探索全球前沿学术脉络

01.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2601.14288

DeepInflation: an AI agent for research and model discovery of inflation

作者:

Ze-Yu Peng↗Hao-Shi Yuan↗Qi Lai↗Jun-Qian Jiang↗Gen Ye↗Jun Zhang↗Yun-Song Piao↗

arXiv:2601.14288v2 Announce Type: replace-cross Abstract: We present DeepInflation, an AI agent designed for research and model discovery in inflationary cosmology. Built upon a multi-agent architecture, DeepInflation integrates Large Language Models (LLMs) with a symbolic regression (SR) engine and a retrieval-augmented generation (RAG) knowledge base. This framework enables the agent to automatically explore and verify the vast landscape of inflationary potentials while grounding its outputs in established theoretical literature. We demonstrate that DeepInflation can successfully discover simple and viable single-field slow-roll inflationary potentials consistent with the latest observations (with the ACT DR6 results taken as an example) or any given $n_s$ and $r$, and provide accurate theoretical context for obscure inflationary scenarios. DeepInflation serves as a prototype for a new generation of autonomous scientific discovery engines in cosmology, which enables researchers and non-experts alike to explore the inflationary landscape using natural language. This agent is available at https://github.com/pengzy-cosmo/DeepInflation.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11854

Fine-tuning Multi-modal LLMs with ART: Art-based Reinforcement Training

作者:

Michal Chudoba↗Sergey Alyaev↗Petra Galuscakova↗Tomasz Wiktorski↗

There are two main Parameter-Efficient Fine-Tuning (PEFT) techniques for Large Language Models (LLMs). While Low-Rank Adaptation (LoRA) introduces additional weights between the LLM layers, Soft Prompting introduces additional fine-tuning-specific raw tokens to an LLM input. However, both require modification to the computational graphs of precompiled, preoptimized LLMs. As a result, neither is fully supported in high-throughput engines like vLLM. We propose fine-tuning with ART (Art-based Reinforcement Training). The method injects information into a frozen Multimodal Large Language Model (MLLM) by optimizing only its raw visual input, thus enabling the soft-token approach on pre-compiled computational graphs. It relies on backpropagation of gradients back into a plain pixel array and thus supports any fine-tuning objective. Moreover, the optimized visual input can be stylized as task-relevant computational artworks. The approach's effectiveness is confirmed for different sizes of a popular open Qwen architecture and for several textual benchmarks. Specifically, ART reaches accuracy competitive with LoRA across mathematics and structured-tool-use benchmarks.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.17474

AIPatient Arena: EHR-grounded evaluation of large language models in end-to-end clinical consultation workflows

作者:

Jiahui Niu↗Huizi Yu↗Wenkong Wang↗Guangxin Dai↗Jingxian He↗Xiang Li↗Zhiying Liang↗Xinxin Lin↗Kent CY So↗Bryan YP Yan↗Yun Kwok Wing↗Yanqiu Xing↗…

Large language models (LLMs) are increasingly considered for use in clinical consultation tasks, yet most medical evaluations remain static, single-turn, or narrowly outcome-based, limiting their ability to reflect the sequential, uncertain, and interactive nature of real-world care. Here, we propose AIPatient Arena, an EHRs-grounded evaluation framework for assessing the clinical utility of LLMs across eight dimensions of clinical competence. The framework integrates EHR data into patient-specific knowledge graphs, enabling multi-turn physician-patient interactions. We applied AIPatient Arena on a primary cohort of 437 patients and two out-of-distribution validation cohorts of 119 and 67 patients. We observe that LLMs performed well in medical interview questioning skills (QS; mean scores, 4.43-4.99/5), ethical and professional conduct (ET; 4.38-4.93/5), and clarity and transparency of clinical explanations (EX; 3.80-4.72/5). Performance was moderate in information integration (II; 3.19-4.21/5) and medication safety and justification (MS; 3.13-3.78/5), but persistent weaknesses were observed in handling of ambiguous patient responses (HR; 2.57-3.32/5), information coverage (IC; 2.08-3.02/5), and diagnostic accuracy and reasoning (Dx; 2.63-3.55/5). Process-based evaluation revealed recurrent interaction failures, including repetitive questioning, omission of past medical history, and inadequate handling of uncertainty. Richer conversational context improved diagnostic reasoning but yielded limited gains in treatment planning. These findings indicate that final-answer accuracy alone is insufficient for evaluating clinical readiness and highlight the importance of assessing how models gather, interpret, and communicate information throughout a consultation. AIPatient Arena provides an EHR-grounded framework for workflow-oriented pre-deployment evaluation of medical LLMs.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2501.12942

Offline Diffusion Policy for Multi-User Delay-Constrained Scheduling

作者:

Zhuoran Li↗Ruishuo Chen↗Hai Zhong↗Longbo Huang↗

arXiv:2501.12942v2 Announce Type: replace Abstract: Effective multi-user delay-constrained scheduling is crucial in various real-world applications, including embodied AI, instant messaging, live streaming, and data center management, where efficient resource allocation is required among users with diverse delay sensitivities. In these scenarios, schedulers must make real-time decisions to satisfy both delay and resource constraints without prior knowledge of system dynamics, which are often time-varying and challenging to estimate. {Current learning-based methods typically require online interactions with actual systems during the training stage. Therefore, these approaches are often difficult or impractical, as they can significantly degrade system performance and incur substantial service costs.} To address these challenges, we propose a novel offline reinforcement learning-based algorithm, named \underline{S}cheduling By \underline{O}ffline Learning with \underline{C}ritic Guidance and \underline{D}iffusion Model (SOCD), to learn efficient scheduling policies purely from pre-collected offline data. SOCD innovatively employs a diffusion policy, complemented by a sampling-free critic network for policy guidance. By integrating the Lagrangian multiplier optimization into the offline reinforcement learning, SOCD efficiently trains high-quality constraint-aware policies exclusively from available datasets, eliminating the need for online interactions with the system. Experimental results demonstrate that SOCD is resilient to various system dynamics, including partially observable and large-scale environments, and delivers superior performance compared to existing methods.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16532

Dual-Granularity Orthogonal Disentanglement for Generalizable Audio Deepfake Detection

作者:

Zhuodong Liu↗Hugen Lv↗Xiangyu Li↗Chunhong Yuan↗

arXiv:2606.16532v1 Announce Type: cross Abstract: Audio deepfake detectors often fail to generalize across speakers, as they learn speaker-identity features rather than synthesis artifacts, known as implicit identity leakage. Existing methods address this but incur architectural complexity or training instability. This paper proposes a dual-granularity orthogonal disentanglement framework enforcing feature independence at two levels: sample-level cosine orthogonality captures directional decorrelation, while batch-level cross-covariance regularization eliminates linear correlations across embedding dimensions. A curriculum disentanglement schedule progressively strengthens the orthogonality constraint without auxiliary networks or adversarial dynamics. Experiments on ASVspoof 2019 LA, ASVspoof 2021 DF, and In-the-Wild datasets demonstrate that the proposed method achieves 1.35%, 7.88%, and 21.58% equal error rates (EER), respectively, surpassing gradient reversal disentanglement by 2.60% absolute on cross-dataset transfer.

阅读与讨论 → 访问原文 →

06.

arXiv (quant-ph) 2026-06-11 DOI: arXiv:2606.02283

Quantum optimal control of the Dicke manifold in dipolar Rydberg atom arrays

作者:

Ivy Pannier-G\"unther↗Vikas Buchemmavari↗Pablo M. Poggi↗Ivan H. Deutsch↗

arXiv:2606.02283v2 Announce Type: replace Abstract: The ability to engineer and control quantum states of many-body systems is a central challenge in quantum information science. For a register of $N$ qubits, the full Hilbert space dimension grows exponentially as $2^N$, rendering generic state preparation and control infeasible without exploiting structure or symmetry. A particularly important and physically motivated restriction is to the fully symmetric subspace, spanned by the Dicke states, which are simultaneous eigenstates of collective spin $J=N/2$. Ensembles of Rydberg atoms interacting via electric dipoles in two-dimensional tweezer arrays form a promising platform for achieving such control. However, the finite range of dipole-dipole interactions poses a challenge to generating and controlling the Dicke manifold because the Hamiltonian incurs leakage from the computational subspace. To counteract this leakage, we perform quantum optimal control algorithms on a truncated Hilbert space according to our newly developed method of ``irrep distillation'' (IRD), which captures the process by which the symmetric subspace couples to leakage error-spaces, using only linear-scaling Hilbert dimension. We implement gradient ascent pulse engineering (GrAPE) on control schemes with little or no local addressing, to generate resourceful states like Greenberger-Horne-Zeilinger, Dicke, and extremal quantum states. We benchmark each scheme of IRD-GrAPE for its quantum speed limit (QSL), as well as exactly testing pulse fidelities on small system sizes and predicting fidelities using higher-order IRD on larger systems.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.09669

SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks

作者:

Hongcheng Gao↗Hailong Qu↗Jingyi Tang↗Jiahao Wang↗Zihao Huang↗Hengkang Qiao↗Shihong Huang↗Junming Yang↗Yi Li↗Hongyixuan Yuan↗Wenjie Li↗Bohan Zeng↗…

Spatial reasoning is a foundational capability for multimodal large language models (MLLMs) to perceive and operate within the physical world. However, existing benchmarks predominantly rely on passive evaluation (e.g., static VQA) or simulator-specific pipelines, failing to assess general interactive spatial understanding. We introduce SpatialWorld, a unified benchmark designed specifically for evaluating the interactive spatial understanding of multimodal agents in complex real-world tasks. Integrating eight heterogeneous simulation backends under a shared, simulator-agnostic protocol, SpatialWorld features 760 human-annotated tasks across diverse domains (e.g., household routines, travel, social collaboration). Agents must solve tasks under vision-only partial observability, actively gathering egocentric visual evidence and expressing decisions via a unified, text-based action interface native to MLLMs. For reliable evaluation, each task includes a human-validated initial state, a reference trajectory, and a terminal-state verifier. Evaluating 15 advanced agents reveals that robust spatial task solving remains challenging: the strongest model, GPT-5, achieves an average task success rate (TSR) of only 17.4%, while the leading open-source model, Qwen-3.5, reaches 14.1%. Further analysis exposes a clear mismatch between task success and execution efficiency, alongside substantial domain-specific performance variations. These bottlenecks in active exploration and long-horizon planning position SpatialWorld as a rigorous testbed for future spatial agents.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2502.11201

Bridging the Gap: Enabling Natural Language Queries for NoSQL Databases through Text-to-NoSQL Translation

作者:

Jinwei Lu↗Jiawei Lu↗Chen Zhang↗Zhiqian Qin↗Haodi Zhang↗Yuanfeng Song↗Raymond Chi-Wing Wong↗

arXiv:2502.11201v3 Announce Type: replace-cross Abstract: NoSQL databases are core data infrastructure, yet natural-language access to them remains underdeveloped: correct query generation must recover how a non-relational data model represents entities, nested paths, arrays, missing fields, and dynamic keys. This paper studies Text-to-NoSQL, translating natural-language requests into executable NoSQL queries, instantiated with MongoDB aggregation pipelines over schema-less document stores. We present TEND, short for Text-to-NoSQL Dataset, an execution-verified benchmark with 1,210 MongoDB-native tasks across 11 databases. To our knowledge, TEND is the first Text-to-NoSQL benchmark whose database worlds are MongoDB-native by design: experts manually define collection boundaries, nested arrays, optional and sparse paths, polymorphic shapes, and dynamic-key conventions; these worlds are populated with real data and verified through frozen MongoDB execution, so TEND evaluates schema-less document reasoning rather than SQL-to-MQL transfer. We further introduce SAG, a Schema-as-Data Grounding solver that induces path and value grounding from stored-document evidence before bounded MQL generation, execution-grounded repair, and result-consistency selection. Evaluation uses bounded column-tolerant execution accuracy (EXC) as the headline metric, complemented by a graded result-set F1 and a mutually exclusive execution-outcome decomposition. Experiments show that LLMs with strong NL2SQL performance degrade substantially on TEND, validating Text-to-NoSQL as a distinct schema-less document reasoning problem.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11640

TAROT: Task-Adaptive Refinement of LLM-prior Graphs for Few-shot Tabular Learning

作者:

Ruxue Shi↗Yili Wang↗Mengnan Du↗Hangting Ye↗Yi Chang↗Xin Wang↗

arXiv:2606.11640v1 Announce Type: cross Abstract: Few-shot tabular learning provides a cost-effective approach for real-world applications where annotation is costly and collecting sufficient samples for new tasks is difficult. Existing Traditional and LLM-based methods have demonstrated effectiveness in few-shot scenarios. However, traditional methods need additional training on unlabeled or generated data, which incur significant computational overhead. In addition, LLM-based methods that directly feed raw tabular data into LLMs raise privacy and compliance concerns. More importantly, both paradigms largely overlook the semantic relationships between features, which provide structural and semantic prior for constructing a semantic graph. Semantic graph is essential for modeling meaningful feature interactions in few-shot scenarios. In this paper, we propose TAROT, a GNN-based framework that encodes the structural and semantic prior by constructing and refining a task-adaptive semantic graph from this prior, thereby improving predictive performance in few-shot tabular learning. TAROT first encodes heterogeneous tabular data into unified node semantic representations via a Unified Semantic Tabular Node Encoder (USTNE). Then, it prompts LLMs to infer the semantic relationship between features based on the task description and feature names to construct a semantic graph. To mitigate structural noise introduced by the hallucination of LLMs, TAROT introduces Task-adaptive Semantic Graph Refinement that prunes spurious or task-unrelated edges and adds missing task-related ones, aligning the graph structure with the downstream objective. Finally, a GNN performs message passing over the refined graph to capture task-related semantic dependencies for prediction. Extensive experiments on various few-shot tabular learning benchmarks demonstrate the superior performance of TAROT, establishing it as a state-of-the-art approach in this domain.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2606.14691

CORA: Analyzing and bridging thinking-answer gap in Multimodal RLVR via Consistency-Oriented Reasoning Alignment

作者:

Jiayue Cao↗Zhicong Lu↗Xuehan Sun↗Wei Jia↗Hongling Zheng↗Changyuan Tian↗Zichuan Lin↗Wenqian Lv↗Nayu Liu↗

Reinforcement learning with verifiable rewards (RLVR) has successfully elicited the reasoning capabilities of large language models, motivating its extension to multimodal scenarios. Existing methods primarily focus on improving the visual coverage of reasoning traces and mitigating visual hallucinations, but underestimate the semantic inconsistency between the reasoning process and the final answer. In this paper, we delve into thinking-answer inconsistency in RLVR for large vision-language models (LVLMs), showing thorough analyses of rollouts collected throughout Group Relative Policy Optimization (GRPO) training process and post-RLVR evaluation outputs that this issue persists during training and remains present during inference. Motivated by the analysis, we propose Consistency-Oriented Reasoning Alignment (CORA), which introduces thinking-answer semantic consistency into RLVR through a lightweight plug-and-play consistency reward model, and further incorporates Hybrid Reward Advantage Splitting (HRAS) to stably coordinate task and consistency optimization. Extensive experiments across representative multimodal reasoning benchmarks and mainstream LVLMs show that CORA improves task performance while effectively mitigating thinking-answer inconsistency, leading to more faithful reasoning traces.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2603.22766

From Overload to Convergence: Supporting Multi-Issue Human-AI Negotiation with Bayesian Visualization

作者:

Mehul Parmar↗Chaklam Silpasuwanchai↗

arXiv:2603.22766v2 Announce Type: replace-cross Abstract: As AI systems increasingly mediate negotiations, understanding how the number of negotiated issues impacts human performance is crucial for maintaining human agency. We designed a human-AI negotiation case study in a realistic property rental scenario, varying the number of negotiated issues; empirical findings show that without support, performance stays stable up to three issues but declines as additional issues increase cognitive load. To address this, we introduce a novel uncertainty-based visualization driven by Bayesian estimation of agreement probability. It shows how the space of mutually acceptable agreements narrows as negotiation progresses, helping users identify promising options. In a within-subjects experiment (N=32), it improved human outcomes and efficiency, preserved human control, and avoided redistributing value. Our findings surface practical limits on the complexity people can manage in human-AI negotiation, advance theory on human performance in complex negotiations, and offer validated design guidance for interactive systems.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2606.17445

Toward Controllable Catalyst Inverse Design via Large-Scale Autoregressive Pretraining

作者:

Dong Hyeon Mok↗Jonggeol Na↗Seoin Back↗

arXiv:2606.17445v1 Announce Type: new Abstract: Inverse design of heterogeneous catalysts remains challenging because catalyst surfaces exhibit substantial structural complexity with coupled surface-adsorbate interactions across a vast chemical space that is difficult to explore efficiently through conventional screening alone. Although machine learning-based high-throughput screening has accelerated catalyst discovery, its efficiency inevitably declines as the search space grows, motivating the development of generative models that can directly construct catalysts with target properties. Here, we present a conditional catalyst generative model based on the Generative Pretrained Transformer architecture with a numerical embedding layer that enables the generation of catalyst structures conditioned on both categorical and continuous properties within a single autoregressive framework. The model was pretrained on 133 million catalyst structures and subsequently fine-tuned on approximately 460,000 optimized structures with associated categorical properties and binding energies for conditional generation. The resulting model achieved 98% structural validity, 95% optimization validity, and high categorical condition fidelity, with a 93 % joint match rate for adsorbate type and composition. For binding energy conditioning, the match rate of approximately 20% represents a four-fold improvement over the baseline training distribution, and the generated distributions shift systematically toward the target values, enabling a 1.5 to 4-fold improvement in screening efficiency for reaction-targeted catalyst discovery without additional fine-tuning. These results show that large-scale autoregressive pre-training, combined with explicit property conditioning, provides a practical route toward controllable catalyst generation and accelerated catalysts discovery.

阅读与讨论 → 访问原文 →

13.

arXiv (quant-ph) 2026-06-11 DOI: arXiv:2606.11655

Fast Adiabatic Quantum Gates via Hyperfine Intermediate States

作者:

Jiayin Fan↗Xingdong Zhao↗Manqi Zhang↗Fangfang Xie↗Jing Qian↗

arXiv:2606.11655v1 Announce Type: new Abstract: The appeal of adiabatic quantum computing lies in its intrinsic robustness against various technical imperfections, making it attractive for many quantum information applications. However, it faces a fundamental challenge: accelerating the adiabatic operations while preserving adiabaticity within the qubit coherence time. In this article, we propose an electromagnetically induced transparency-based adiabatic CNOT gate protocol which harnesses atomic hyperfine intermediate states (HISs) to speed up the adiabatic evolution. The HISs, naturally-existed in two-photon transitions, often need to be suppressed due to their significant decay errors. In contrast, this paper introduces a novel method that utilizes appropriately chosen HISs not only to enhance the adiabaticity in STAY pathway but also to accelerate the population transfer in TRANSFER pathway. Through pulse optimization, we achieve adiabatic gate fidelities exceeding 0.9991 within 0.3903 {\mu}s in realistic Cs atomic setups. To demonstrate the generality of protocol we further assess the impact of decays from multiple HIS and extend our model to arbitrary number of states, providing a practical route toward fast and robust adiabatic quantum gates in Rydberg-atom platforms.

阅读与讨论 → 访问原文 →

14.

arXiv (quant-ph) 2026-06-12 DOI: arXiv:2512.24225

Entropic order parameters and topological holography

作者:

Hua-Chen Zhang↗Germ\'an Sierra↗Javier Molina-Vilaplana↗

arXiv:2512.24225v2 Announce Type: replace-cross Abstract: We show that the symmetry topological field theory (SymTFT) construction, also known as the topological holography, provides a natural and intuitive framework for the entropic order parameter characterising phases with (partially) broken symmetries. Various examples of group and non-invertible symmetries are studied. In particular, the origin of the distinguishability of the vacua resulting from spontaneously broken non-invertible symmetries is made manifest with an information-theoretic perspective, where certain operators in the SymTFT are excluded from observation.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.04101

UltraEP: Unleash MoE Training and Inference on Rack-Scale Nodes with Near-Optimal Load Balancing

作者:

Xinming Wei↗Chao Jin↗Tuo Dai↗Yinmin Zhong↗Shan Yu↗Chengxu Yang↗Bingyang Wu↗Zili Zhang↗Jing Mai↗Qianchao Zhu↗Zhouyang Li↗Yuliang Liu↗…

arXiv:2606.04101v3 Announce Type: replace-cross Abstract: Large-scale expert parallelism (EP) is becoming pivotal for training and serving frontier MoE models, but it also amplifies device-level expert load imbalance into compute stragglers, token all-to-all bottlenecks, and activation-memory spikes. Existing balancers redistribute experts periodically based on historical load, which becomes unreliable for production deployments with non-stationary load patterns. We present UltraEP, the first exact-load, real-time balancer for large-EP MoE training and serving prefill on rack-scale nodes (RSNs). Leveraging the extended scale-up connectivity among dozens of GPUs within RSNs, UltraEP rebalances every microbatch and layer on critical paths, which requires nontrivial co-design of plan solving and expert replication communication to minimize exposed overhead. To this end, UltraEP eagerly reacts to post-gating load with an efficient quota-driven planner, and executes the resulting irregular expert-state transfers with RSN-native persistent tile streaming and relay-based fan-out mitigation. We evaluate UltraEP in a multi-RSN deployment of up to 256 GPUs, using cutting-edge MoE models from 106B to 671B parameters. Averaged across training and serving, UltraEP achieves 94.3% of the force-balanced ideal throughput, delivering 1.49$\times$ improvement over no-balancing, while reducing the final inter-rank imbalance from 1.30$-$4.01 to 1.01$-$1.04.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.06834

The Dark Regulome: Disentangling Predictability from Regulation in Genomic Foundation Models

作者:

Chahat Baranwal↗Aaditya Baranwal↗Lakshya Nitin Tandon↗

High-grade gliomas integrate into neural circuits through functional synapses with neurons, raising the question of which noncoding elements shape synaptogenic gene expression in tumor cells. The regulatory program written across the dark genome, what we call the $dark regulome$, is the natural substrate to probe, and sequence foundation models offer a zero-shot route through in-silico mutagenesis (ISM); yet likelihood-based scoring is tautologically coupled to local sequence predictability, leaving the regulatory interpretation underdetermined. Across three architecturally distinct foundation models (Caduceus-Ph, HyenaDNA, Enformer) and 30,448 dark genome elements at 92 glioma-relevant loci, we introduce a residualization-and-permutation diagnostic that separates predictability-driven from regulation-driven RIS variance. A sharp 10kb proximal-regulatory horizon survives every control we apply, but the LM-derived element-class hierarchy does not: a six-feature linear baseline matches Caduceus top-decile membership at AUC $= 0.985$. Cross-architecture decomposition cleanly separates a sequence-predictability layer (the two language models co-rank long well-predicted transposable elements) from a regulatory-output layer (Enformer alone retains residual cCRE-discriminative signal), with literally zero overlap between the two top-100 lists. Conservation, brain cis-eQTL, and STRING-PPI cross-checks then anchor what biology survives: top-100 elements across all three models are $3.3\times$ enriched per model for matching brain eQTLs ($p_\mathrm{emp} < 5\times 10^{-3}$), while a tempting transposable-element regulatory layer and a striking NRXN1+NLGN1 protein-pair convergence both fail proper permutation tests once those tests are constructed. We deliver the diagnostic as a general methodological tool for any ISM-based regulatory study.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15333

Replay What Matters: Off-Policy Replay for Efficient LLM Reinforcement Unlearning

作者:

Zirui Pang↗Chenlong Zhang↗Haosheng Tan↗Zhuoran Jin↗Jiaheng Wei↗Zixin Zhong↗

LLM unlearning has emerged as a cost-effective alternative to full retraining for removing hazardous knowledge from pretrained models while preserving general utility. Recent RL-based methods such as RULE reformulate unlearning as learning a refusal behavior, but their on-policy optimization repeatedly samples from the same forget and retain/boundary prompts throughout training. We identify a critical inefficiency in this process: easy cases quickly converge and provide little useful gradient signal, while hard cases near the forget/retain boundary continue to produce low-reward rollouts that are discarded after a single use. To address this issue, we propose ReRULE, an off-policy replay enhancement for reinforcement unlearning. ReRULE stores low-reward hard-case rollout groups in a replay buffer during early GRPO training and reuses them in later stages through importance-sampled off-policy updates, redirecting computation toward boundary cases that still require learning. Theoretically, we show that ReRULE yields a tighter hard-case convergence bound than pure on-policy RULE. Empirically, ReRULE improves MUSE-Books Retain Quality from 46.3 to 56.2 while adding only 5–11% training time across benchmarks. Its limited improvement on the simpler TOFU setting further supports the intended conditional behavior: replay is most beneficial when the hard/easy disparity is pronounced.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.14823

Human genetic evidence is associated with drug approval across therapeutic areas: an observational analysis of 26,278 target-disease pairs with temporal validation and feature ablation

作者:

Victoria Paterson↗

Genetic evidence is enriched among approved drug targets: in an observational analysis of 26,278 target-disease pairs from Open Targets and ChEMBL, targets with any genetic association had a 3.25-fold higher approval rate than those without (OR = 3.25, 95% CI 2.79-3.79, p = 1.91e-42). A target-level analysis accounting for non-independence of pairs sharing the same gene gave OR = 2.79 (bootstrap 95% CI 2.22-3.53); the oncology pair-level OR of 6.72 attenuates to 2.71 at the target level, illustrating how non-independence inflates area-specific estimates. The enrichment replicated in post-2015 approvals (OR = 3.51, p = 1.72e-8). Feature ablation across six evidence types revealed that literature mining alone accounts for most classifier performance (AUPRC = 0.099 versus 0.109 for all features), consistent with temporal leakage from post-approval publications. Excluding literature, remaining evidence types retain above-baseline signal (AUPRC = 0.084, 1.63x baseline). Sensitivity analyses bracket the pair-level OR between 3.25 and 4.93. Genetic evidence alone yields only a 1.0-percentage-point absolute AUPRC gain and the best model has poor calibration; the classifier has limited practical predictive value. We catalogue 1,433 genetically supported Phase 1/2 pairs as a hypothesis-generating resource. All findings are observational.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.17904

DiagFlowBench: Evaluating How Language Models Handle Off-Procedure Inputs in Grounded Diagnostic Dialogue

作者:

Guillermo Gil de Avalle↗Laura Maruster↗Shaina Raza↗Christos Emmanouilidis↗

arXiv:2606.17904v1 Announce Type: new Abstract: Language models increasingly serve as advisory systems in maintenance operations. To prevent hallucination, recent systems ground these models in procedural documentation to constrain them to approved steps. In practice, however, operator queries frequently stray from this path, requiring models to recognise out-of-scope inputs mid-conversation, a dynamic that current benchmarks rarely prioritise. We introduce DiagFlowBench, a dataset of 50 industrial diagnostic flowcharts from a consumer manufacturer converted into 1,676 multi-turn conversations that contrast compliant with out-of-scope utterances. Evaluating a panel of ten commercial and open-weight models reveals high variability in abstention rates, with models commonly selecting a real but contextually inadequate step rather than fabricating facts. The inherent plausibility and authority of this mapped but wrong advice exposes a challenging vulnerability for grounding systems.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.19625

Where Does Social Reasoning Come From? Capability Provenance in Language Models

作者:

Glenn Matlin↗Chandreyi Chakraborty↗Saehee Eom↗Mika Okamoto↗Rayan Castilla↗Louis Jaburi↗Alvin Deng↗Taywon Min↗Lucia Quirke↗Stella Biderman↗Mark Riedl↗

We use training-data attribution as an interpretable tool for capability discovery, mapping which regions of the pretraining corpus support social-reasoning versus STEM-reasoning in OLMo3-7B. Training-data attribution measures how strongly each training document influences a model's predictions on a benchmark, but document-level scores are too noisy to identify which corpus regions support which capabilities, and prior work has emphasized factual knowledge rather than reasoning. We compute gradient-based attribution (TrackStar via Bergson) over a working set drawn from the de-duplicated Dolma3 mix, aggregate influence across WebOrganizer's 24-format x 24-topic taxonomy (576 bins), and contrast benchmark pairs in a 2x2 design that varies domain (social vs. STEM) and capability type (reasoning vs. knowledge): SocialIQA and MMLU Social Sciences against ARC-Challenge and MMLU STEM. Social and STEM reasoning draw on qualitatively distinct corpus regions, and the contrast is sharper at the reasoning level than at the knowledge level. Targeted machine unlearning provides partial causal validation: forgetting high-attribution topic bins (e.g., Literature for SocialIQA) degrades the aligned benchmark more than within-bin random baselines, and we open-source all code, sampling manifests, the bin-level influence matrix, and unlearning checkpoints.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.18005

LLM Consumer Behavior Theory: Foundations of a Novel Research Field

作者:

Manon Reusens↗Sofie Goethals↗David Martens↗

arXiv:2606.18005v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as autonomous agents that make consumption decisions on behalf of users. This shift raises fundamental questions for consumer theory, which has traditionally modeled humans as the primary decision-makers. In this paper, we introduce LLM Consumer Behavior Theory, a new field of study concerned with analyzing consumer behavior in agentic markets. Drawing on classical and behavioral economics alongside recent advances in Natural Language Processing, we formalize how human preferences are reflected and acted upon by LLM-based agents, and how agent-level decisions aggregate into market demand. We unify previously fragmented literature on LLM decision-making, human behavior simulation, and preference elicitation under a common economic lens, highlighting where assumptions, such as rationality and heterogeneity, may fail in agentic markets. Rather than providing empirical validation, this paper outlines the scope of LLM consumer behavior and identifies open research questions related to alignment, preference representation, and market dynamics.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2606.14354

MUFFLe: Efficient Model Update Compression via Generalized Deduplication for Federated Learning

作者:

Xiaobo Zhao↗Daniel E. Lucani↗

arXiv:2606.14354v1 Announce Type: new Abstract: Federated learning is well suited to edge environments but is often limited by the uplink cost of transmitting model updates. This Work-in-Progress paper presents MUFFLe, a communication-efficient update compression scheme that integrates generalized deduplication (GD) into the FedAvg pipeline. MUFFLe deduplicates repeated patterns across the update vector, yielding a fixed-rate, variable-count compression scheme. Preliminary experiments on IID MNIST with 20 clients show that MUFFLe reaches the target accuracy of $92.93\%$ with 38~MB cumulative uplink communication, compared with 75~MB for 8-bit quantization, 86~MB for Top-$k$ sparsification, and 310~MB for uncompressed FedAvg. These results demonstrate the feasibility of applying GD to communication-efficient federated learning.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.05692

Benchmarking Counterfactual Prediction in Epidemic Time Series with Time-Varying Interventions

作者:

Wenhao Mu↗Facundo Yan↗Anik Mumssen↗Marisa Eisenberg↗Alexander Rodr\'iguez↗

arXiv:2606.05692v2 Announce Type: replace-cross Abstract: Deep learning has enabled significant advances in time-series causal inference, yet progress remains constrained by the lack of realistic benchmarks with observable counterfactual outcomes. Existing datasets either rely on real-world observations without ground-truth counterfactuals or on simplified simulations that fail to capture complex causal dynamics. To address this gap, we develop a large-scale benchmark for counterfactual prediction in epidemic time series under dynamic interventions. Unlike existing benchmarks, it supports static and time-varying treatments, as well as both single-policy and multi-policy intervention settings, enabling evaluation of causal inference methods across a broad range of causal inference scenarios. Leveraging a calibrated agent-based model grounded in real-world demographic, mobility, epidemiological, and policy data, we generate realistic counterfactual trajectories across more than 150 U.S. counties. Using this benchmark, we evaluate widely used and state-of-the-art causal inference methods, revealing substantial performance differences and highlighting the challenges of realistic time-series causal reasoning.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.13076

$\alpha$-fair heterogeneous agent reinforcement learning

作者:

Yao-hua Franck Xu↗Tayeb Lemlouma↗Jean-Marie Bonnin↗Arnaud Braud↗

arXiv:2606.13076v1 Announce Type: cross Abstract: Cooperation in multi-agent systems is typically optimized through utilitarian objectives that maximize overall efficiency but fail to account for reward distribution, often resulting in inequitable "leader-follower" dynamics. While fairness-based approaches encourage pro-social behaviors where every agent benefits from cooperation, many current algorithms - including those utilizing reward shaping - break the stationarity of Markov Games or lack rigorous theoretical guarantees. This creates a critical gap between fair objective methods and theoretically safe learning frameworks. We propose a novel framework that bridges $\alpha$-fairness with Heterogeneous-Agent Trust Region Learning (HATRL), ensuring monotonic improvement and convergence toward Nash Equilibria. Our approach leverages a fair advantage function that dynamically weights agent utilities based on their expected returns, allowing the global objective to transition from purely utilitarian efficiency to $\alpha$-fairness welfare based on the parameter $\alpha$. We introduce two practical algorithms, $\alpha$-fair HATRPO and $\alpha$-fair HAPPO, and demonstrate through experiments in sequential social dilemmas like CleanUp and CommonHarvest that they perform better than HATRL's algorithms from a utilitarian point of view while achieving socially higher outcomes.

阅读与讨论 → 访问原文 →

25.

arXiv (math.PR) 2026-06-11 DOI: arXiv:2209.03999

Consensus on Dynamic Stochastic Block Models: Fast Convergence and Phase Transitions

作者:

Haoyu Wang↗Jiaheng Wei↗Zhenyuan Zhang↗

arXiv:2209.03999v2 Announce Type: replace Abstract: We introduce two models of consensus following a majority rule on time-evolving stochastic block models (SBM), in which the network evolution is Markovian or non-Markovian. Under the majority rule, in each round, each agent simultaneously updates their opinion according to the majority of their neighbors. Our network has a community structure and randomly evolves with time. In contrast to the classic setting, the dynamics is not purely deterministic, and reflects the structure of SBM by resampling the connections at each step, making agents with the same opinion more likely to connect than those with different opinions. In the Markovian model, connections between agents are resampled at each step according to the SBM law and each agent updates their opinion via the majority rule. We prove a power-of-one type result, i.e., any initial bias leads to a non-trivial advantage of winning in the end, uniformly in the size of the network. In the non-Markovian model, a connection between two agents is resampled according to the SBM law only when at least one of them changes opinion and is otherwise kept the same. We identify the phase-transition threshold, up to the second-order leading term, between halting and fast convergence to consensus. We also give sufficient initial-lead conditions for consensus to occur within one, two, or three rounds.

阅读与讨论 → 访问原文 →