中 EN
登录 注册账户

Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达，利用大语言模型自动生成交叉领域文献分析简报。

登录 注册账户
01.
arXiv (CS.AI) 2026-06-16

PANDA: An LLM-Enhanced Performance-Driven Analog Design Framework Bridging Design Intent and Layout Generation

作者:
Haoyi Zhang↗Weijian Fan↗Xiaohan Gao↗Bingyang Liu↗Runsheng Wang↗Yibo Lin↗

arXiv:2606.15052v1 Announce Type: cross Abstract: Traditional design of analog circuits heavily relies on manual interventions across topology, sizing, and layout, with prior automation addressing stages in isolation. In this work, we propose PANDA, an LLM-enhanced framework that bridges high-level design intent to final layout by actively managing cross-stage dependencies through guided topology synthesis, substructure-aware sizing, and constraint-driven layout generation. This shifts automation from algorithm-centric execution to intent-centric co-design, reducing turnaround time from days or weeks to hours while improving design performance.

阅读与讨论 → 访问原文 →
02.
medRxiv (Medicine) 2026-06-18

Guiding the development of climate counterfactuals for health impact attribution studies

作者:
Charnley↗G. E. C↗Kotz↗Kawiecki Peralta↗Grayson↗K. M↗

Climate change detection and attribution (D&A) methods have become vital for quantifying the influence of anthropogenic forcing on the Earth's systems, including human health. Health impact attribution (HIA) studies seek to disentangle climate-driven health effects from natural variability yet are often constrained by the availability of accessible counterfactual climate scenarios. This tutorial paper presents a flexible, reproducible framework for developing counterfactual climates without reliance on computationally intensive global circulation models. We provide practical, R-based methodologies for constructing both trend-based (temperature and non-temperature) and event-based counterfactual, using a variety of techniques including model residual detrending, data-driven decomposition (e.g., Singular Spectrum Analysis and Empirical Mode Decomposition) and stochastic weather generators. The tutorial also explores the incorporation of greenhouse gas concentrations as forcing variables, rather than global mean temperature anomalies. By operationalising these methods through worked examples and an open code repository, this paper aims to build capacity within the HIA community, enhance methodological transparency, and foster interdisciplinary collaboration between climate and health researchers.

阅读与讨论 → 访问原文 →
03.
arXiv (CS.LG) 2026-06-17

Noise-Driven Escape from Metastable Phases explains Grokking in Deep Neural Networks

作者:
Ibrahim Talha Ersoy↗Karoline Wiesner↗

arXiv:2606.17120v1 Announce Type: new Abstract: Deep neural networks (DNNs) exhibit first order phase transitions under variations of the L2 regularization strength, with each transition marking the onset of a new learnable feature. Below a critical regularization strength, all features are in principle learnable, but coexisting metastable states, separated by energy barriers, can trap the network and impede convergence. A strength of DNNs is their ability to generalize. But many open questions remain, among them the origin of so called grokking: the abrupt, delayed onset of generalization after prolonged apparent overfitting. We show for linear DNNs that grokking is consistent with hysteresis in first-order L2 phase transitions: using L2 regularization to engineer deliberate trapping, we demonstrate that a model in a low-accuracy metastable state escapes only when SGD noise drives it across an energy barrier, with escape times following Arrhenius scaling. We reproduce grokking-like delayed convergence across two orders of magnitude in escape time by deliberately trapping models in metastable phases. Using sparse sub-sampling we also reproduce the canonical grokking curve where test error eventually approaches the final training error. Our work suggests that the number of metastable states equals the number of learnable features – one per singular value of the data covariance – the potential for hysteresis grows naturally with task complexity. We provide evidence that the same mechanism likely operates in general nonlinear DNNs. Our results provide routes toward more efficient learning schemes.

阅读与讨论 → 访问原文 →
04.
bioRxiv (Bioinfo) 2026-06-19

OmniPath Metabo: chemical structures, interactions and mechanisms to study the metabolome

作者:
Schaul↗Bai↗Franken↗Lawrence↗Palacio-Escat↗Bottazzi↗Carreno↗Daley↗Gul↗Sahin↗Mananes↗Bohar↗…

Mechanistic and functional analysis of omics data largely relies on the incorporation of prior knowledge; however, connecting metabolomics data and knowledge is a major methodological challenge. This is largely driven by the diverse prior knowledge being fragmented across many databases requiring the merging of different database records across chemical structures, identifiers, and varying levels of structural specificity. Hence, this limits mechanistic interpretation and functional characterisation of the metabolome. Here, we present OmniPath Metabo, a comprehensive, harmonized, metabolome-centric database covering metabolites, lipids, food-derived compounds, and small molecule drugs, along with their associated receptors, transporters, enzymes, reactions, allosteric regulators, and disease associations. OmniPath Metabo harmonizes attributes using controlled vocabularies and ontologies, structures and built-in cheminformatics to map identifiers and track ambiguity. OmniPath Metabo is built directly from 40+ original resources and is freely accessible via an interactive web app and API at metabo.omnipathdb.org. OmniPath Metabo enables dynamic, context-specific construction of subnetworks to serve dedicated purposes, such as cell-cell communication or integrated multi-omics metabolite-driven regulation, connecting reactions, allosteric regulation, metabolite-receptor and metabolite-transporter interactions. Combining it with the over 170 other resources in OmniPath, it can be used for integrated networks of signaling, gene regulation, and metabolism. We showcase the application of OmniPath Metabo by analysing publicly available metabolomics data of lung cancer cell lines and metabolic footprints to mutational patterns. In summary, OmniPath Metabo transforms fragmented resources into a harmonised prior knowledge framework for a mechanistic and functional analysis of the metabolome.

阅读与讨论 → 访问原文 →
05.
arXiv (quant-ph) 2026-06-11

Consistent Evaluation of Operators Involving the Position Operator in the Bloch Representation: Application to the Orbital Moment

作者:
Daehyeon An↗Junmo Jeon↗Se Kwon Kim↗

arXiv:2606.11679v1 Announce Type: cross Abstract: The position operator plays a central role in condensed-matter observables such as velocity, orbital moment, and electric polarization. In solid-state physics, the evaluation of operators incorporating the position operator has not reached a consensus, as observed in the operator-level discrepancy between the local circulation of Wannier functions and the self-rotation of wave packets. Here, to achieve a consistent evaluation of such operators, we propose three rules for evaluating operators involving the position operator in the Bloch representation. The rules are devised to satisfy physical conditions: independence from the choice of unit cell, preservation of Hermitian conjugacy for the product of operators, and recovery of the correct intraband velocity. We further address the gauge dependence of the position operator and introduce a scheme termed gauge filtration, which systematically removes gauge-dependent contributions from the operators containing the position operator. This methodology ensures that the quantities obtained from the operator evaluation correspond to observable physical phenomena. By applying our framework, we reconcile the results concerning the self-rotation of the wave packet and the local circulation of the Wannier function. We expect our proposal to establish a consistent framework for evaluating operators involving the position operator.

阅读与讨论 → 访问原文 →
06.
bioRxiv (Bioinfo) 2026-06-12

From Proteome Mining to Structural Validation: Phosphopyruvate Hydratase as a Structurally Tractable Drug Target in Kinetoplastid Parasites

作者:
Goyzueta Mamani↗L. D↗Barazorda Ccahuana↗H. L↗G Ng↗Pineda R↗Medina Franco↗J. L↗Florin Christensen↗Ferraz Coelho↗E. A↗Spadafora↗…

Chagas disease, caused by Trypanosoma cruzi, demands novel therapeutic strategies that overcome the toxicity and limited efficacy of current treatments. To address this need, herein we report an integrative, target-centric strategy that combines parasite proteome mining, structural modeling, and experimental validation. Functional enrichment and druggability analyses identified phosphopyruvate hydratase (PPH) as a promising candidate due to its essential metabolic role and limited similarity to human homologs. Notably, proteome mining revealed the presence and conservation of PPH across kinetoplastid parasites, including Leishmania donovani, supporting its evaluation beyond T. cruzi. For the selected PPH sequences, AlphaFold-derived three-dimensional models underwent extensive molecular dynamics refinement, yielding stable conformational ensembles suitable for structure-based studies. Using this validated model, virtual screening of the Latin American Natural Products Database - LANaPDB - identified aptosimon as a top-ranked compound candidate. Molecular dynamics simulations further showed ligand-dependent binding behavior, suggesting alternative binding modes distinct from the canonical substrate configuration. In vitro assays demonstrated consistent antiparasitic activity against intracellular T. cruzi amastigotes (IC50 = 3.52 ug/mL) and Leishmania donovani promastigotes (IC50 = 13.06 ug/mL), supporting the biological relevance of the aptosimon-related lignan chemotype, hinokinin, across two kinetoplastid parasite models. Together, these results support PPH as a structurally tractable and biologically relevant candidate target, while identifying an aptosimon-related lignan chemotype, represented experimentally by hinokinin, as a cross-species antiparasitic scaffold that warrants further biochemical target-validation studies.

阅读与讨论 → 访问原文 →
07.
arXiv (CS.AI) 2026-06-12

GeoDial: A Multimodal Conversational Tutoring Dataset for Geometry Problem-Solving with Visual Tutor Turns

作者:
Sankalan Pal Chowdhury↗Junling Wang↗Donya Rooein↗April Yi Wang↗Mrinmaya Sachan↗

arXiv:2606.12419v1 Announce Type: cross Abstract: Several educational domains rely heavily on diagrams and visual cues, yet most existing tutoring datasets are limited to text-only interactions. This limits the development of AI tutors that can teach in visually grounded ways used by human instructors. Thus, we introduce GeoDial, a multimodal tutoring dataset of over 1.3K teacher-student dialogs in the domain of geometry collected from experienced math teachers, where instructional turns are explicitly grounded in diagram highlights. We propose a scalable annotation protocol that integrates dialog acts, visual highlighting, and feedback, enabling fine-grained supervision of both language and visual tutoring behavior. To illustrate the challenges posed by this setting, we fine-tune several vision-language models on GeoDial and evaluate their ability to generate tutoring utterances and diagram highlights. While supervised fine-tuning substantially improves the quality of generated dialog, it struggles to produce accurate diagram highlights, revealing a key limitation of current methods and highlighting the need for approaches that more effectively integrate visual reasoning with pedagogical interaction.

阅读与讨论 → 访问原文 →
08.
arXiv (CS.LG) 2026-06-18

FORGE: Foundational Optimization Representations from Graph Embeddings

作者:
Zohair Shafi↗Serdar Kadioglu↗

arXiv:2508.20330v5 Announce Type: replace Abstract: Combinatorial optimization problems are ubiquitous in science and engineering. Still, learning-based approaches to accelerate combinatorial optimization often require solving a large number of difficult instances to collect training data, incurring significant computational cost. Existing learning-based methods require training dedicated models for each problem distribution, for each downstream task, severely limiting their scalability and generalization. We introduce Forge: Foundational Optimization Representations from Graph Embeddings, a framework that pre-trains a vector-quantized graph autoencoder on a large, diverse collection of mixed-integer programming (MIP) instances in an unsupervised manner, without relying on optimization solvers or optimal solutions. Vector quantization produces discrete code assignments that serve as a vocabulary for representing optimization instances. We evaluate Forge in both unsupervised and supervised settings. In the unsupervised setting, Forge embeddings effectively cluster unseen instances across problem domains and sizes. In the supervised setting, we fine-tune Forge embeddings and show that a single pre-trained model helps predicting both the integrality gap for cut-generation and variable hints for search guidance across multiple problem and size distributions. In both tasks, we improve the performance of a commercial optimization solver and outperform state-of-the-art learning-based methods. Finally, we open-source our training code, pre-trained Forge weights, and embeddings for multiple MIP distributions to foster further research in representation learning for optimization problems https://skadio.github.io/forge/

阅读与讨论 → 访问原文 →
09.
arXiv (quant-ph) 2026-06-12

Supersymmetry of dissipative Bose-Fermi systems with application to Jaynes-Cummings and Dicke models

作者:
Colin V. Coane↗Francesco Iachello↗

arXiv:2606.12682v1 Announce Type: new Abstract: We demonstrate how supersymmetries of Hamiltonians for coupled Bose-Fermi systems can be used to place the Hamiltonians of the Jaynes-Cummings model and Dicke model under the rotating wave approximation in matrix form and provide explicit analytic solutions for their eigenvalues. We then use this supersymmetry to place the Liouvillians of the associated Markovian open systems in matrix form and provide explicit solutions for their eigenvalues. These results are a consequence of the fact that the Hamiltonian of the Jaynes-Cummings model commutes with the linear Casimir invariant of the superalgebra $u(1|1)$ and that the Hamiltonian of the Dicke model commutes both with the linear invariant of $\sum_{i} u_{i}(1|1)$ and with the invariant of an additional $su(2)$ algebra. Our methods apply to various coupled Bose-Fermi systems with $u(1|1)$ and more generally with $u(n|m)$ dynamical superalgebras, and may provide efficient tools for studying more complicated examples.

阅读与讨论 → 访问原文 →
10.
arXiv (CS.CL) 2026-06-18

SFT Overtraining Predicts Rank Inversion via Entropy Collapse Under RLVR

作者:
Siddharth Aphale↗Kelly Liu↗

The standard heuristic of selecting the SFT checkpoint with the highest pass@1 for GRPO can fail when SFT compresses the rollout distribution. For binary rewards, the expected within group advantage variance is $p(1{-}p)(g{-}1)/g$; when early GRPO drives $p$ below $p^*(g)$, most groups have identical rewards and provide no group relative signal. We study SFT depth ladders for Qwen2.5-Coder-3B and DeepSeek-Coder-6.7B. We test Qwen2.5-Coder-3B across five depths and three seeds, and DeepSeek-Coder-6.7B across four matched depths and three seeds. On Qwen, pre RL pass@1 rises with SFT depth, but peak GRPO pass@10 falls from $0.806$ to $0.481$ (3 seed mean, $n{=}20$); pre RL entropy is positively associated with the GRPO outcome ($\rho{=}{+}0.69$). On DeepSeek, pass@1 remains far above $p^*(8){=}0.083$, and GRPO outcomes compress rather than invert. A two stage diagnostic, combining pre RL entropy triage with an early GRPO entropy monitor, flags high risk checkpoints and can stop failing runs early. Simple KL to reference regularisation and label smoothing variants do not rescue the collapsed Qwen checkpoint in our setting, suggesting the failure is not a trivial GRPO hyperparameter artefact.

阅读与讨论 → 访问原文 →
11.
arXiv (CS.CV) 2026-06-18

Bridging Creative Intent and Visual Quality: Creator-Driven Recurrent Video Generation with Agentic Feedback Loops

作者:
Denis Savytski↗Aiden Lei↗Heding Liu↗Warren Yang↗Sihan Liang↗Alexander Liu↗Zhe Zhao↗

Generative AI has made content creation increasingly accessible, but many AI-generated videos lack narrative coherence and creative direction, issues that become more substantial at longer durations. Unlike coding, where AI generation benefits from reliable feedback and techniques such as recurrent self-improvement, video generation requires subjective feedback about plot, scenes, and narrative, which naturally motivates approaches that incorporate human creative direction. We introduce CHIEF, a human-AI co-creation video generation framework that places the creator at the center of human-in-the-loop iterative video refinement, and supports them by providing automatic subjective feedback. The creator incorporates their creative direction by driving each iteration, while their revisions are incorporated by a specialized refiner agent. The feedback loop is generated by persona-conditioned multimodal LLMs that watch generated videos and produce subjective critique from the audience perspectives, providing feedback that self-evaluation alone cannot capture. To test the effectiveness of our proposed framework, we work with high school and college students with no prior filmmaking experience to create videos, from short 1-minute videos to a complete short 10-minute film with a complicated plot.

阅读与讨论 → 访问原文 →
12.
arXiv (CS.AI) 2026-06-12

TimeROME-DLM: Temporal Causal Tracing and Low-Rank Inference-Time Knowledge Editing for Masked Diffusion Language Models

作者:
Zhengtao Yao↗Liuyang Song↗Hongbo Zhang↗Chenhao Wei↗Haoyan Xu↗Guang Yang↗Siheng Wang↗

arXiv:2606.12841v1 Announce Type: cross Abstract: Masked diffusion language models (MDLMs) such as LLaDA now rival autoregressive (AR) LLMs, but every existing knowledge-editing and unlearning method (ROME, MEMIT, etc.) targets AR transformers and either makes assumptions that fail under iterative denoising, or requires gradient updates whose backward-pass activations cost tens of GB of extra VRAM and which collapse MDLMs at standard learning rates. We introduce TimeROME-DLM, the first training-free, gradient-free, inference-time knowledge-editing framework for MDLMs. It couples two components: a Temporal Indirect Effect (TIE) causal-tracing protocol that identifies, for each fact, the coordinate whose intervention most strongly drives the object prediction at later denoising steps; and a closed-form, low-rank residual edit memory that aggregates subject keys and target deltas across all forget facts and applies a single ridge-regularised update at that coordinate at every diffusion forward, with sparsification to limit utility spillover. Backbone weights stay frozen; only three hyperparameters (alpha, lambda, q) are tuned on a small validation split. On TOFU forget01 with TOFU-finetuned LLaDA-8B-Base, TimeROME-DLM cuts forget-set log-probability by roughly 83 nats. The same configuration transfers to LLaDA-8B-Instruct, Dream-7B, MMaDA-8B, DiffuLLaMA-7B, and LLaDA-MoE-1.4B. It keeps retain-set log-probability nearly flat (within ~1 nat at the utility-safe operating point) across 50 sequentially inserted facts, delivers a four- to fourteen-fold wall-clock speedup with zero additional VRAM over the strongest converged training-time baseline, and scales sub-linearly to 400 facts. TimeROME-DLM closes the locate-then-edit gap between AR LLMs and MDLMs at a fraction of the computational cost.

阅读与讨论 → 访问原文 →
13.
arXiv (CS.CL) 2026-06-11

ProHiFlo: Hierarchical Flow Matching with Functional Guidance for De Novo Protein Generation

作者:
Chuanzhen Wang↗Meade Cleti↗Pete Jano↗

De novo protein generation has transformative potential in therapeutic design, enzyme engineering, and synthetic biology. While diffusion-based and flow matching approaches have achieved progress, they typically operate at single resolution and lack mechanisms for incorporating functional constraints. We introduce ProHiFlo, a hierarchical flow matching framework with three innovations: (1) coarse-to-fine generation that models backbone geometry before refining to all-atom coordinates, reducing computational cost while maintaining accuracy; (2) functional guidance leveraging pretrained predictors to steer generation toward desired properties without retraining; (3) adaptive SE(3)-equivariant architecture for efficient multi-scale processing. Experiments on unconditional generation, motif scaffolding, and functional design demonstrate state-ofthe-art performance while requiring 4 fewer sampling steps. On enzyme active site scaffolding, ProHiFlo achieves 58.9% success rate compared to 41.2% for RFDiffusion.

阅读与讨论 → 访问原文 →
14.
medRxiv (Medicine) 2026-06-11

Incremental costs of transitioning from four to eight WHO-recommended antenatal care visits in Uganda: A costing analysis from a societal perspective

作者:
Atuhumuza↗E. B↗Atukunda↗E. C↗Musiimenta↗Mugyenyi↗G. R↗Haberer↗Obua↗Siedner↗M. J↗Matthews↗…

Background In 2016, the World Health Organization revised its antenatal care (ANC) recommendation from four to eight visits. For low- and middle-income countries like Uganda, where achieving even four visits remains a challenge, this transition has significant cost implications for both the health system and households. This study estimated the incremental costs of adopting the eight-visit model from a societal perspective. Methods The study was conducted in six government health facilities in southwestern Uganda. A micro-costing approach estimated health facility costs (personnel, equipment, consumables, and overhead). Costs incurred at patients end (transport, ultrasound, medical expenses, and time) were collected from 785 women using a questionnaire, with all costs in 2025 USD. Results For an average of 4.3 visits, total cost per woman was $100.1: facility costs $43.7 (43.7%), and patient costs $56.4 (56.3%). Transitioning to eight visits would increase total cost by $57.8 (57.8%), of which $36.4 (63.0%) would fall on households, equivalent to 68.8% of average monthly household income. Total costs would rise by 55.4% ($115.5 to $179.5) at Health Center IVs and 64.3% ($102.3 to $168.1) at Health Center IIIs, with facility costs up 43.4% and 62.9% and patient costs up 61.2% and 65.7%, respectively. Conclusion Transitioning to eight ANC visits would impose a large financial burden on households, with the incremental patient cost equivalent to more than two-thirds of average monthly household income. Equitable implementation requires improving availability of medicines and diagnostics, subsidizing transport, exploring telemedicine or community-based models, and improving efficiency at lower-tier health centers.

阅读与讨论 → 访问原文 →
15.
arXiv (CS.CV) 2026-06-12

On Pitfalls of $RemOve-And-Retrain$: Data Processing Inequality Perspective

作者:
Junhwa Song↗Keumgang Cha↗Junghoon Seo↗

The RemOve-And-Retrain (ROAR) benchmark is widely used to evaluate feature attribution methods, yet its validity remains underexplored from an information-theoretic perspective. We show that model- and data-agnostic post-processing of attribution maps (transformations that, by the data processing inequality, cannot add information about the decision function) can often improve ROAR scores. This means that an improved ROAR ranking is not, by itself, evidence that an attribution map carries more information about the model. We trace this failure mode to a bias toward spatially blurry masks. Experiments on CIFAR-10, SVHN, and CUB-200 show a consistent association between blurriness and ROAR performance, a pattern that also appears in the ROAD variant. We provide guidelines for more cautious removal-based benchmarking, with implications for validating mechanistic understanding of neural network internals.

阅读与讨论 → 访问原文 →
16.
arXiv (CS.LG) 2026-06-11

SEDULity: A Proof-of-Learning Framework for Distributed and Secure Blockchains with Efficient Useful Work

作者:
Weihang Cao↗Mustafa Doger↗Sennur Ulukus↗

arXiv:2512.13666v2 Announce Type: replace-cross Abstract: The security and decentralization of Proof-of-Work (PoW) have been well-tested in existing blockchain systems. However, its tremendous energy waste has raised concerns about sustainability. Proof-of-Useful-Work (PoUW) aims to redirect the meaningless computation to meaningful tasks such as solving machine learning (ML) problems, giving rise to the branch of Proof-of-Learning (PoL). While previous studies have proposed various PoLs, they all, to some degree, suffer from security, decentralization, or efficiency issues. In this paper, we propose a PoL framework that trains ML models efficiently while maintaining blockchain security in a fully distributed manner. We name the framework SEDULity, which stands for a Secure, Efficient, Distributed, and Useful Learning-based blockchain system. Specifically, we encode the template block into the training process and design a useful function that is difficult to solve but relatively easy to verify, as a substitute for the PoW puzzle. We show that our framework is distributed, secure, and efficiently trains ML models. We further demonstrate that the proposed PoL framework can be extended to other types of useful work and design an incentive mechanism to incentivize task verification. We show theoretically that a rational miner is incentivized to train fully honestly with well-designed system parameters. Finally, we present simulation results to demonstrate the performance of our framework and validate our analysis.

阅读与讨论 → 访问原文 →
18.
arXiv (CS.CV) 2026-06-16

UniT: Unified Multimodal Chain-of-Thought Test-time Scaling

作者:
Leon Liangyu Chen↗Haoyu Ma↗Zhipeng Fan↗Ziqi Huang↗Animesh Sinha↗Xiaoliang Dai↗Jialiang Wang↗Zecheng He↗Jianwei Yang↗Chunyuan Li↗Junzhe Sun↗Chu Wang↗…

Unified models can handle both multimodal understanding and generation within a single architecture, yet they typically operate in a single pass without iteratively refining their outputs. Many multimodal tasks, especially those involving complex spatial compositions, multiple interacting objects, or evolving instructions, require decomposing instructions, verifying intermediate results, and making iterative corrections. While test-time scaling (TTS) has demonstrated that allocating additional inference compute for iterative reasoning substantially improves language model performance, extending this paradigm to unified multimodal models remains an open challenge. We introduce UniT, a framework for multimodal chain-of-thought test-time scaling that enables a single unified model to reason, verify, and refine across multiple rounds. UniT combines agentic data synthesis, unified model training, and flexible test-time inference to elicit cognitive behaviors including verification, subgoal decomposition, and content memory. Our key findings are: (1) unified models trained on short reasoning trajectories generalize to longer inference chains at test time; (2) sequential chain-of-thought reasoning provides a more scalable and compute-efficient TTS strategy than parallel sampling; (3) training on generation and editing trajectories improves out-of-distribution visual reasoning. These results establish multimodal test-time scaling as an effective paradigm for advancing both generation and understanding in unified models.

阅读与讨论 → 访问原文 →
19.
arXiv (CS.AI) 2026-06-15

StainFlow: Entity-Stain Tracking and Evidence Linking for Process Rewards in GUI Agents

作者:
Haojie Hao↗Longkun Hao↗Yihang Lou↗Yan Bai↗Zhenyang Li↗Zhichao Yang↗Dongshuo Huang↗Hongyu Lin↗Lanqing Hong↗Jiakai Wang↗Xianglong Liu↗

arXiv:2606.07027v2 Announce Type: replace Abstract: Reinforcement Learning (RL) has become a promising approach for improving GUI Agents in long-horizon, stochastic digital environments, but trajectory-level success feedback is too sparse to provide reliable credit assignment for intermediate exploration steps. To mitigate this issue, recent studies introduce Process Reward Models (PRMs), which provide finer-grained training feedback through global milestone verification or local step-level evaluation. However, these methods still suffer from two level-specific limitations: global milestone decomposition is subjective and singular, making it difficult to accommodate the multiple valid execution paths in real GUI tasks, while fixed local judging windows may miss long-range key evidence or dilute the decision signal with irrelevant frames. Inspired by stain-tracing mechanisms in network flow analysis, we propose StainFlow, an entity-stain-flow process reward model for GUI Agents. To reduce the subjectivity of global partitioning, we introduce the Global Entity Stain Tracking module, which extracts visually verifiable task entities and tracks how their stain concentrations and states evolve along the trajectory, allowing task phases to be objectively separated by changes in the entity evidence flow. To improve the accuracy of local verification, we introduce the Local Stain Evidence Linking module. Centered on the triggering entities of each candidate key node, it retrieves relevant steps based on their stain concentrations and state changes, and dynamically constructs high-density evidence windows for verifying true key nodes. Extensive experiments on AndroidWorld and OGRBench show that StainFlow relatively improves online RL success by 3.2% and trajectory completion judgment accuracy by 1.8%.

阅读与讨论 → 访问原文 →
20.
arXiv (CS.AI) 2026-06-16

Large Language Models as Optimizers: A Survey of Direct vs. Tool-Augmented Approaches and Their Performance Frontiers

作者:
Roko Peran↗Luka Hobor↗Mihael Kovac↗Mario Brcic↗

arXiv:2606.15577v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly involved in complex mathematical optimization, even if the pragmatic user who triggers them is unaware of it. After all, many real-world problems reduce to the search for better or the best solutions. The field of LLM-as-optimizer has three paradigms: direct optimization, tool-augmented optimization, and tool-creating optimization. Direct optimization uses iterative prompting and heuristic generation to navigate solution spaces. Tool-augmented optimization translates natural language problems into formal specifications and orchestrates external solvers. Tool-creating optimization goes further, using LLMs to discover reusable algorithms or heuristics that can be deployed at zero marginal LLM cost. We describe current performance frontiers based on the benchmarks from the literature. We identify the critical reasoning gap in current architectures and argue for trade-offs between the future potential of direct optimization and the auditability of tool-augmented optimization. Even future, more powerful models might opt for tool-making to improve operational efficiency for repetitive families of problems.

阅读与讨论 → 访问原文 →
21.
arXiv (CS.CL) 2026-06-16

AdaMame: A Training Recipe for Adaptive Multilingual Reasoning

作者:
Dayeon Ki↗Kevin Duh↗Marine Carpuat↗

While Large Reasoning Models (LRMs) show strong performance in English, they often fail to reason in the language of the query, a phenomenon known as language collapse. Existing RL-based fixes typically add a binary language fidelity reward to the accuracy objective, yet still incur trade-off in accuracy, mid-trace code-switching, and excessive token usage. In this work, we propose AdaMame, a two-stage training recipe for multilingual mathematical reasoning that addresses these limitations by adaptively aligning the reasoning language to the query language without compromising accuracy. The first SFT stage fine-tunes on naturally occurring reasoning traces across five languages to establish multilingual reasoning capability. In the subsequent RL stage, we introduce AdaMame-GRPO, an adaptation of Group Relative Policy Optimization (GRPO) in which a query-conditioned alignment factor grows progressively during training, guiding the model to first explore diverse reasoning languages before exploiting reasoning in the query language. Evaluated across two benchmarks, two LRMs, and 12 languages, AdaMame-GRPO achieves Pareto-optimal performance across reasoning accuracy, language fidelity, and token efficiency over all baselines, with the strongest gains on out-of-domain, lower-resource languages.

阅读与讨论 → 访问原文 →
22.
arXiv (CS.CL) 2026-06-11

Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization

作者:
Hao Xiang↗Qiaoyu Tang↗Le Yu↗Yaojie Lu↗Xianpei Han↗Ben He↗Le Sun↗Bowen Yu↗Peng Wang↗Hongyu Lin↗Dayiheng Liu↗

Reinforcement Learning (RL) with verifiable environments has emerged as a powerful approach for enhancing the reasoning capabilities of Large Language Models (LLMs). While prior research demonstrates that scaling environment quantity improves RL performance, existing manual or individual construction methods suffer from linear scaling limits, thereby hindering scalable reasoning generalization. This paper introduces RACES (Recursive Automated Composition for Environment Scaling), a framework that conceptualizes verifiable environments as composable building blocks that can be recursively assembled. The key insight is that when the codomain (output type) of one environment matches the domain (input type) of another, they can be automatically fused into a new verifiable environment, enabling recursive composition. RACES is implemented with 300 individual environments and defines a set of composition operators (\textsc{SEQUENTIAL}, \textsc{PARALLEL}, \textsc{SORT}, and \textsc{SELECT}) that induce diverse reasoning patterns. Extensive experiments show that RL training on these composite environments consistently enhances reasoning generalization. Specifically, RACES improves DeepSeek-R1-Distill-Qwen-14B by an average of 3.1 points (from 48.2 to 51.3) and boosts Qwen3-14B performance from 58.8 to 61.1 on six benchmarks, which are unseen during the construction of training environments. Moreover, RACES achieves performance comparable to training on 300 individual environments using only 50 base environments, demonstrating significant efficiency in environment utilization.

阅读与讨论 → 访问原文 →
23.
arXiv (quant-ph) 2026-06-16

Quantum simulation of the Liouville equation in classical mechanics with discontinuous potential via Schrödingerization

作者:
Shi Jin↗Shuyi Zhang↗

arXiv:2606.15066v1 Announce Type: new Abstract: We develop quantum simulation algorithms for the Liouville equation of classical mechanics with discontinuous potential. Such discontinuities represent potential barriers at which classical particles undergo energy preserving transmission or reflection, and the resulting interface conditions must be incorporated into the numerical flux. We combine Hamiltonian-preserving schemes by Jin and Wen in Commun. Math. Sci. 3(3), 285-315 (2005) with the Schrödingerization method, which embeds the resulting nonunitary semi-discrete dynamics into a unitary Schrödinger type system in one additional auxiliary variable [arXiv:2212.14703, arXiv:2212.13969]. For one-, two-, and $n$-dimensional problems with grid aligned interfaces, we construct sparse matrix representations of the transmission and reflection fluxes using step and hat functions, derive the corresponding Hamiltonians of the Schrödingerized systems, and analyze their sparse-access query complexity. In the sparse-access oracle model, the resulting algorithms have a polynomial dependence on the inverse accuracy and avoid the exponential dependence on the phase-space dimension suffered by classical grid based Hamiltonian-preserving schemes, up to the cost of implementing the oracles and the postselection overhead. We also describe the postselected recovery of the physical solution state and the quantum readout of macroscopic observables such as density and averaged velocity through overlap estimation. Numerical experiments based on classical simulation of the Schrödingerized dynamics validate the proposed formulation and illustrate the correct transmission/reflection behavior at potential barriers.

阅读与讨论 → 访问原文 →
24.
arXiv (CS.CL) 2026-06-11

RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation

作者:
Leyi Pan↗Shuchang Tao↗Yunpeng Zhai↗Lingzhe Zhang↗Zhaoyang Liu↗Bolin Ding↗Aiwei Liu↗Lijie Wen↗

On-policy self-distillation (OPSD) provides dense, token-level supervision for reasoning models by aligning a model's own distribution with the distribution it produces under privileged context, typically a verified solution. However, we show that the learning signal drawn from this distributional gap concentrates on style tokens rather than task-bearing ones, as the hinted model tends to produce more direct, shorter outputs. We term this pathology privilege-induced style drift, which destabilizes training or causes response length to shrink. To address this, we propose RLCSD (Reinforcement Learning with Contrastive on-policy Self-Distillation), which mitigates this drift by contrasting the teacher-student gap under a correct hint against that under a wrong hint, suppressing the style shift that conditioning on a hint tends to induce regardless of correctness, and yielding a signal that is more concentrated on task-bearing tokens. Experiments on Qwen3 (1.7B/4B/8B) and Olmo-3-7B-Think across mathematical and logical reasoning show that RLCSD consistently outperforms GRPO and prior OPSD methods. We further show that the contrastive principle is general: it plugs into existing OPSD methods to improve them, and its underlying insight extends to the broader cross-model on-policy distillation setting.

阅读与讨论 → 访问原文 →
25.
arXiv (CS.CV) 2026-06-19

Collaborative Multi-Modal Coding for High-Quality 3D Generation

作者:
Ziang Cao↗Zhaoxi Chen↗Liang Pan↗Ziwei Liu↗

3D content inherently encompasses multi-modal characteristics and can be projected into different modalities (e.g., RGB images, RGBD, and point clouds). Each modality exhibits distinct advantages in 3D asset modeling: RGB images contain vivid 3D textures, whereas point clouds define fine-grained 3D geometries. However, most existing 3D-native generative architectures either operate predominantly within single-modality paradigms-thus overlooking the complementary benefits of multi-modality data-or restrict themselves to 3D structures, thereby limiting the scope of available training datasets. To holistically harness multi-modalities for 3D modeling, we present TriMM, the first feed-forward 3D-native generative model that learns from basic multi-modalities (e.g., RGB, RGBD, and point cloud). Specifically, 1) TriMM first introduces collaborative multi-modal coding, which integrates modality-specific features while preserving their unique representational strengths. 2) Furthermore, auxiliary 2D and 3D supervision are introduced to raise the robustness and performance of multi-modal coding. 3) Based on the embedded multi-modal code, TriMM employs a triplane latent diffusion model to generate 3D assets of superior quality, enhancing both the texture and the geometric detail. Extensive experiments on multiple well-known datasets demonstrate that TriMM, by effectively leveraging multi-modality, achieves competitive performance with models trained on large-scale datasets, despite utilizing a small amount of training data. Furthermore, we conduct additional experiments on recent RGB-D datasets, verifying the feasibility of incorporating other multi-modal datasets into 3D generation.

阅读与讨论 → 访问原文 →