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 (quant-ph) 2026-06-19

Quantum models with the Yang-Lee phase transition

arXiv:2606.19732v1 Announce Type: cross Abstract: In this article, we present four different $1+1$D quantum models that realize the Yang-Lee (YL) phase transition under a deformation that preserves $PT$ symmetry. These are the antiferromagnetic Ising spin chain in transverse and longitudinal magnetic fields, the massive Schwinger model, the Blume-Capel model, and the three-state quantum clock model. Using the state-operator correspondence, we identify the YL critical point, compute the scaling dimensions of the lowest operators in each model, and find perfect agreement with the exact results for the YL criticality in two dimensions. Using bosonization for the Schwinger model and the Polyakov-Hubbard transformation for the other models, we show that in all of these quantum models the YL critical point is described, as expected, by a massless bosonic field with an $i \phi^3$ interaction. In the quantum clock model, this critical field interacts with a massive bosonic field, and we identify the massless and massive states in the Hamiltonian spectrum. In addition, we numerically compute the two-point function of $\phi$ at the Yang-Lee critical point and show that it grows with distance, in agreement with theoretical expectations.

02.
arXiv (CS.CV) 2026-06-18

Learned Radius Estimation for UDF-Based Point Cloud Reconstruction

Surface reconstruction from point clouds is important for consumer-grade 3D capture, including AR/VR and indoor scanning. Local-patch Unsigned Distance Field (UDF) methods are lightweight and generalizable, but their accuracy depends on the support radius, traditionally fixed or selected by a one-dimensional curvature heuristic that cannot capture heterogeneous local geometry. We propose a learned per-query radius selector that predicts a continuous support radius and plugs into a frozen LoSF-UDF backbone. The selector is trained using off-grid target radii obtained by parabolic interpolation of cached UDF error curves. Experiments show improved fine-scale reconstruction accuracy.

03.
arXiv (CS.CL) 2026-06-16

CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment

Malicious content generated from large language models (LLMs) could pose severe safety risks and ethical concerns. While existing LLM safety guardrails excel in English or multilingual settings, they lack adaptation to Chinese-specific regulatory policies, cultural context and linguistic nuances, failing to support fine-grained risk classification for diverse deployment needs. In this paper, we introduce a 5-macro, 31-micro category fine-grained risk taxonomy for Chinese scenarios, and build CHILLGuard: a dedicated Chinese LLM content safety guardrail. To address the critical scarcity of high-quality annotated Chinese safety data, we propose a scalable multi-stage data construction pipeline: we expand multi-source corpus via retrieval-augmented generation, generate implicit harmful samples through prompt engineering rewriting, and refine high-quality data via multi-model voting-based label calibration. Based on this, we build CHILLGuardTrain, a large-scale training set with 405,007 samples, and CHILLGuardTest, a rigorously curated annotated test set with 51,745 samples. We then train CHILLGuard on CHILLGuardTrain under a generator-classifier collaborative framework via Model-aware Direct Preference Optimization. Extensive experiments under multiple settings demonstrate the state-of-the-art performance of CHILLGuard, e.g., a 15.92% improvement of F1 score over Qwen3Guard-8B-Strict on our benchmark. We will release our resources at https://github.com/cswbyu/CHILLGuard.

04.
arXiv (CS.CL) 2026-06-25

Continual Knowledge Updating in LLM Systems: Learning Through Multi-Timescale Memory Dynamics

LLMs are trained once, then deployed into a world that never stops changing. External memory compensates for this, but most systems manage it explicitly rather than letting it adapt on its own. Biological memory works differently: coupled multi-timescale dynamics make new associations immediately usable, strengthen what repetition confirms, and let the rest fade. We argue that external memory should follow a similar principle. In Memini, this view takes the form of an associative memory that organizes knowledge as a directed graph. Each edge carries two coupled internal variables, one fast and one slow, following the Benna-Fusi model of synaptic consolidation. From this coupling, episodic sensitivity, gradual consolidation, and selective forgetting are expected to emerge as facets of a single mechanism, reframing external memory as a learning substrate that reorganizes through its own dynamics. This workshop article describes an early-stage conceptual design without experimental evaluation.

05.
arXiv (CS.AI) 2026-06-15

Regulating the Machine Contributor: Governance and Policy Alignment in Open Source

arXiv:2606.14594v1 Announce Type: cross Abstract: AI-assisted software development has moved from line-level autocomplete to agents that can plan changes, edit files, and submit pull requests with limited human supervision. Open-source software, however, evolves through a process designed for humans: contributor agreements, codes of conduct, and review norms all assume a legally accountable person who can attest to provenance and answer reviewer questions. Autonomous and semi-autonomous AI contributors strain those assumptions, and the 2025-2026 record of agent-driven incidents, AI-generated nuisance volume, and platform-level shutdowns shows that the gap is operationally consequential. Several open-source organisations have responded with contribution policies, but the result is fragmented, and its alignment with emerging AI governance frameworks (EU AI Act, NIST AI RMF with the UC Berkeley Agentic AI Profile, ISO/IEC 42001 and 23894) is unmapped at the contribution level. We compare policies across six organisations (SymPy, LLVM, matplotlib, OpenInfra, the Apache Software Foundation, and the Linux Foundation) using Most-Similar Systems Design with indicator-based coding and process tracing for SymPy and LLVM. From this we derive a six-dimensional taxonomy (disclosure, responsibility, human oversight, licensing, enforcement, maintainer workload), an ordinal Policy Maturity Score, and a mapping of documented agent incidents onto the dimensions each policy fails to govern. Aligning the dimensions with the regulatory frameworks above identifies overlapping gaps neither side currently closes, and we close by sketching the shape of a harmonised tiered framework and the empirical evaluation needed to calibrate it.

06.
medRxiv (Medicine) 2026-06-11

Foundation model-based tool for automated ulcerative colitis histology scoring demonstrates non-inferiority to pathologists across multiple scoring indices

In clinical trials for ulcerative colitis (UC), pathologists assess disease severity through standardized histological indices, including the Geboes Score, Robarts Histopathology Index (RHI), and Nancy Histologic Index (NHI). Despite strong associations with clinical outcomes, histologic scoring suffers from inter- and intra-reader variability, and consensus criteria for histologic remission remain uncertain. Through a consortium approach, we developed an artificial intelligence-based measurement (AIM) tool for scoring histology in UC mucosal biopsies (AIM-HI UC). This model, trained on a large dataset of UC biopsies (N=10,230), utilizes additive multiple instance learning models leveraging PLUTO, a pathology foundation model, that predict each of the Geboes subgrades, from which the Geboes grade-level score, RHI, and NHI can be calculated. Evaluation of this model on a standalone verification set including clinical trial specimens established algorithm non-inferiority and/or superiority relative to standard qualified pathologists through comparison of algorithm-consensus and pathologist-consensus agreement metrics (non-inferior if difference >-0.1, superior if difference >0, inclusive of confidence intervals). AIM-HI UC was determined to be non-inferior to pathologists (N=3) for the prediction of all seven Geboes subgrades, grade-level Geboes, RHI, NHI, histologic improvement (GS

07.
arXiv (quant-ph) 2026-06-19

Truncated Wigner dynamics of biclique quantum spin glasses

Authors:

arXiv:2606.20187v1 Announce Type: cross Abstract: Quantum spin glasses are often considered testbeds for studying quantum optimization algorithms and as such have been the subject of various quantum advantage claims. Here we investigate the near adiabatic dynamics of biclique quantum spin glasses within the (discrete) truncated Wigner approximation (TWA). Benchmarks on small systems show that TWA recovers sample-to-sample fluctuations of the Edwards-Anderson order parameter, over a wide range of annealing times, with increasing fidelity when the system size increases. We extract critical exponents from the Binder cumulant in line with theoretical expectations, reproducing recent quantum experiments. The computational cost of the method is minimal and it can easily be applied to tens of thousands of qubits.

08.
arXiv (CS.CL) 2026-06-16

FraudSMSWalker: Benchmarking Agentic Large Language Models for SMS-to-Webpage Fraud Detection

SMS fraud is increasingly cross-channel: a message directs the user to a webpage, and the final risk depends on how the SMS claim aligns with the page content and requested user action. However, existing evaluations either focus on message-only smishing classification or expose URL and domain cues that allow models to rely on reputation shortcuts. To address this gap, we introduce FraudSMSWalker, a controlled benchmark for URL-masked SMS-to-webpage fraud judgment. FraudSMSWalker contains 699 bilingual chains, including 332 fraudulent and 367 benign cases, across ten service scenarios. The model-visible input consists of the SMS context and sanitized webpage evidence, while raw URLs, hosts, domains, IPs, redirects, and reputation metadata are withheld. The benchmark further includes hard benign cases whose pages contain login, payment, verification, or account-management elements that are plausible under the service context but also appear in scam flows. We evaluate nine web agents under masked browser-agent protocols and conduct URL-visibility ablations. The results show that current agents can detect suspicious cues, but struggle to preserve benign recall and often produce positive predictions that are weakly supported by the observed evidence. These findings position FraudSMSWalker as a benchmark for measuring whether web agents can make fraud judgments that remain both accurate and evidence-grounded when direct reputation shortcuts are suppressed. The associated code and dataset are accessible at the \href{https://anonymous.4open.science/w/FraudMessageWalker-Bench}{anonymous link}.

09.
arXiv (CS.CV) 2026-06-16

VEPHand: View-Efficient Photometric Hand Performance Capture at Scale

Robust, high-fidelity 3D hand capture, while fundamental to digital human creation, remains challenging with practical multi-view systems that balance rich photometry with the geometric ambiguities of reconstruction arising from limited viewpoint density. This paper presents an end-to-end pipeline for dynamic hand performance capture and registration, specifically designed for view-efficient setups ($\sim$20 views). We address key challenges with two primary innovations. First, to overcome reconstruction difficulties like limited view overlap and background clutter, our mask-free neural method robustly extracts detailed hand geometry and appearance from unmasked images using scene parameterization and scenario-specific density regularization. Second, addressing registration challenges such as accurately capturing non-linear skin deformations and ensuring plausible results during severe self-contact, we propose a physics-inspired framework. It aligns reconstructions to a personalized hand model by optimizing intrinsic volumetric offsets within its canonical tetrahedral mesh, alongside pose parameters. This approach, supported by robust losses and optimization, captures fine surface deformations, ensures plausible results under severe articulation and self-contact, and demonstrates strong tolerance to input noise. We demonstrate the scalability and robustness of our automated pipeline on an extensive dataset of over 12,000 sequences, from which we also derive a large-scale, high-quality synthetic 2D/3D hand dataset for training downstream tasks. This showcases its effectiveness for single hands, intricate two-hand interactions, and natural hand-object manipulations. Our method achieves state-of-the-art reconstruction fidelity in view-efficient, unmasked scenarios and highly accurate registration. Our project page are available at https://zyshen021.github.io/VEPHand/.

10.
Nature (Science) 2026-06-10

A first-in-class pulsatile FXR agonist for bile-acid-related liver diseases

Authors:

Nuclear receptors are central regulators of metabolism1, yet therapeutic strategies that enforce continuous receptor activation frequently lead to reduced efficacy and unacceptable toxicity. Here we report a first-principles drug design strategy that aligns pharmacokinetics with physiological signalling cycles. We developed linafexor, a potent non-bile-acid agonist of the farnesoid X receptor (FXR)2; it is engineered for rapid systemic clearance, which enables pulsatile receptor activation that mirrors endogenous bile acid dynamics3–5. Linafexor has robust efficacy across multiple preclinical models of metabolic dysfunction-associated steatohepatitis6, liver fibrosis7, primary biliary cholangitis and primary sclerosing cholangitis8,9. Transcriptomic analyses reveal that, unlike long-acting FXR agonists10,11, linafexor preserves cyclic FXR signalling, avoids receptor downregulation and prevents broad transcriptional dysregulation. Direct manipulation of delivery patterns demonstrates that sustained FXR activation—independent of compound identity—induces severe toxicity, establishing activation duration as a determinant of therapeutic index. In phase 1 clinical studies (ClinicalTrials.gov; NCT05082779), linafexor administered once daily produces transient FXR pathway engagement, marked by (1) induction of FGF1912–14, a key endocrine mediator of bile acid feedback regulation; and (2) suppression of C415, an intermediate reflecting hepatic bile acid synthesis, with no treatment-related adverse events. Together, these findings identify pulsatile FXR activation as a mechanistically grounded and clinically translatable strategy, and establish linafexor as a first-in-class therapeutic for bile acid–related liver diseases. Linafexor is a rapidly cleared FXR agonist designed to mimic natural bile acid signalling, achieving transient receptor activation with strong efficacy and reduced toxicity in preclinical and early clinical studies.

11.
arXiv (CS.LG) 2026-06-17

Learning Survival Models with Right-Censored Reporting Delays

arXiv:2510.04421v3 Announce Type: replace-cross Abstract: Survival analysis provides statistical methods to model the time until an event occurs. Reporting delays arise when event times are not observed at their occurrence but are only revealed upon reporting. This issue is particularly critical for timely risk evaluation when the observation window is short due to administrative censoring. In this study, we incorporate right-censored reporting delays by jointly modeling parametric hazards for the event and reporting processes. We then construct a consistent estimator for the model parameters and develop a Monte Carlo expectation-maximization algorithm to compute it. To address the challenges posed by administrative censoring, we leverage these findings and propose a transfer-learning procedure. Experimental results demonstrate that our method improves the accuracy of timely risk evaluation under administrative censoring.

12.
arXiv (CS.CL) 2026-06-15

Be My Tutor: On-Policy Co-Distillation for Mutual LLM Improvement via Peer Feedback

We study multi-domain LLM training in which two models, each stronger in a different domain, co-evolve by tutoring each other through on-policy feedback. Unlike one-way distillation or single-model fine-tuning, our goal is mutual Pareto improvement: each model improves across domains without losing its original strength. To this end, we propose On-Policy Co-Distillation (OPCoD), where each student's self-distillation is conditioned on its own correct rollout and feedback from its peer. To make feedback exchange effective, OPCoD uses cognizance-based gating to decide when to give feedback and feedback anchoring to ground feedback in the problem. On Science Q\&A tasks, OPCoD consistently outperforms baselines and achieves Pareto improvement across all evaluated domain pairs and students.

13.
arXiv (CS.CL) 2026-06-17

LLM Features Can Hurt GNNs: Concatenation Interference on Homophilous Graph Benchmarks

Adding LLM-generated node features to graph neural networks (GNNs) is widely reported to improve accuracy on standard benchmarks. We document a contrasting observation: when LLM features are introduced through pure input concatenation (rather than joint training, distillation, or prompt-conditioning), they can systematically degrade accuracy on the same homophilous benchmarks where end-to-end LLM pipelines succeed. With an MLP backbone on the Planetoid public split and bag-of-words original features, concatenating SBERT-encoded GPT-4o-mini TAPE features reduces PubMed test accuracy by -17.0 +/- 0.3 pp and Cora by -4.3 +/- 0.6 pp (CiteSeer -0.6 +/- 0.8 pp, within seed noise). The drop attenuates as we relax each condition (GCN / GCNII / GAT backbones, random splits, smaller encoders) and reverses on medium-homophily WikiCS (+4.4 pp) and ogbn-arxiv (+11.7 pp). To predict when concatenation helps versus hurts, we report a simple measure of LLM-alone discriminability, Delta_sig. Across 9 datasets Delta_sig correlates with the concatenation cost more strongly than homophily at point estimate (r^2 = 0.38 vs. 0.06; N=9, bootstrap CIs overlap). The bootstrap-best change-point is tau = 13.8 pp, and the rule "Delta_sig

14.
medRxiv (Medicine) 2026-06-16

Prevalence and Correlates of Ideal Cardiovascular Health among Ugandan Adolescents: A Cross-Sectional Study

Introduction: Cardiovascular disease (CVD) risk factors often emerge during adolescence and track into adulthood, yet data on cardiovascular health (CVH) in sub-Saharan Africa remain limited. We assessed the prevalence and correlates of ideal CVH among Ugandan adolescents. Methods: We analysed baseline data of adolescents enrolled in a cluster-randomised controlled trial being conducted in urban (Kampala) and rural (Jinja) districts of Uganda. In this study, Ideal CVH was defined as meeting "ideal" status of 5-7 of the American Heart Association's Life's Simple 7 metrics. Random-effects logistic regression was used to identify factors associated with ideal CVH, accounting for village-level clustering. Results: We recruited 1316 participants with a mean age of 13.2 years, of whom 58.1% were female. Overall, the prevalence of ideal CVH was 66.8% (95% CI: 64.2% - 69.3%). The prevalence was higher in Jinja (74.4%, 95%CI: 70.9% - 77.7%) than Kampala (59.6%, 95%CI: 55.8%-63.2%) and the difference was evident (p

15.
arXiv (quant-ph) 2026-06-25

Quantum Error Correction-like Noise Mitigation for Wave-like Dark Matter Searches with Quantum Sensors

arXiv:2511.03253v2 Announce Type: replace-cross Abstract: We propose a quantum error correction-like noise mitigation protocol for enhancing the sensitivity of wave-like dark matter searches with quantum sensors. Our protocol uses multiple sensors to mitigate the noise affecting each sensor individually, allowing for the suppression of excitation noise that is parallel to the dark matter signal. We demonstrate that our protocol can improve the sensitivity to dark matter signals by a factor of $\sqrt{N}$, where $N$ is the number of sensors used, for small $N$. Furthermore, for sufficiently large $N$, we find that our protocol achieves the same performance as the standard quantum limit by the ideal measurement, which non-entangled sensors with parallel noise cannot reach due to the unknown phase of the dark matter field. Our work can be widely applied to various types of signals with unknown phases, and has the potential to enhance the sensitivity of quantum sensors such as arrays of resonant cavities.

16.
arXiv (CS.CL) 2026-06-18

RedactionBench

Large Language Models are increasingly applied to sensitive domains that require redaction of personally identifiable information (PII). While redacting PII is a data cleaning prerequisite, existing benchmarks conflate extraction mechanics with privacy semantics. A public phone number is not equivalent to a phone number in a medical record. Whether information constitutes a violation depends heavily on who holds it, why, and in what context, fundamentally differentiating redaction from simple entity recognition. Grounded in contextual integrity, we introduce RedactionBench, a manually annotated benchmark comprising 200 diverse documents across 11 domains, mostly seeded from real-world sources. We also introduce R-Score, a novel character-level metric that treats semantically similar redactions equally and nullifies shallow formatting choices, such as varying masking styles for phone numbers. Evaluations across Named Entity Recognition models, entity extraction Small Language Models, and frontier models equipped with agentic tools demonstrate that contextual redaction remains an unsolved problem. A human evaluation with over 80 users on RedactionBench reveals a stark dichotomy in privacy perceptions. Annotators show consensus with target labels for mandatory redactions (89.4 percent) and safe text preservations (94.1 percent), but fail to agree on contextual redactions (47.7 percent). This variance demonstrates the subjective nature of contextual privacy and motivates R-Score, which decouples contextual ambiguity from strict precision. We compare 35 models across families and report their performance in redacting PII. Finally, we release RedactionBench to establish a baseline for future privacy-preserving systems, hoping to inspire efficient model design and standardized evaluations.

17.
medRxiv (Medicine) 2026-06-10

Towards the Virtual Amyotrophic Lateral Sclerosis Patient: Inferring Cortical Excitability through Whole-Brain Dynamical Modeling

Amyotrophic lateral sclerosis (ALS) is increasingly recognized as a multisystem neurodegenerative disorder in which motor-neuron degeneration is accompanied by widespread alterations in cortical dynamics. Among its most reproducible neurophysiological signatures is cortical hyperexcitability, yet how this local excitability imbalance shapes distributed whole-brain activity remains poorly understood. Here, we combined source-reconstructed resting-state MEG data, tractography-informed whole-brain modeling, and simulation-based inference to investigate whether ALS-related alterations in large-scale brain dynamics can be mechanistically explained by changes in cortical excitability. First, we characterized empirical brain dynamics using complementary features spanning regional activity amplitude and variability, functional connectivity, and avalanche-based metrics. These analyses revealed significant alterations in ALS patients relative to healthy controls, as well as associations with clinical impairment and disease staging. To mechanistically interpret these changes, we employed a reduced Wong-Wang whole-brain model in which local recurrent excitation modulates emergent large-scale neural dynamics. Simulations showed that increasing excitability systematically reproduced the empirical dynamical signatures observed in ALS. We then applied a simulation-based inference framework to estimate latent excitability parameters directly from empirical observations. Whole-brain model inversion revealed increased excitability in ALS patients compared with controls. The recovered excitability parameter was associated with disease staging, supporting its clinical relevance as a model-derived descriptor of ALS progression. Finally, by extending the model to estimate frontal and non-frontal excitability separately, we found that ALS-related alterations were predominantly associated with increased frontal excitability, whereas non-frontal regions appeared comparatively less affected. The recovered parameters related to disease staging. Together, these findings provide a mechanistic framework linking altered large-scale brain dynamics in ALS to selective cortical hyperexcitability, explaining how local excitability changes can give rise to global network reorganization. More broadly, they show how computational model inversion can recover latent multiscale pathophysiological processes from empirical neural recordings, offering a non-perturbative alternative to complex experimental paradigms typically required to causally probe local-to-global mechanisms.

18.
arXiv (CS.AI) 2026-06-11

WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces

arXiv:2606.09426v2 Announce Type: replace Abstract: Computer-use agents (CUAs) increasingly operate in runtimes that combine visual desktop control, command-line execution, code editing, browsers, and external tools. Existing benchmarks, however, often evaluate these interfaces as separable capabilities, leaving long-horizon cross-interface orchestration under-tested. Thus, we introduce WeaveBench, a long-horizon hybrid-interface benchmark with 114 tasks across 8 real-world work domains, grounded in real user requests and publicly verifiable artifacts. Each task requires agents to combine GUI observations/actions with CLI/code operations within a single trajectory. We evaluate these tasks on a real Ubuntu desktop inside deployed CLI-agent runtimes, augmented with a minimal desktop-control plugin. We also propose a companion trajectory-aware judge that inspects deliverables, files, screenshots, logs, and action traces, while detecting shortcut behaviors such as fabricated visual evidence or hard-coded metrics. Across frontier model-runtime pairings, the best PassRate reaches only 41.2%, showing the benchmark remains far from saturated. The trajectory-aware judge further reveals that outcome-only grading substantially overestimates agent performance. Overall, WeaveBench exposes a critical gap in CUA evaluation and provides an effective testbed to measure whether agents can orchestrate GUI, CLI, and code operations across long-horizon real-world tasks.

19.
arXiv (CS.CL) 2026-06-15

Did You Forget What I Asked? Prospective Memory Failures in Large Language Models

Authors:

Large language models often fail to satisfy formatting instructions when they must simultaneously perform demanding tasks. We study this behaviour through a prospective memory inspired lens from cognitive psychology, using a controlled paradigm that combines verifiable formatting constraints with benchmark tasks of increasing complexity. Across three model families and over 8,000 prompts, compliance drops by 2-21% under concurrent task load. Vulnerability is highly type-dependent: terminal constraints (requiring action at the response boundary) degrade most, with drops up to 50%, while avoidance constraints remain comparatively robust. A salience-enhanced format (explicit instruction framing plus a trailing reminder) recovers much of the lost compliance, restoring performance to 90-100% in many settings. Interference is bidirectional: formatting constraints can also reduce task accuracy, with one model's GSM8K accuracy dropping from 93% to 27%. In additional stacking experiments, joint compliance declines sharply as constraints accumulate. All results use deterministic programmatic checkers without an LLM-as-judge component on publicly available datasets.

20.
arXiv (CS.CV) 2026-06-25

Neural Network Quantization by Learning Low-Loss Subspaces

Neural network quantization aims to find a discrete representation of parameters that preserves the performance of a full-precision (FP) model as faithfully as possible. Enforcing discrete constraints perturbs parameters away from a well-optimized minimum, generally resulting in performance degradation. Recent studies indicate that low-loss FP solutions are not isolated, but instead belong to connected low-loss subspaces of the loss landscape, where the loss maintains nearly the same minimum value. Models sampled from these subspaces are diverse and retain high accuracy. This raises the question: can a quantized model be constructed to lie within a low-loss subspace of the FP model, thereby automatically preserving performance? We address this question by learning quantization-aware linear paths in weight space optimized to minimize loss. We demonstrate that the midpoint of the resulting subspace is, by design, quantization-friendly and that its direct quantization yields performance comparable to that of quantization-aware training. The proposed procedure offers a novel perspective on weight quantization and, in contrast to conventional methods, neither relies on the straight-through estimator nor involves explicit discretization during training.

21.
arXiv (CS.CL) 2026-06-15

Implicit Reasoning for Large Language Model-based Generative Recommendation

Large Language Models (LLMs) are increasingly adopted as backbones for Generative Recommendation (GR), promising access to pretrained world knowledge. Yet reliably invoking this knowledge for GR remains poorly understood. A key obstacle is that LLM-based GR typically represents items with Semantic IDs (SIDs), disrupting LLMs' natural-language reasoning interface because these tokens are unseen by the LLM during pretraining. Existing approaches address this with expensive multi-stage pipelines that ground SIDs and elicit explicit rationales, but offer limited insight into when and why each stage is necessary. In this work, we systematically decompose explicit reasoning training pipelines for LLM-based GR, revealing three key limitations: weakened world-knowledge verbalization, misalignment between SID and natural-language token embedding spaces, and sensitivity to rationale quality, all of which hurt explicit reasoning performance. To circumvent these issues, we propose PauseRec, a lightweight implicit reasoning paradigm tailored for GR. PauseRec is exceptionally practical, avoiding costly reasoning trace acquisition and reasoning alignment training, leading to a multitude of benefits: (1) it outperforms standard explicit CoT methods by up to 6.22%, (2) it reduces training cost by up to 65% GPU hours, and (3) it speeds up inference by up to 71.3%. These results position PauseRec as a lightweight alternative to explicit rationale generation, enabling more effective and efficient LLM-based GR.

22.
arXiv (CS.AI) 2026-06-12

Cross-Model Disagreement as a Label-Free Correctness Signal

arXiv:2603.25450v2 Announce Type: replace Abstract: Detecting when a language model is wrong without ground truth labels is a fundamental challenge for safe deployment. Existing approaches rely on a model's own uncertainty – such as token entropy or confidence scores – but these signals fail critically on the most dangerous failure mode: confident errors, where a model is wrong but certain. In this work we introduce cross-model disagreement as a correctness indicator – a simple, training-free signal that can be dropped into existing production systems, routing pipelines, and deployment monitoring infrastructure without modification. Given a model's generated answer, cross-model disagreement computes how surprised or uncertain a second verifier model is when reading that answer via a single forward pass. No generation from the verifying model is required, and no correctness labels are needed. We instantiate this principle as Cross-Model Perplexity (CMP), which measures the verifying model's surprise at the generating model's answer tokens, and Cross-Model Entropy (CME), which measures the verifying model's uncertainty at those positions. Both CMP and CME outperform within-model uncertainty baselines across benchmarks spanning reasoning, retrieval, and mathematical problem solving (MMLU, TriviaQA, and GSM8K). On MMLU, CMP achieves a mean AUROC of 0.75 against a within-model entropy baseline of 0.59. These results establish cross-model disagreement as a practical, training-free approach to label-free correctness estimation, with direct applications in deployment monitoring, model routing, selective prediction, data filtering, and scalable oversight of production language model systems.

23.
arXiv (CS.CL) 2026-06-24

Benchmarking LLMs' Mathematical Reasoning with Unseen Random Variables Questions

Recent studies have raised significant concerns regarding the reliability of current mathematics benchmarks, highlighting issues such as simplistic design and potential data contamination. Consequently, developing a reliable benchmark that effectively evaluates large language models' (LLMs) genuine capabilities in mathematical reasoning remains a critical challenge. To address these concerns, we propose RV-Bench, a novel evaluation methodology for Benchmarking LLMs with Random Variables in mathematical reasoning. Specifically, we build question-generating functions to produce random variable questions (RVQs), whose background content mirrors original benchmark problems, but with randomized variable combinations, rendering them "unseen" to LLMs. Models must completely understand the inherent question pattern to correctly answer RVQs with diverse variable combinations. Thus, an LLM's genuine reasoning capability is reflected through its accuracy and robustness on RV-Bench. We conducted extensive experiments on over 30 representative LLMs across more than 1,000 RVQs. Our findings propose that LLMs exhibit a proficiency imbalance between encountered and ``unseen'' data distributions. Furthermore, RV-Bench reveals that proficiency generalization across similar mathematical reasoning tasks is limited, but we verified it can still be effectively elicited through test-time scaling.

24.
arXiv (CS.CL) 2026-06-15

Large Language Model Agents Are Not Always Faithful Self-Evolvers

Self-evolving large language model (LLM) agents continually improve by accumulating and reusing past experience, yet it remains unclear whether they faithfully rely on that experience to guide their behavior. We present the first systematic investigation of experience faithfulness, the causal dependence of an agent's decisions on the experience it is given, in self-evolving LLM agents. Using controlled causal interventions on both raw and condensed forms of experience, we comprehensively evaluate four representative frameworks across 13 LLM backbones and 9 environments. Our analysis uncovers a striking asymmetry: while agents consistently depend on raw experience, they often disregard or misinterpret condensed experience, even when it is the only experience provided. This gap persists across single- and multi-agent configurations and across backbone scales. We trace its underlying causes to three factors: the semantic limitations of condensed content, internal processing biases that suppress experience, and task regimes where pretrained priors already suffice. These findings challenge prevailing assumptions about self-evolving methods and underscore the need for more faithful and reliable approaches to experience integration.

25.
medRxiv (Medicine) 2026-06-11

Dissecting the functional landscape of rare diseases through genomic variation in a heterogeneous cohort of 11,000 patients

Rare diseases (RDs) remain a major diagnostic challenge. Genetic and phenotypic heterogeneity, incomplete knowledge of disease mechanisms, and limitations in variant clinical interpretation leave many patients without a molecular diagnosis. Meanwhile, the growing volume of genomic data generated in clinical practice offers an opportunity to develop data-driven methodologies for exploring disease mechanisms and improving the reanalysis of unsolved cases. We aggregated real-world genomic data from 11,084 unrelated patients with suspected RD. Patients were clinically classified into 122 diseases. We built a multi-disease genomic variant frequency database (FJD-DB), which enabled the development of variant and gene-disease association scores by means of case-control subcohort comparisons across 32 disease groups. Functional enrichment analyses were then used to highlight disease-associated protein domains, pathways, biological processes, and phenotypes. Finally, the resulting knowledge was integrated into a data-driven framework for the guided reanalysis of unsolved RD patients applied to Inherited Retinal Dystrophies (IRD) patients as first use case. FJD-DB contained more than 45 million unique variants, including ~185,000 potentially pathogenic variants. Disease-specific analyses identified disease-associated pathogenic variants and highlighted both established and candidate disease genes. We detected 179 significantly enriched protein domains across 23 diseases, 124 Human Phenotype Ontology terms across 13 diseases, 79 Reactome pathways across 10 diseases, and 72 Gene Ontology biological processes across 8 diseases, revealing highly disease-specific functional signatures. Integration of disease-specific variant, gene, and functional association signals enabled the development of a data-driven framework for guided reanalysis of unsolved RD cases. Applied to more than 1,100 unsolved IRD cases, the framework generated clinically relevant findings in 26 patients, including four molecular diagnoses, seven candidate diagnoses, and 15 cases upgraded from non-informative findings to variants of uncertain significance. Aggregated real-world genomic data can be leveraged to identify disease-associated molecular signals generating novel biological hypotheses. A unified analytical framework provides a scalable strategy for knowledge discovery and guided reanalysis, facilitating the identification of overlooked and potentially novel genetic causes of RDs.