Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

01.
arXiv (CS.LG) 2026-06-16

Decomposing one-class support vector machine into an ensemble of one-data support vector machines

arXiv:2606.16002v1 Announce Type: new Abstract: One-class classification (OCC) is a classification problem in which the training data contains only one class. The one-class support vector machine (OCSVM) is one of the most competitive OCC algorithms. However, OCSVM has scalability issues with large-scale datasets. This paper proposes the acceleration strategy of OCSVM. The idea is to decompose the dataset into samples and train OCSVM models for single data points. Subsequently, ensemble learning is applied to combine all models to compute the OCSVM model for the dataset. In addition, further acceleration is achieved through a data-reduction strategy with an OCSVM model trained on the average of the training samples. The experiment compared the proposal and traditional OCSVM using the Python package. The proposed strategy is faster than traditional OCSVM, while achieving similar classification results. Moreover, the proposed strategy can create one-to-one correspondence between samples and models. Source code is uploaded at https://github.com/ToshiHayashi/ODSVM

02.
arXiv (math.PR) 2026-06-17

Cutoff for asymmetric shelf shuffle

arXiv:2606.18039v1 Announce Type: new Abstract: A mechanical shuffler consists of $m$ shelves. A deck of $n$ cards, arranged in increasing order, is dealt from the bottom sequentially. Each card is assigned a shelf uniformly at random and placed on the top (bottom) of the existing pile with probability $p$ ($1-p$) independently. We refer to this as asymmetric shelf-shuffle. We find the law $\nu_{n, m}^{(p)}$ of the permutation induced by the asymmetric shelf-shuffle and show that the pair consisting of the number of descents and the number of valleys is a sufficient statistic. This generalizes a result of Diaconis, Fulman, and Holmes (Ann. Appl. Prob., 2013) corresponding to the case $p=1/2$. For $p=1/2$, Chen and Ottolini (ECP, 2025) established the cutoff in the total variation distance near $\lfloor n^{5/4}\rfloor$. We establish the cutoff for the asymmetric shelf shuffle. Let $\nu_n$ be the uniform measure on the set of all permutations $S_n$ of $\{1, \ldots, n\}$. For a fixed $p\neq 1/2$ and $c>0$, we show that \[\operatorname{TV}\left(\nu_{n, \lfloor cn^{3/2}\rfloor }^{(p)}, \nu_n\right)=1-2\Phi\left(-\frac{|2p-1|}{4\sqrt{3}c}\right)+O_{c, p}(n^{-1/2})\;.\] We also establish the cutoff in the separation distance near $m\approx n^{2}$ and in the relative entropy near $m=n^{3/2}$. In both cases, we also obtain the cutoff profile explicitly.

03.
arXiv (CS.CL) 2026-06-18

Retell, Reward, Repeat: Reinforcement Learning for Narrative Theory-Informed Story Retelling

Counterfactual story retelling exposes LLM shortcomings in constrained narrative solution spaces where they can no longer rely on recalling memorised training data. Ground-truth-based post-training, such as SFT, fails to teach LLMs how to generate logical and rational narrative events. In this paper, we introduce Retell, Reward, Repeat (RRR), an RL-based pipeline synthesising Structuralist Narratology with scalar narrativity to teach storytelling structure. We extend the TimeTravel dataset with human-annotated stages of narrative equilibrium to evaluate reward models. By using d-RLAIF, RRR derives training signals from the narrativity of textual features without the need for reference outputs. Evaluations demonstrate that RRR-trained LLMs outperform few-shot and SFT baselines in logic, rationality, and completeness, with output quality additionally validated by blind human preference. Relying on a small, query-only dataset, RRR provides a linguistically grounded, cost-effective post-training mechanism for storytelling–a domain currently lacking effective post-training methods. RRR highlights the continued relevance of integrating established linguistic theories into contemporary NLP.

04.
arXiv (quant-ph) 2026-06-12

Exceptional Points as Manifestations of Analyticity Breakdown in the 't Hooft Model

Authors:

arXiv:2606.10141v2 Announce Type: replace-cross Abstract: We use the exactly-solvable t Hooft model of 1+1D large-N_c QCD as a rigorous laboratory for the breakdown of analyticity of a causal response function, the meson two-point function. A PT-symmetric deformation i gamma(x-1/2) of the light-cone meson operator, the analogue of an imaginary chemical potential, drives the lowest two mesons to an exceptional point (EP) at gamma_c. Recasting the resolvent as a Jacobi continued fraction yields gamma_c in closed form: 2 pi g^2 N_c at the two-pole level, converging to 7.966 g^2 N_c by depth five – an analytic, not numerical, threshold. The square-root exponent nu=1/2 is fixed by the 2x2 Jordan form and confirmed by finite-size scaling to N=1999. The breakdown has an unambiguous time-domain signature: the propagator norm is bounded for gamma < gamma_c, grows linearly at gamma_c (the Jordan secular law), and exponentially beyond – observable, since the deformed operator is a non-Hermitian Wannier-Stark ladder, in photonic and topolectrical analogues. The threshold is locked to confinement, gamma_c propto g^2 N_c, and recurs as a uniform EP cascade; a second, non-reciprocal deformation yields an exactly-exponential non-Hermitian skin effect. This is the first analytically-controlled instance of exceptional-point analyticity breakdown in a confining gauge theory.

05.
arXiv (CS.CL) 2026-06-19

Your Mouse and Eyes Secretly Leak Your Preference: LLM Alignment using Implicit Feedback from Users

To align a Large Language Model (LLM), most existing methods collect explicit human feedback and train a reward model to predict the human preference based on the response text. These existing methods have two key limitations. First, the users rarely provide explicit feedback for LLM responses, which makes the high-quality preference annotation expensive to collect. Second, the methods do not leverage implicit human feedback, which has proven vital to the economic moats of Internet giants. To quantify the value of implicit feedback, we build a new dataset called IFLLM, which collects 1336 multi-turn questions from the 59 Mechanical Turk workers, their mouse trajectories, and eye gazing points to the LLMs' responses from their webcams. IFLLM shows that the users have very diverse types of gazing behavior and mouse trajectories. Our reward model based on the implicit user feedback boosts the accuracy of the text-based reward model from 55% to 64% and nearly triples the relative response quality improvements after applying the DPO to eight LLMs, demonstrating the value of implicit feedback in the wild. Our data collection website, dataset, and codes can be found at https://github.com/themehulpatwari/llm-implicit-feedback/.

06.
arXiv (CS.CV) 2026-06-11

UI2Code^N: UI-to-Code Generation as Interactive Visual Optimization

UI-to-code aims to translate UI screenshots into executable front-end code. Despite progress with vision-language models (VLMs), most existing methods formulate UI-to-code as a single-pass generation, which mismatches real-world UI development that is inherently iterative and feedback-driven. We reformulate UI-to-code as an interactive visual optimization problem, where code generation is embedded in a closed-loop process of execution, visual inspection, and iterative refinement driven by rendered visual feedback. To address the non-differentiability of visual objectives and the noise of absolute visual evaluators, we propose Relative Visual Policy Optimization (RVPO), a preference-based reinforcement learning method that optimizes relative visual rankings among rendered candidates under execution feedback. We instantiate this paradigm in UI2Code^N, an open-source 9B model trained via continual pre-training, supervised fine-tuning, and reinforcement learning. Experiments demonstrate state-of-the-art performance on UI drafting, UI polishing, and UI editing benchmarks, even outperforming larger models, with performance consistently improving through iterative visual optimization. Our code and models are available at https://github.com/zai-org/UI2Code_N.

07.
arXiv (CS.LG) 2026-06-15

Machine-learned particle flow as a foundation model for collider physics

arXiv:2606.14373v1 Announce Type: cross Abstract: The workflow from particle collision to physics analysis passes through a series of reconstruction steps that are traditionally modular and disconnected, with no shared representation linking low-level detector data to high-level analysis tasks. We show that casting event reconstruction as a machine learning problem naturally produces such a shared representation. We repurpose a machine learning model trained for particle-flow reconstruction (MLPF) to perform three distinct analysis tasks: jet flavor identification, jet energy regression, and missing momentum regression. By appending the per-particle latent representations learned during reconstruction as additional input features, we substantially improve over baselines that use kinematic features alone. We further demonstrate that a single linear layer trained using only the latent representations achieves competitive performance against state-of-the-art baseline architectures, and outperforms the baseline for missing momentum regression with approximately 35 times fewer parameters. These results demonstrate that the latent representations learned during reconstruction encode essential physics information needed for downstream analysis, establishing MLPF as a foundation model and offering a concrete step toward an end-to-end pipeline from detector data to physics analysis.

08.
arXiv (CS.AI) 2026-06-11

JailbreakOPT: Tool-Assisted Iterative Jailbreak Prompt Optimization

arXiv:2606.11425v1 Announce Type: cross Abstract: Jailbreak attacks expose persistent safety weaknesses in large language models (LLMs), but existing stateless single-turn methods face a trade-off: hand-crafted prompts are expressive but static, while iterative prompt optimization can adapt but often relies on low-level mutations that require many target queries. We propose JailbreakOPT, a tool-assisted framework for improving iterative single-turn jailbreak prompt optimization. JailbreakOPT organizes diverse atomic jailbreak prompts into an attack tool library and composes them through a unified intra-episode optimization abstraction to generate stronger standalone attack prompts. To reuse experience across attack episodes, JailbreakOPT further frames tool selection as a contextual bandit problem and applies contextual Thompson sampling to guide exploration and exploitation based on past outcomes. Experiments across multiple target LLMs and attack goals show that JailbreakOPT improves attack success rate (ASR) while reducing the number of attacks until success (No.A) compared with atomic single-turn attacks and existing iterative optimization baselines. This paper may contain offensive or harmful content.

09.
arXiv (quant-ph) 2026-06-19

Proposal of quantum arrival-time measurement with a Bose-Einstein condensate

arXiv:2606.20278v1 Announce Type: new Abstract: This work shows how a Bose-Einstein condensate of ultracold atoms could be used to address a long-standing question in quantum theory: how much time does it take for a particle to reach a detector? To this end, we propose a realistic experimental setup, whose key idea is not to measure arrival times directly, but the arrival flux on the detector as a function of its position. This novel approach not only solves practical issues with having a detector close to the system, but also results in signals that allow to unambiguously distinguish different theoretical predictions. This proposal raises prospects for resolving the decades-old debate on this fundamental issue.

10.
arXiv (CS.AI) 2026-06-17

FllumaOne: A Code-Native Multimodal CAD Dataset with Executable Programs and Kernel-Validated Feature Histories

Authors:

arXiv:2606.17696v1 Announce Type: new Abstract: Parametric computer-aided design records both final geometry and the ordered construction history that determines how a part can be edited. Datasets for editable CAD research should therefore expose modeling operations, parameters, and feature dependencies together with validated geometry. We introduce FllumaOne, a code-native multimodal CAD dataset whose models are generated by executable Python programs in Flluma, a Qt/C++ OpenCASCADE-based CAD system. Each sample aligns its program with a structured feature tree, a training-oriented intermediate representation, STEP geometry, a surface point cloud, natural-language descriptions, metadata, and eight canonical visible-edge renderings. The primary release, FllumaOne-100K, contains 100,000 accepted samples across four template-level complexity regimes. Programs are executed and retained only after kernel geometry, solid validity, and export checks; release reports also record modality completeness and split-level duplicate tests. A Qwen2.5-Coder-1.5B LoRA baseline trained on 80,000 samples achieves 99.98% Python syntax validity, 99.97% Flluma build success, and 99.14% STEP-export validity on the held-out 10,000-sample test split. For the 9,909 predictions converted to surface point clouds, the mean normalized Chamfer Distance is 0.002124. The dataset supports conditioned CAD reconstruction, executable program synthesis, feature-tree prediction, B-Rep analysis, retrieval, design completion, and editable reverse engineering.

11.
PLOS Medicine 2026-06-01

The NIH 2025 Public Access Policy: Immediate access, unequal costs

by Caitlin R. Ryus, Caroline Raymond King, Edward R. Melnick The NIH 2025 Public Access Policy eliminates embargo periods for federally funded research, expanding who can read science. Yet without addressing article processing charges and market concentration, the policy risks creating new barriers to who can afford to perform and publish their science. In this Perspective, Caitlin Ryus and colleagues discuss the NIH 2025 Public Access Policy, highlighting that while expanding who can read science, the policy risks creating new barriers to who can afford to perform and publish their science.

12.
arXiv (CS.LG) 2026-06-11

Why Depth Matters in Parallelizable Sequence Models: A Lie Algebraic View

arXiv:2603.05573v2 Announce Type: replace Abstract: Scalable sequence models, such as Transformer variants and structured state-space models, often trade expressivity power for sequence-level parallelism, which enables efficient training. Here we examine the bounds on error and how error scales when models operate outside of their expressivity regimes using a Lie-algebraic control perspective. Our theory formulates a correspondence between the depth of a sequence model and the tower of Lie algebra extensions. Echoing recent theoretical studies, we characterize the Lie-algebraic class of constant-depth sequence models and their corresponding expressivity bounds. Furthermore, we analytically derive an approximation error bound and show that error diminishes exponentially as the depth increases, consistent with the strong empirical performance of these models. We validate our theoretical predictions using experiments on symbolic word and continuous-valued state-tracking problems.

13.
medRxiv (Medicine) 2026-06-16

Comparative Effectiveness and Safety of Prophylactic Vasopressors for Preventing Post-induction Hypotension in the Elderly: A Systematic Review and Network Meta-analysis

Background: Post-induction hypotension is a predictable haemodynamic hazard in older adults undergoing general anaesthesia. Prevention remains divided among volume optimisation, anaesthetic dose reduction, rescue treatment after hypotension occurs and proactive vasoactive support. Methods: We searched PubMed, Embase, Web of Science, CENTRAL, CNKI, Wanfang and VIP from inception to 30 March 2026. Eligible studies were randomised trials of prophylactic vasoactive drugs given before, during or immediately after induction in older adults. The primary outcome was post-induction hypotension. Secondary outcomes were post-induction mean arterial pressure (MAP), systolic arterial pressure (SBP), heart rate (HR) and reported haemodynamic adverse events. Random-effects network meta-analysis was used, and confidence in network estimates was assessed using CINeMA principles. Results: Thirty-one trials including 2,821 participants were included in the revised network. Compared with placebo/control, all active agents favoured lower post-induction hypotension. The most favourable point estimates were observed for phenylephrine (odds ratio [OR] 0.17, 95% confidence interval [CI] 0.01 to 2.16) and metaraminol (OR 0.19, 95% CI 0.02 to 1.53), although both were imprecise. More precise reductions were observed for methoxamine (OR 0.23, 95% CI 0.13 to 0.43), norepinephrine (OR 0.25, 95% CI 0.13 to 0.47) and ephedrine (OR 0.34, 95% CI 0.19 to 0.63). Phenylephrine ranked highest for MAP support, norepinephrine ranked highest for SBP support, and ephedrine ranked highest for HR preservation. Global inconsistency was detected for SBP but not for hypotension incidence, MAP or HR, supporting cautious profile-based interpretation. Conclusions: Prophylactic vasopressor choice during induction should be guided by haemodynamic phenotype rather than ranking alone. In the revised network, active prophylaxis consistently favoured lower hypotension, but sparse nodes produced uncertainty. Norepinephrine retained a comparatively balanced profile when vasodilatory post-induction hypotension is anticipated, phenylephrine and related alpha-agonists provided stronger pressure support when HR and cardiac-output reserve are preserved, and ephedrine was most relevant when chronotropic support is desired. Keywords: general anaesthesia; induction; hypotension; norepinephrine; phenylephrine; ephedrine; network meta-analysis; older adults.

14.
arXiv (CS.AI) 2026-06-16

TimeVista: Exploring and Exploiting Vision-Language Models as Judges for Time Series Forecasting

arXiv:2606.16173v1 Announce Type: new Abstract: High-quality time series forecasting is pivotal for real-world decision-making. However, traditional point-wise metrics often fail to reveal complex temporal patterns and align poorly with human intuitive preferences. While the ''LLM-as-a-Judge'' paradigm has revolutionized text evaluation by providing flexible, human-aligned judgment, its application to time series remains largely unexplored. In this paper, we leverage Vision-Language Models (VLMs) as judges for time series forecasting, harnessing their ability to comprehend time series plots grounded in textual information. Specifically, we propose a novel framework integrating micro- and macro-level judgments informed by contextual information to evaluate time series forecasting. To this end, we introduce TimeVista, a comprehensive VLM-as-a-Judge benchmark comprising 5563 time series samples paired with detailed evaluation rubrics. Extensive meta-evaluations demonstrate that VLMs are highly reliable judges, achieving significantly higher consistency with human preferences than conventional metrics. Building upon our benchmark, we comprehensively assess recent Time Series Foundation Models (TSFMs) under the VLM-as-a-Judge paradigm. Our results demonstrate that VLMs serve as robust and interpretable judges, providing a comprehensive, human-aligned standard for evaluating time series models.

15.
arXiv (CS.LG) 2026-06-16

Multi-Agent Framework for Audit Risk Assessment with Explicit Uncertainty and Evidence Conflict Modeling

arXiv:2606.15640v1 Announce Type: new Abstract: Audit risk assessment increasingly benefits from combining heterogeneous evidence sources, yet existing approaches typically produce point predictions without quantifying how well different evidence streams agree. We propose UMAR (Uncertainty-Aware Multi-Agent Risk Assessment), a framework that employs three specialized agents: an MD&A Text Agent, a Financial Ratio Agent, and a CAM Agent, each producing independent risk scores with calibrated uncertainty estimates. An Uncertainty Aggregator based on Dempster-Shafer evidence theory fuses these scores while explicitly measuring inter-agent conflict. We evaluate UMAR on a U.S. dataset of 3,200 firm-year observations from SEC 10-K filings (2019-2023), with financial restatement as the target label. Experimental results show that UMAR achieves an AUROC of 0.782 and a PR-AUC of 0.341, outperforming logistic regression, XGBoost, FinBERT, and single-agent and dual-agent LLM baselines. UMAR attains the lowest expected calibration error (ECE = 0.052) among all methods and identifies evidence-conflict patterns that correlate with actual restatement risk, offering auditors potentially actionable and interpretable risk signals.

16.
arXiv (CS.AI) 2026-06-19

VitalAgent: A Tool-Augmented Agent for Reactive and Proactive Physiological Monitoring over Wearable Health Data

arXiv:2605.29483v2 Announce Type: replace Abstract: Wearable devices enable continuous monitoring of physiological signals such as ECG and PPG, but existing mHealth systems are largely limited to task-specific prediction pipelines or reactive question answering over static summaries. They lack the ability to support temporal reasoning, persistent physiological context, and proactive monitoring over long-term signal streams. We propose VitalAgent, a tool-augmented agentic framework for ECG/PPG-based mHealth that supports both reactive question answering and proactive monitoring. VitalAgent is built on a longitudinal physiological memory and a tool-augmented reasoning interface that enables dynamic computation over raw signals. We further introduce VitalBench, a longitudinal physiological monitoring benchmark dataset comprising 1,862 QA pairs for reactive question answering and 90.2 hours of continuous ECG/PPG recordings for proactive monitoring, covering cardiac, physical activity, and stress-related tasks. Experiments demonstrate that VitalAgent achieves over 25% improvement over prompt-based and ReAct baselines in reactive evaluation and supports proactive alert monitoring over long-term physiological signals, highlighting the importance of dynamic tool use and long-term physiological monitoring.

17.
arXiv (quant-ph) 2026-06-17

Engineering entanglement and transport in interacting quantum walks with tailored potentials

arXiv:2606.17825v1 Announce Type: new Abstract: Controlling the interplay between particle propagation and quantum correlation generation is a central challenge in quantum transport. Here, we investigate two distinguishable continuous-time quantum walkers evolving on parallel one-dimensional lattices, interacting via distance-dependent potentials. While on-site interactions reproduce the typical bosonic behaviour, extending the interaction to a linear potential over multiple neighbors introduces controlled Bloch-like oscillations and shifts the bound-pair regime to stronger couplings. More generally, we explore a Coulomb-like interaction parameterized by strength, spatial scaling, and decay rate. This reveals a rich phase diagram including four distinct dynamical regimes: (i) a high-entropy, oscillatory regime akin to a linear potential; (ii) a strongly localized, bound-pair regime; (iii) a novel intermediate regime combining near-ballistic spreading with strong correlations; and (iv) a weakly interacting, free-propagation regime. Notably, regime (iii) achieves concurrent optimization of transport efficiency and entanglement, offering a sweet spot for correlated quantum dynamics. Our results provide a tool for designing interaction-engineered quantum walks with potential applications in quantum information processing and simulations.

18.
arXiv (quant-ph) 2026-06-15

Conditional squeezing induced by a two-level system: arbitrary-time Magnus coefficients in the quantum Rabi model

arXiv:2508.03506v5 Announce Type: replace Abstract: We present a systematic Magnus expansion treatment of the quantum Rabi model beyond the Rotating Wave Approximation. We show that at the second order of Magnus series, the second-order evolution operator contains a term that induces conditional squeezing of the field mode depending on the state of the atom, in addition to the energy shifts. We analyze the scaling behavior of the conditional squeezing coefficient for $^{87}\mathrm{Rb}$ $5^2S_{1/2}\rightarrow5^2P_{1/2}$ transition line and show that the slow envelope of the squeezing coefficient is maximized at half-detuning cycles, and that it scales with $\frac{4g^2}{\omega_0|\Delta|}$. We also show that the quadrature squeezing angle suggests a possible route towards quantum non-demolition readouts, while further investigation is required for a full first-order suppression. We then connect our work to the well-studied AC-Stark shift and Bloch-Siegert shift using the effective Hamiltonian theory. Finally, we show how the energy shifts and the conditional squeezing arise, as a whole $\mathrm{SU}(1,1)$ algebra, and how they can be disentangled as individual unitary evolutions.

19.
arXiv (CS.AI) 2026-06-17

FacProcessTwin: An LLM-Based System for Process Twin Development

arXiv:2606.17666v1 Announce Type: cross Abstract: Process twins provide real-time representations of entire production processes. By capturing how process steps interact, rather than monitoring a single machine in isolation as an asset-based digital twin does, they have the potential to drive efficiency gains across the whole process. However, developing a process twin is costly. It requires accurately modelling the entire production process: its process steps, the equipment and product-specific settings each step uses, and its process variations. The resulting model must then be bound to live operational data. We present FacProcessTwin, a system that leverages a large language model (LLM) to reduce this development time, building a process twin from a plant's process documentation and natural-language input from an operator. FacProcessTwin generates this complete process model and then automatically binds its process steps to live operational data. The generated model and its data bindings are rendered as an interactive process diagram through which manufacturing personnel can monitor and correct the system's autonomous decisions, such as resolving uncertainty at safety-critical binding steps. We evaluate FacProcessTwin through a real-world case study of an Australian food manufacturer, covering 16 production process flows that span chilled, frozen, and aseptic shelf-stable product categories and include process variations within the same product. The results show that FacProcessTwin generates these process models accurately (a mean F1 of 95.2% against ground truth) and builds each twin in roughly a sixth of the manual time. Its human-in-the-loop governance then keeps the safety-critical bindings correct: at ambiguous tags where a single-pass baseline silently mis-binds 75.0% of the time, FacProcessTwin defers to the operator and mis-binds none.

20.
arXiv (CS.CL) 2026-06-19

Apparent Psychological Profiles of Large Language Models are Largely a Measurement Artifact

Psychological instruments designed for humans are increasingly used to assign large language models (LLMs) stable psychological profiles that affect their usability, safety assessment, and use as proxies for human participants in research. Using a formal psychometric framework, we show that these profiles are largely a measurement artifact. Administering a battery of personality and risk-preference instruments spanning self-reports and behavioral tasks to 56 instruction-tuned LLMs alongside large human reference samples, we report four findings. First, differences between models are driven not by the traits an instrument targets but by a directional response bias, a tendency to respond toward one end of the scale, or one labeled option, regardless of item content; a variance decomposition attributes 81-90% of between-model variation to this bias, against 9-16% in humans. Second, the bias declines with model capability but is not eliminated by it. Third, because bias rather than trait drives responding, an instrument's apparent reliability is almost entirely predicted by its response orthogonality, a term we coin for the proportion of items for which trait and bias point in opposite directions. Fourth, the profile a model appears to have shifts with the items used and can be manufactured through item selection. These results demonstrate that the apparent psychological profiles of LLMs are artifacts of the instrument used to measure them, not properties of the models themselves. As instruments borrowed from human psychology are rarely fully orthogonal and may inherently lack validity for LLMs, we call for dedicated assessments centered on response orthogonality.

21.
arXiv (CS.CL) 2026-06-19

Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement Learning

This work presents a general framework for training large language models (LLMs) to "Connect the Dots" (CoD), a meta-capability required by long-lifecycle agents: as an LLM-based AI agent gets deployed in an environment, it solves a long sequence of tasks while continuously exploring the environment, learning from its own experiences, and iteratively self-updating its context about the environment, thereby achieving progressively better performance on future tasks conditioned on the updated context. Major components of the CoD framework include: (1) algorithm design and infrastructure for end-to-end reinforcement learning (RL) with long rollout sequences interleaving solve-task and update-context episodes; (2) tasks and environments for incentivizing and eliciting the targeted meta-capability in LLMs during training, as well as for faithfully measuring progress during evaluation. We present proof-of-concept implementations of the CoD framework, including a GRPO-style RL algorithm with fine-grained credit assignment, as well as tasks and environments tailored to the targeted meta-capability (rather than domain-specific LLM capabilities or standard task-by-task RL). Empirical results validate the efficacy of end-to-end RL training in the CoD setting, and demonstrate the potential for out-of-distribution generalization – within the training domains, across different domains, and from CoD to Ralph-loop settings – of the elicited meta-capability. Our investigation of CoD connects several lines of prior works, and opens up new opportunities for advancing LLMs and AI agents. To facilitate further research and applications, we release our implementations at \url{https://github.com/agentscope-ai/Trinity-RFT/tree/research/cod/examples/research_cod}.

22.
arXiv (quant-ph) 2026-06-17

Quantum-inspired Ising machine using sparsified spin connectivity

arXiv:2604.04606v2 Announce Type: replace-cross Abstract: Combinatorial optimization problems become computationally intractable as these NP-hard problems scale. We previously proposed extraction-type majority voting logic (E-MVL), a quantum-inspired algorithm using digital logic circuits. E-MVL mimics the thermal spin dynamics of simulated annealing (SA) through controlled sparsification of spin interactions for efficient ground-state search. This study investigates the performance potential of E-MVL through systematic optimization and comprehensive benchmarking against SA. The target problem is the Sherrington-Kirkpatrick (SK) model with bimodal and Gaussian coupling distributions. Through equilibrium state analysis, we demonstrate that the sparsity control mechanism provides a consistent search of the solution space regardless of the problem's coupling distribution (bimodal, Gaussian) or size. E-MVL not only achieves the best performance among all tested algorithms–solving exact solutions up to 1600 spins where the best SA baseline is limited to 400 spins–but also provides insights that significantly improve SA's own temperature scheduling. These results establish E-MVL's dual contribution as both an efficient optimizer and a practical methodology for enhancing SA performance. Moreover, FPGA implementation achieved an approximately 6-fold faster solution speed than SA.

23.
bioRxiv (Bioinfo) 2026-06-20

Systematic Evaluation of Feature Representations for Cancer-Associated sORF Prediction in Non-coding RNA

Short open reading frames (sORFs) within non-coding RNAs (ncRNAs) have arisen as a hidden layer of gene regulation, encoding small peptides that represent a new class of cancer regulators with diagnostic and therapeutic potential. However, inferring associations between sORFs to specific cancer types remains challenging and requires computational approaches for accurate prediction. Recently, the CoraL framework introduced the first computational approach for predicting cancer-associated peptides, focusing primarily on model architecture while overlooking how feature extraction strategies influence predictive accuracy. We present a systematic evaluation of machine learning models and feature extraction approaches to predict cancer-associated sORFs across 15 cancer types. We benchmarked seven traditional machine learning algorithms combined with three feature extraction methods: k-mer frequency, Word2Vec embeddings, and genomic language model (gLM)-based embeddings. To our knowledge, this is the first study applying gLM-derived embeddings to the prediction of cancer-associated sORFs in ncRNA. Our results show that traditional machine learning models with appropriate feature extraction outperform the CoraL baseline across all cancer types, achieving up to 10% higher accuracy in some of the 15 evaluated datasets. Interestingly, k-mer features consistently outperformed gLM embeddings without fine-tuning, suggesting that local sequence composition may provide more discriminative information for this task and that pre-trained genomic representations may require task-specific adaptation to fully capture these patterns. Additionally, we observed that the way sequences are tokenized, such as the k-mer length, can affect performance: longer fragments (e.g., k=7) sometimes reduced accuracy for Random Forest but had a smaller effect on MLP. Our findings suggest that appropriate feature engineering can provide greater improvements than increasing model complexity.

24.
bioRxiv (Bioinfo) 2026-06-08

DipSkmer: Reference-free population genomics with diploid genome skims

Ecologists and conservation biologists rely on genetic diversity as a key essential biodiversity variable (EBV) used to track population health and dynamics, and utilize the population parameter {theta} (estimated by the average pairwise genomic distance) as a key metric of diversity. While whole-genome-sequencing (wgs) is increasingly affordable, it will be considerable time before the full diversity of life is represented by high-quality assembled genomes; even then, constant monitoring will still require repeated sampling of populations. In contrast, genome skimming (low-coverage, short-read wgs) is highly cost-effective but challenging to analyze because the coverage is too low for assembly and reliable error correction. Mature methods, such as Mash, exist for estimating pairwise genomic distances based on the Jaccard similarity of k-mer sets computed using sketching techniques. Some, such as Skmer, additionally model the impacts of low coverage. These methods have been successfully applied to assembly-free species identification and phylogenetics; however, their use in population genetics has been limited. This is because these methods implicitly treat genomes as haploid and heterozygosity confounds true estimates of genomic distance for diploid organisms. In this paper, we address this problem through a number of technical advances. First, we use coalescent theory to mathematically derive how the Jaccard index between two diploid samples changes with the scaled population size parameter ({theta}). Next, we derive an estimator that computes {theta} from the Jaccard index, in addition to several auxiliary variables, which we also estimate from the genome skims. The resulting method, DipSkmer, enables more accurate estimates of coverage, sequencing error, and pairwise nucleotide distance for diploid samples. Analyses of both simulated and empirical datasets show that for diploids and low distances (e.g.,

25.
arXiv (CS.CV) 2026-06-18

EDoF-NeRF: extended depth-of-field neural radiance fields using a coded aperture camera

We propose a method for extending the depth-of-field (DoF) to construct high-fidelity neural radiance fields (NeRF) – an emerging technique for rendering photorealistic novel views from a dataset of images captured at different viewpoints, based on implicit neural representations. The trade-off between DoF and light quantity is inherent not only in conventional cameras but also in NeRF, since the datasets used by NeRF are captured by these cameras. To address this issue, we introduce a coded aperture placed at the camera pupil, preserving spatial frequency components under defocused conditions. We develop a camera model incorporating coded apertures into NeRF, allowing direct input of coded images and enabling the generation of novel views with an extended DoF. We validate the proposed method, termed extended DoF-NeRF (EDoF-NeRF), through simulations and experiments, demonstrating its superior performance compared to conventional aperture cameras.