pairwise self-preference. We evaluate RHO across three diverse domains, spanning software engineering, technical work, and knowledge work. Notably, a single optimization round improves the pass rate on SWE-Bench Pro from 59% to 78% without any external grading. Furthermore, our analysis demonstrates that RHO effectively targets prior failure modes. As a result, the optimized harness alters the agent's behavior patterns and sustains higher accuracy during long-horizon sessions.

阅读与讨论 → 访问原文 →

04.

medRxiv (Medicine) 2026-06-18 DOI: HASH:932d1753dc6f5dae42b4af427c53b4a5

Intra-arterial recombinant human TNK tissue-type plasminogen activator (rhTNK-tPA) thrombolysis for acute medium vessel occlusion (MeVO-TNK): Study rationale and design

作者:

Deng↗Liu↗C.-C↗Wang↗Y.-H↗Ao↗D.-H↗Huang↗Xie↗Zhang↗Kong↗Q.-Q↗…

Background The optimal management of acute ischemic stroke caused by medium vessel occlusion (MeVO) remains uncertain. Recent randomized trials have failed to demonstrate a clear benefit of endovascular therapy in this population, whereas intra-arterial thrombolysis (IAT) has emerged as a biologically plausible alternative. However, prospective evidence supporting IAT in MeVO is lacking, and the optimal dosing strategy for stand-alone IAT remains undefined. Aim To preliminarily evaluate the efficacy and safety of intra-arterial tenecteplase (IA-TNK) plus standard medical therapy (SMT) compared with SMT alone in patients with acute MeVO stroke, and to explore a stepwise IA-TNK dosing strategy. Design The MeVO-TNK trial is a multicenter, prospective, randomized, open-label, blinded-endpoint (PROBE), exploratory phase II study. A total of 60 participants with imaging-confirmed MeVO will be randomized 1:1 to receive either IA-TNK plus SMT or SMT alone. Participants presenting beyond 6 hours from symptom onset must demonstrate salvageable penumbral tissue on advanced imaging. Those assigned to the intervention group will receive up to two intra-arterial boluses of tenecteplase (0.0625 mg/kg per bolus), with the second bolus administered based on angiographic assessment of reperfusion and safety. Outcomes The primary efficacy outcome is final infarct volume measured at 72{+/-}24 hours after randomization. Secondary efficacy outcomes include the proportions of patients achieving modified Rankin Scale (mRS) scores of 0-1, 0-2 and 0-3 at 90 days, a shift analysis of the mRS distribution at 90 days, early neurological deterioration, and National Institutes of Health Stroke Scale score at 7 days or discharge. The primary safety outcome is symptomatic intracranial hemorrhage within 24 hours. Conclusions This trial will provide preliminary evidence on the biological efficacy, reperfusion potential and safety of stand-alone IA-TNK for acute MeVO stroke, helping to address an important evidence gap and inform the design of future confirmatory studies.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.16771

GD$^2$PO: Mitigating Multi-Reward Conflicts via Group-Dynamic reward-Decoupled Policy Optimization

作者:

Haotian Liu↗Yihao Liu↗Jingwei Ni↗Siyuan Huang↗Xinpeng Liu↗Pengyu Cheng↗Jiajun Song↗Ruijin Ding↗Junfeng Li↗Zhechao Yu↗Mengyu Zhou↗Hongteng Xu↗…

arXiv:2606.16771v1 Announce Type: new Abstract: As LLMs advance, post-training reinforcement learning (RL) increasingly relies on multi-dimensional rewards to cultivate comprehensive capabilities. This shift demands new algorithms capable of optimizing diverse and potentially competing objectives simultaneously. To address this, existing methods such as Group reward-Decoupled Policy Optimization (GDPO) decompose the overall score into independent reward groups, then compute the RL loss separately within each group. However, this strategy still encounters multi-reward conflicts: a single rollout can yield positive advantages on certain reward dimensions but negative ones on others, causing opposing signals to cancel each other out during aggregation, further hindering RL training efficiency. Inspired by Dynamic sAmpling Policy Optimization (DAPO), which improves RL training efficiency by filtering out ineffective rollouts with near-zero advantages, we propose Group-Dynamic reward-Decoupled Policy Optimization (GD$^2$PO). Specifically, GD$^2$PO employs a conflict-aware filtering mechanism to mask out rollouts suffering from severe reward-wise disagreement. By preventing conflicting signals from canceling each other out, this masking strategy preserves and enhances the magnitude of effective RL advantages, thereby significantly accelerating learning efficiency. Furthermore, we introduce query-level reweighting to dynamically adjust the update intensity of each query based on its overall reward consensus. Experiments on various multi-reward scenarios, including tool calling and human preference alignment, demonstrate that GD$^2$PO consistently and significantly outperforms existing baselines. The code is available at https://github.com/Qwen-Applications/GD2PO.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2504.11775

Discrimination-free Insurance Pricing with Privatized Sensitive Attributes

作者:

Tianhe Zhang↗Suhan Liu↗Peng Shi↗

arXiv:2504.11775v3 Announce Type: replace-cross Abstract: Fairness has become an important concern in insurance pricing as insurers increasingly rely on machine learning models to predict expected losses. At the same time, regulatory and privacy constraints often restrict insurers' ability to access or use sensitive attributes such as gender or race. Recent actuarial research addresses fairness in this context through the concept of the discrimination-free premium, which removes both the direct and indirect effects of sensitive attributes while preserving actuarial consistency. However, implementing this approach typically requires access to the sensitive attributes themselves, which may not be available in practice. This paper studies the estimation of discrimination-free insurance premiums when sensitive attributes are observed only in privatized or noise-perturbed form. We consider a multi-party data setting in which insurers observe non-sensitive attributes and outcomes, while a trusted third party holds privatized sensitive attributes generated through a privacy mechanism. Within this framework, we develop statistical methods for estimating discrimination-free premiums using only the privatized attributes. We study two settings of practical relevance: when the privacy mechanism is known and when its noise level is unknown. For both cases, we establish theoretical guarantees for the proposed estimators. Numerical experiments and empirical applications demonstrate that the proposed approach enables fair insurance pricing while respecting privacy and regulatory constraints.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.12871

DailyReport: An Open-ended Benchmark for Evaluating Search Agents on Daily Search Tasks

作者:

Jingxuan Han↗Wei Liu↗Mingyang Zhu↗Youpeng Wang↗Ziwen Wang↗Lin Qiu↗Xuezhi Cao↗Xunliang Cai↗Zheren Fu↗Licheng Zhang↗Zhendong Mao↗

arXiv:2606.12871v1 Announce Type: new Abstract: Search Agents (SAs) typically leverage large language models (LLMs) to support complex information-seeking tasks by autonomously exploring web sources and synthesizing information into comprehensive responses. For SAs evaluation, prior benchmarks mainly focus on specialized tasks that are unlikely to arise in real-world user scenarios. Moreover, their reliance on coarse task-level rubrics often limits evaluation interpretability. To bridge this gap, we introduce DailyReport, an open-ended benchmark to evaluate SA capabilities on daily search tasks. It contains 150 open-ended tasks with 3,546 associated rubrics, capturing widely discussed and timely information demands of real-world users. Each task is decomposed into subtasks and evaluated with cascade rubrics across disentangled dimensions. Through cascade performance attribution and user-centric aggregation, we derive highly interpretable scores for each dimension, along with a user preference score. Our results on 17 agentic systems show that current systems still fall short of users' expectations. To facilitate future research, our dataset and code are made publicly available at https://github.com/AGI-Eval-Official/DailyReport.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.16836

Does Traversal Order Matter? A Systematic Study of Tree Traversal Methods in Transformer Grammars

作者:

Zongru Liu↗Pengyu Ji↗Pengcheng Wang↗Kewei Tu↗

Transformer Grammars (TGs) enhance language modeling by incorporating syntactic tree structures. Despite the potentially significant impact on model performance of how syntactic trees are linearized in TGs, existing studies rely solely on Depth-First Traversal (DFT) for linearization. In this paper, we expand the traversal design space by exploring Breadth-First Traversal (BFT) and a novel hybrid traversal strategy, Production-Rule Traversal (PRT), which combines the structural lookahead of BFT with the early lexical generation of DFT. We integrate these traversal methods with varying tree configurations and masking strategies, and empirically evaluate their performance on language modeling, syntactic generalization and summarization. We reveal the inherent trade-offs between nested composition and global lookahead, providing actionable recommendations for designing task-aware Transformer Grammars.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15225

Edu-Theater: A Data-Efficient Agent Framework for Scalable Learner Behavior Simulation through Staging Roll-Call

作者:

Weibo Gao↗Qi Liu↗Linan Yue↗Zheng Zhang↗Yichao Du↗Fangzhou Yao↗Ao Yu↗Zhenya Huang↗Shijin Wang↗

arXiv:2606.15225v1 Announce Type: cross Abstract: Large-scale learner-task interaction data are crucial for intelligent educational systems but are costly to collect and constrained by privacy and learner engagement. Learner simulators play a critical role in simulating scalable learner behavior without the need for continuous involvement of real learners. However, existing methods are predominantly individual-centric, pairing a simulator with each learner to iteratively infer latent knowledge states from dense interaction histories, which is both data- and computation-intensive, and fragile in cold-start scenarios. We propose a cohort-aware roll-call simulation paradigm that first constructs cohort-level proficiency priors and refines individual learner states through a small number of targeted diagnostic queries. Based on this paradigm, we introduce Edu-Theater, an LLM-powered agent system that performs cohort-aware learner simulation via a teacher agent and retrospective roll-call probing over learner logs. Edu-Theater enables scalable future behavior simulation without the need for dense per-learner histories. Experiments on two real-world datasets demonstrate that Edu-Theater achieves higher simulation accuracy with significantly fewer LLM calls, producing synthetic data that enhances downstream applications such as adaptive testing.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2606.12258

Bridging Day and Night: Unsupervised Cross-Domain Re-Identification with Synergistic Prompt and Prototype Learning

作者:

Jiyang Xu↗Rui Liu↗Hang Dai↗

Cross-domain day-night re-identification (ReID) is fundamentally challenged by the substantial visual appearance discrepancies between daytime and nighttime scenes. Existing fully supervised methods rely heavily on labor-intensive annotations, which are costly and exhibit limited generalization across domains. In this work, we investigate unsupervised day-night ReID and propose a novel framework that synergistically combines prompt learning and prototype-based representation learning to associate identities across domains without requiring manual labels. Our approach follows a progressive two-stage training strategy. In the first stage, we exploit the vision-language model to generate instance-specific textual prompts in an annotation-free manner. We employ an instance-level alignment mechanism to embed visual features and textual prompts into a unified semantic space, aligning unlabeled day/night images with learnable prompts via instance-aware dynamic-bias adaptation. In the second stage, we construct domain-specific prototype memory banks and introduce two complementary modules: i) an intra-domain identity association module to enhance feature discriminability within each domain, and ii) a cross-domain prototype matching module to reliably identify positive and negative prototype pairs, thereby establishing robust identity correspondences across day and night. Extensive experiments on public benchmarks validate the effectiveness of our method. Under the unsupervised setting, our framework attains Rank-1 accuracy comparable to state-of-the-art fully supervised methods.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.18543

CEO-Bench: Can Agents Play the Long Game?

作者:

Haozhe Chen↗Karthik Narasimhan↗Zhuang Liu↗

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

阅读与讨论 → 访问原文 →

12.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2605.20436

Lighting-aware Unified Model for Instance Segmentation

作者:

Qisai Liu↗Alloy Das↗Zhanhong Jiang↗Joshua R. Waite↗Aditya Balu↗Adarsh Krishnamurthy↗Soumik Sarkar↗

Foundation models like the Segment Anything Model (SAM) demonstrate impressive zero-shot generalization but frequently degrade under diverse real-world illumination, particularly for instance segmentation. In this work, we address this limitation by developing Lighting Convolutional-Attention (\lca{)}, an adapter module that enhances segmentation robustness without fine-tuning the heavy backbone. \lca{} employs a dual-branch architecture to process RGB features alongside contrast maps, enabling physically motivated sensitivity to structural changes rather than illumination artifacts. We optimize \lca{} through a pairwise training strategy, introducing a targeted loss term that explicitly penalizes discrepancies between clean images and their corresponding illumination variants. To evaluate and support this architecture, we conduct a comprehensive empirical study across multiple existing benchmarks and present a novel Unity-based synthetic dataset specifically designed to accurately replicate complex real-world lighting conditions. Extensive experimental results demonstrate that our approach successfully bridges the domain gap, delivering superior lighting-robust segmentation.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.17077

Comprehensive pKa Data Augmentation from Limited Real Data through an Engineered Models-Quantum Framework

作者:

Wang Rui↗Liu Dinghao↗

arXiv:2606.17077v1 Announce Type: cross Abstract: Proton dissociation constants (pKa) are critical for functional molecule discovery and molecular modeling. Building on iBonD, the largest experimental pKa database established, we and other researchers have developed several methods including machine-learning-based empirical prediction and high-accuracy energy calculations. Despite this foundation, the rapid augmentation of high-quality pKa data remains fundamentally constrained. As part of this work, we performed large-scale regression-based pKa prediction on unlabeled molecular datasets using a collection of extensively optimized machine-learning models. The results indicate that, since the feature distributions of unlabeled molecular datasets, the pKa data distribution approximates normality, with extreme scarcity of tail-region samples. Although such augmentation is highly valuable for improving overall data availability and predictive modeling, it remains insufficient for efficiently discovering molecules with broad-spectrum pKa properties. To address this, we explore the targeted generation of molecules with sparse pKa properties from the vast chemical space. Given that traditional continuous latent space VAE-RNN methods for molecular generation suffer from insufficient stability and fail to demonstrate clear advantages in complementing sparse data, we design and implement a quantum-assisted sparse-pKa molecular generation. Feasibility is validated on a simulated quantum annealer, and superior extreme-value sampling is further achieved on physical coherent Ising machines (CIMs). (to be continued)

阅读与讨论 → 访问原文 →

14.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2605.05983

Towards Steering without Sacrifice: Principled Training of Steering Vectors for Prompt-only Interventions

作者:

Yuntai Bao↗Qinfeng Li↗Xinyan Yu↗Ge Su↗Wenqi Zhang↗Liu Yan↗Haiqin Weng↗Jianwei Yin↗Xuhong Zhang↗

arXiv:2605.05983v2 Announce Type: replace Abstract: Recently, steering vectors (SVs) have emerged as an effective and lightweight approach to steer behaviors of large language models (LLMs), among which fine-tuned SVs are more effective than optimization-free ones. However, current approaches to fine-tuned SVs suffer from two limitations. First, they require careful selection of steering factors on a per-SV basis to balance steering effectiveness and generation quality at inference time. Second, they operate as full-sequence SVs (FSSVs), which can sacrifice generation quality regardless of factor selection due to excessive intervention on the model generation process. To address the first limitation, we propose joint training of steering factors and directions, such that post-hoc factor selection is no longer required. Using neural network scaling theory, we find that moderately large initialization sizes and learning rates for steering factors are essential for stability and efficiency of joint training. To tackle the second limitation, we draw inspiration from representation fine-tuning and introduce Prompt-only SV (PrOSV), an SV that intervenes only on a few prompt tokens. Our empirical results show that PrOSV outperforms traditional FSSVs on AxBench when using our joint training scheme. We also find that PrOSV achieves a better tradeoff between general model utility and adversarial robustness than FSSV.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.AI) 2026-06-25 DOI: arXiv:2606.22027

RARM: Confidence-Gated Progress Reward Modeling for RL in Manipulation

作者:

Pengzhi Yang↗Xinyu Wang↗Pengyu Jing↗Kehan Wen↗Yiduo Qu↗Zhenhao Huang↗Minghao Fu↗Xin Liu↗Yaheng Shen↗Fan Shi↗

arXiv:2606.22027v2 Announce Type: replace-cross Abstract: Reinforcement learning for robot manipulation is often bottlenecked by reward design, especially in long-horizon tasks: sparse success rewards provide weak supervision, while hand-crafted dense rewards are tedious to design and generalize poorly across tasks. Progress-based reward models offer a promising alternative by estimating how far an observation has advanced toward task completion, but existing approaches often require task-specific demonstrations or progress labels, and can assign high rewards to visually plausible but physically incorrect states. We introduce the Reference-Anchored Reward Model (RARM), a lightweight visual comparator that converts a single successful demonstration into a dense, progress-aware reward. RARM is trained once on general-purpose videos with a contrastive temporal objective, requiring no robot-specific data, task-specific reward labels, or per-task reward engineering. At deployment, RARM matches rollout clips to reference clips and rewards only confident forward progress, suppressing uncertain matches that may otherwise produce false-positive rewards. Across 9 simulated manipulation tasks from LIBERO and MetaWorld and 4 real-world tasks, RARM achieves the best overall success rates in subsequent RL training, with particularly large gains on long-horizon tasks such as cloth folding, where unreliable progress estimates are especially harmful.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2501.00826

LLM-Powered Multi-Agent System for Automated Crypto Portfolio Management

作者:

Yichen Luo↗Yebo Feng↗Jiahua Xu↗Paolo Tasca↗Yang Liu↗

arXiv:2501.00826v3 Announce Type: replace-cross Abstract: Cryptocurrency portfolio management requires the fusion of heterogeneous multi-modal signals, including structured price and on-chain time series, unstructured news text, and technical indicators, under high-volatility and real-time constraints. While deep learning approaches show predictive capability, their opacity limits practical adoption, and single large language model (LLM) agents struggle to process the breadth of modality-specific inputs needed for robust decision-making. We propose a multi-agent system (MAS) framework in which three modality-specialised agents, a Crypto Agent for market dynamics, a News Agent for weekly news sentiment, and a Trading Agent for signal fusion and portfolio execution, decompose the task across three communication architectures: hierarchical, collaborative, and debate. We evaluate four capability configurations: zero-shot, chain-of-thought (CoT), retrieval-augmented generation (RAG), and skill-augmented. In a 52-week backtest over calendar year 2025 across the top 15 L1 blockchain native cryptocurrencies by market capitalisation as of January 2025, the best configuration, Hierarchical (Skill), achieves a cumulative return of 133.52% and a Sharpe ratio of 1.502, outperforming single-agent variants, passive benchmarks, and deep learning baselines. An ablation study identifies the Crypto Agent as the most critical component, with its removal reducing cumulative return by 42.57 percentage points. A cross-model comparison further shows that MAS outperforms the single-agent baseline under GPT-4o, GPT-5, and Claude Sonnet 4.5, suggesting that the benefit of multi-agent coordination is model-agnostic. Unlike black-box deep learning models, every portfolio decision is traceable to explicit agent reasoning, offering an interpretable and effective approach to multi-modal cryptocurrency portfolio management.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18810

Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards

作者:

Yingyu Shan↗Yuhang Guo↗Zihao Cheng↗Zeming Liu↗Xiangrong Zhu↗Xinyi Wang↗Jiashu Yao↗Wei Lin↗Hongru Wang↗Heyan Huang↗

arXiv:2606.18810v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in training LLMs for reasoning tasks, but representative methods such as GRPO assign uniform credit across all tokens, wasting gradient on routine tokens while under-crediting pivotal reasoning steps. Existing token-level credit assignment methods require resources beyond the model's own rollouts. GRPO variants rely on process reward models or ground-truth answers. Knowledge distillation assigns credit through per-token divergence but requires external teachers (On-Policy Distillation) or privileged information (On-Policy Self Distillation). However, these dependencies limit applicability in the pure RLVR setting. We observe that conditioning the model on its own verified trajectories induces a measurable per-token KL divergence between the original and conditioned distributions, and prove that distilling from a self-teacher constructed by verified trajectories leads to infeasible weighted-average solutions when multiple verified trajectories exist. We propose SC-GRPO (Self-Conditioned GRPO), which uses KL divergence mentioned before as a multiplicative weight on GRPO gradients. Across five benchmarks spanning math, code, and agentic tasks, SC-GRPO consistently outperforms 8.1% over GRPO and 5.9% over DAPO with stronger OOD performance. Moreover, SC-GRPO achieves higher performance than OPD.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2506.08473

AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin

作者:

Shuo Yang↗Qihui Zhang↗Yuyang Liu↗Xiaojun Jia↗Kunpeng Ning↗Jiayu Yao↗Jigang Wang↗Hailiang Dai↗Yibing Song↗Li Yuan↗

arXiv:2506.08473v4 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) improves performance but introduces critical safety vulnerabilities: even minimal harmful data can severely compromise safety measures. We observe that perturbations orthogonal to the alignment direction - defined by weight differences between aligned (safe) and unaligned models - rapidly compromise model safety. In contrast, updates along the alignment direction largely preserve it, revealing the parameter space as a "narrow safety basin". To address this, we propose AsFT (Anchoring Safety in Fine-Tuning) to maintain safety by explicitly constraining update directions during fine-tuning. By penalizing updates orthogonal to the alignment direction, AsFT effectively constrains the model within the "narrow safety basin," thus preserving its inherent safety. Extensive experiments on multiple datasets and models show that AsFT reduces harmful behaviors by up to 7.60%, improves task performance by 3.44%, and consistently outperforms existing methods across multiple tasks.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.12837

LoHoSearch: Benchmarking Long-Horizon Search Agents Beyond the Human Difficulty Ceiling

作者:

Jiarui Zhao↗Rongzhi Zhang↗Lingchuan Liu↗Hao Yang↗Xunliang Cai↗Xi Su↗

Search agent benchmarks exemplified by BrowseComp have rapidly saturated over the past year, with the strongest models surpassing 90% accuracy. Since these benchmarks are predominantly human-authored, annotators lack a global perspective on entity statistics and cannot systematically maximize search space size and structural complexity. This creates a difficulty ceiling that is hard to break. To address this, we introduce LoHoSearch (Long-Horizon Search Agents), a challenging benchmark comprising 544 human-verified questions across 11 domains. LoHoSearch is constructed via an automated pipeline built upon a knowledge graph covering over 7 million Wikipedia entities, which selects relations with large search spaces and assembles them into structurally complex questions with KG-verified unique answers. Our evaluation demonstrates that even the strongest model achieves only 34.74% accuracy, and existing context management strategies (best +6.8%) yield far smaller gains than on prior benchmarks. LoHoSearch provides a more demanding standard for evaluating long-horizon reasoning and context management in search agents.

阅读与讨论 → 访问原文 →

20.

bioRxiv (Bioinfo) 2026-06-17 DOI: HASH:4c6766f4a2fb3e9a822c905b569d02eb

DNA-binding specificity recognition from predicted homologous protein-DNA structures

作者:

Zeng↗Zou↗Li↗Liu↗Xu↗Wang↗Peng↗

Predicting protein DNA-binding specificity is essential for understanding gene regulation and disease mechanisms. Existing deep learning methods typically infer specificity from a single protein-DNA complex structure, which limits their ability to capture the diverse geometric patterns underlying protein-DNA recognition. Homologous protein-DNA interfaces provide complementary structural evidence and richer geometric features related to interatomic interactions. To address the limited diversity and coverage of experimentally determined complexes, we constructed a large-scale library of predicted homologous protein-DNA complex structures. Building on this resource, we propose HomoDSP, a template-retrieval-based framework for accurate DNA-binding specificity prediction. Benchmark evaluations and validation on newly released JASPAR 2026 samples indicate that HomoDSP outperforms existing methods in both accuracy and generalization, with particularly substantial gains on high-error samples. Moreover, this performance is largely retained when AlphaFold3-predicted complex structures are used as input. Template- and residue-level interpretability analyses suggest that HomoDSP improves prediction by focusing on DNA-affinity residues across multiple homologous templates. Finally, universal Protein Binding Microarrays evaluations on AI-designed DNA-binding proteins show that HomoDSP rescues a baseline failure mode in which the baseline method produces incorrect predictions because of training-set bias. Together, these results support the use of homologous template interfaces as informative structural priors for decoding protein DNA-binding specificity.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2510.01663

Shift-Invariant Attribute Scoring for Kolmogorov-Arnold Networks via Shapley Value

作者:

Wangxuan Fan↗Ching Wang↗Siqi Li↗Nan Liu↗

arXiv:2510.01663v2 Announce Type: replace-cross Abstract: For many real-world applications, understanding feature-outcome relationships is as crucial as achieving high predictive accuracy. While traditional neural networks excel at prediction, their black-box nature obscures underlying functional relationships. Kolmogorov–Arnold Networks (KANs) address this by employing learnable spline-based activation functions on edges, enabling recovery of symbolic representations while maintaining competitive performance. However, KAN's architecture presents unique challenges for network pruning. Conventional magnitude-based methods become unreliable due to sensitivity to input coordinate shifts. We propose ShapKAN, a pruning framework using Shapley value attribution to assess node importance in a shift-invariant manner. Unlike magnitude-based approaches, ShapKAN quantifies each node's actual contribution, ensuring consistent importance rankings regardless of input parameterization. Extensive experiments on synthetic and real-world datasets demonstrate that ShapKAN preserves true node importance while enabling effective network compression. Our approach improves KAN's interpretability advantages, facilitating deployment in resource-constrained environments.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.20437

HEPTv2: End-to-End Efficient Point Transformer for Charged Particle Reconstruction

作者:

Siqi Miao↗Shitij Govil↗Jack P. Rodgers↗Mia Liu↗Javier Duarte↗Shih-Chieh Hsu↗Yuan-Tang Chou↗Pan Li↗

arXiv:2606.20437v1 Announce Type: cross Abstract: Charged-particle tracking – reconstructing trajectories from sparse detector measurements – is a fundamental high-energy-physics inference problem and a canonical example of learning under extreme combinatorial ambiguity. At the High-Luminosity Large Hadron Collider (HL-LHC), tracking must remain accurate and efficient despite unprecedented collision densities. Graph neural networks perform strongly, but incur substantial costs from graph construction and processing, while transformer-based approaches rely on auxiliary stages that prevent end-to-end optimization. To address this, we present HEPTv2, an end-to-end point-transformer architecture that reconstructs tracks from detector hits in one trainable pipeline. HEPTv2 combines a locality-aware point encoder with a track decoder that predicts complete trajectories without graph-building, clustering, or filtering. The encoder uses locality-sensitive hashing in detector coordinate space to preserve tracking-relevant geometry while enabling efficient local attention. The decoder resolves ambiguities through sectorized decoding and direct hit-to-track prediction under joint encoder-decoder supervision, allowing the full pipeline to be optimized end-to-end. On TrackML, HEPTv2 achieves 98.6% double-majority tracking efficiency at a 0.8% fake rate, while requiring only $\sim$15~ms inference time and 0.4~GB peak memory per event on a NVIDIA A100 GPU. Latency and memory scale approximately linearly for events with up to $5\times10^5$ hits. HEPTv2 establishes a new state of the art in the accuracy-latency trade-off, improving efficiency by 4.5% over the strongest prior transformer and by 1.1–2.2% over optimized graph-based pipelines, while reducing latency by factors of 7 and 38–52, respectively. These results show end-to-end transformers can deliver the accuracy and efficiency required for real-time particle reconstruction at the HL-LHC.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2604.05527

Prior-guided Fusion of Multimodal Features for Change Detection from Optical-SAR Images

作者:

Xuanguang Liu↗Lei Ding↗Yujie Li↗Chenguang Dai↗Zhenchao Zhang↗Mengmeng Li↗Ziyi Yang↗Yifan Sun↗Yongqi Sun↗Hanyun Wang↗Lorenzo Bruzzone↗

Multimodal change detection (MMCD) identifies changed areas in multimodal remote sensing data, demonstrating significant application value in land use monitoring and urban sustainable development. However, literature MMCD approaches exhibit limitations in both cross-modal interaction and exploiting modality-specific characteristics. This leads to insufficient modeling of fine-grained change information, thus hindering the precise detection of semantic changes. To address these problems, we propose STSF-Net, a framework designed for MMCD between optical and SAR images. STSF-Net jointly models modality-specific and spatio-temporal common features to enhance change representations. Specifically, modality-specific features are exploited to capture genuine semantic change signals, while spatio-temporal common features are embedded to suppress pseudo-changes caused by differences in imaging mechanisms. Furthermore, we introduce an optical and SAR feature fusion strategy that adaptively adjusts multimodal feature importance based on semantic priors obtained from visual foundation models. Finally, we introduce the novel Delta-SN6 dataset, the first openly-accessible multiclass MMCD benchmark consisting of very-high-resolution fully polarimetric SAR and optical images. Experimental results on Delta-SN6, BRIGHT, and Wuhan datasets demonstrate that our method outperforms the state-of-the-art by 3.21%, 0.87%, and 1.32% in mIoU, respectively.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.13024

CausalMoE: A Billion-Scale Multimodal Foundation Model for Granger Causal Discovery with Pattern-Routed Heterogeneous Experts

作者:

Bo Liu↗Di Dai↗Jingwei Liu↗Jiarui Jin↗Xiaocheng Fang↗Guangkun Nie↗Hongyan Li↗Shenda Hong↗

arXiv:2606.13024v1 Announce Type: cross Abstract: Granger Causal Discovery (GCD) is fundamental for analyzing temporal dependencies in complex systems. However, existing neural GCD methods predominantly rely on a "one-size-fits-all" paradigm, struggling to capture distribution shifts and dynamic regime changes inherent in real-world time series. This often leads to entangled representations and spurious causal graphs. In this paper, we propose CausalMoE, a billion-scale multimodal Granger causal foundation model that explicitly models patch-level heterogeneity. CausalMoE introduces a Pattern-Routed Mixture of Heterogeneous Experts, which dynamically identifies latent temporal patterns and routes patches to specialized domain experts, effectively decoupling regime-specific mechanisms from shared dynamics. To ensure interpretable graph recovery, we design a Causality-Aware Self-Attention mechanism operating across variables, yielding sparse Granger causal graphs via proximal optimization. Furthermore, CausalMoE is the first to integrate LLMs and VLMs to align numerical signals with textual and visual priors, regularizing causal estimation in complex scenarios. Extensive experiments demonstrate that CausalMoE establishes a new state-of-the-art on fully supervised benchmarks, while effectively generalizing to few-shot settings where traditional methods fail.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.18180

EgoCS-400K: An Egocentric Gameplay Dataset for World Models

作者:

Rongjin Guo↗Dong Liang↗Yuhao Liu↗Fang Liu↗Tianyu Huang↗Gerhard P. Hancke↗Rynson W. H. Lau↗

The shift from video generation to interactive world modeling places new demands on data: beyond captioned videos, world models require temporally aligned video-action-language trajectories grounded in the actions, camera motion, states, and events that drive future scene changes. However, such data is difficult to obtain at scale. Web video datasets offer broad visual coverage but lack executable actions and reliable states; robotic datasets provide action and state supervision but are costly and limited in scene diversity; and existing simulators often lack large-scale human-driven interaction trajectories. In this paper, we introduce EgoCS-400K, a large-scale replay-grounded egocentric Counter-Strike dataset for world models, built from public professional CS and CS2 match demos that preserve human gameplay trajectories and enable parsing, replaying, rendering, and temporal alignment. We extract player states, view directions, movements, keyboard/button inputs, view-angle changes, weapon usage, game events, and round-level context, and render clean first-person videos from the same trajectories. EgoCS-400K contains over 400,000 first-person videos and 10,000 hours of gameplay from more than 1,000 matches and 40,000 rounds, covering 13 maps and 10 player viewpoints per round. It supports a range of interactive visual modeling tasks, including action-conditioned future prediction, state- and event-aware scene rollout, replay-grounded captioning, and agent egocentric action understanding. By connecting visual observations with human actions, camera motion, game states, and events at scale, EgoCS-400K serves as a practical bridge between passive web videos, controllable game simulation, and costly real-world embodied data.

阅读与讨论 → 访问原文 →