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.
medRxiv (Medicine) 2026-06-18

A Brain-Aging Transcriptomic Signature Reclassifies WHO Glioma Grade and Predicts Survival Independently of IDH Status: A Multi-Cohort Study

Background Despite WHO grade and IDH status, significant survival differences remain in diffuse gliomas. We hypothesized that a brain-aging transcriptomic signature, reflecting neuroinflammation, myeloid infiltration, and synaptic loss, would independently predict survival and allow for molecular reclassification. Methods A neurodegeneration score was derived via PCA of brain MRI volumes from 1,057 OASIS-3 subjects and projected onto 888 TCGA-LGG/GBM (discovery) and 693 CGGA gliomas (validation). A 14-gene signature of glial/myeloid (GFAP, AQP4, TYROBP, TREM2, C1QA, CD68, ITGAM) and neuronal (SYP, DLG4, GRIN1, GRIA1, SNAP25, SYN1, RBFOX3) genes were computed. Elastic-net Cox regression identified a 3-gene panel (C1QA, CD68, GRIA1). Kaplan-Meier, multivariate Cox, decision curve, and single-cell RNA-seq analyses were performed. Results High brain-aging scores predicted poorer overall survival (p < 0.0001) and remained an independent prognostic factor after adjusting for WHO grade and IDH status (z = 4.72, p < 0.001); chronological age was non-significant (p = 0.231). In IDH-mutant gliomas, significance was confirmed in both cohorts (TCGA p = 0.027; CGGA p < 0.0001). Bidirectional reclassification showed high-risk Grade 2 tumors with Grade 3-like survival (p = 0.00089), and indolent Grade 3 tumors resembling Grade 2 by Ki-67. Single-cell RNA-seq confirmed macrophage localization of signature genes; DCA demonstrated net benefit over grade alone at 5-30% probability thresholds. Conclusions A brain-aging transcriptomic signature independently predicts glioma survival beyond WHO grade and IDH status, validated in an independent Chinese cohort, with clinical utility for identifying high-risk Grade 2 and sparing over-treatment of indolent Grade 3 tumors.

02.
arXiv (CS.CL) 2026-06-12

MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes

As AI systems progress, we rely more on them to make decisions with us and for us. To ensure that such decisions are aligned with human values, it is imperative for us to understand not only what decisions they make but also how they come to those decisions. Reasoning language models, which provide both final responses and (partially transparent) intermediate thinking traces, present a timely opportunity to study AI procedural reasoning. Unlike math and code problems which often have objectively correct answers, moral dilemmas are an excellent testbed for process-focused evaluation because they allow for multiple defensible conclusions. To do so, we present MoReBench: 1,000 moral scenarios, each paired with a set of rubric criteria that experts consider essential to include (or avoid) when reasoning about the scenarios. MoReBench contains over 23 thousand criteria including identifying moral considerations, weighing trade-offs, and giving actionable recommendations to cover cases on AI advising humans moral decisions as well as making moral decisions autonomously. Separately, we curate MoReBench-Theory: 150 examples to test whether AI can reason under five major frameworks in normative ethics. Our results show that scaling laws and existing benchmarks on math, code, and scientific reasoning tasks fail to predict models' abilities to perform moral reasoning. Models also show partiality towards specific moral frameworks (e.g., Benthamite Act Utilitarianism and Kantian Deontology), which might be side effects of popular training paradigms. Together, these benchmarks advance process-focused reasoning evaluation towards safer and more transparent AI.

03.
arXiv (CS.AI) 2026-06-19

Physical Atari: A Robust and Accessible Platform for Real-time Reinforcement Learning on Robots

arXiv:2606.19357v1 Announce Type: cross Abstract: We built a robot called the Robotroller that actuates an Atari CX40+ controller and a device called the Atari Devbox that renders the game frame and the reward signal from the Arcade Learning Environment on a screen. The Robotroller and the Atari Devbox, together with an off-the-shelf camera and a desktop computer, constitute a system that can be used to study reinforcement learning algorithms in the physical world. We call the full system Physical Atari. In this paper, we detail the key decisions that make Physical Atari a robust and accessible platform. To make the system robust, we designed the Robotroller so that all movement is done through bearings, which reduces wear. Additionally, we wrote software that monitors the state of the servos at a high frequency and intervenes to limit stress. To make the system accessible, we used affordable off-the-shelf components and parts that can be manufactured using consumer 3D printers. Physical Atari can be built for under $1,000 and has been used for weeks of non-stop reinforcement learning experiments without any mechanical failures. We used it to validate that reinforcement learning algorithms can learn directly on robots and show that even small distribution shifts between learning and deployment can significantly degrade the performance of policies. Our results underscore the importance of on-device adaptation for strong performance on robots.

04.
arXiv (quant-ph) 2026-06-24

Quantum algorithm for Valiant-Vazirani reduction

arXiv:2606.18428v2 Announce Type: replace Abstract: There is growing interest in extensions of the standard model of gate-based quantum computation to include auxiliary degrees of freedom evolving according to a nonlinear Schrödinger equation. By reducing the Boolean satisfiability problem SAT to quantum state discrimination, Abrams and Lloyd argued that the right type of nonlinearity can be used to solve NP and #P problems in polynomial time, at least in an idealized noise-free limit. For practical implementation, however, we are restricted to simulated and emergent nonlinearities, such as that appearing in mean field models for ultracold atoms and similar ensembles. A prominent example is the torsion model, which arises in two-component Bose-Einstein condensates and spin models with all-to-all Ising interaction. But torsion-based state discrimination appears to fall short of solving SAT. Here we close this gap by constructing the filtered oracle of the Valiant-Vazirani theorem, providing a randomized polynomial-time reduction from SAT to UNIQUE SAT, a promise problem where there is at most 1 satisfying assignment. In the noise-free limit, the UNIQUE SAT problem can be solved in polynomial time using torsion nonlinearity. Quantum Valiant-Vazirani reduction is no faster than the efficient classical version, but a fault-tolerant implementation coupled to a nonlinear quantum coprocessor simulating torsion would enable polynomial time solution to NP (but not #P) problems.

05.
arXiv (CS.AI) 2026-06-16

Automating Low-Risk Code Review at Meta: RADAR, Risk Calibration, and Review Efficiency

arXiv:2605.30208v2 Announce Type: replace-cross Abstract: AI-assisted coding tools have altered software production. At Meta, significant lines of code per human-landed diff grew by 105.9% year over year and per-developer diff volume rose 51%, with agentic AI responsible for over 80% of that growth. Meanwhile, the share of diffs receiving timely review has declined, exposing a widening gap between code supply and reviewer bandwidth. We ask three questions that progress from feasibility through calibration to impact: (1) can risk-stratified automation operate at scale across diverse organizations, (2) how does tuning the risk threshold affect the trade-off between automation yield and safety, and (3) to what extent does automated review reduce end-to-end latency for AI-generated changes? We deployed RADAR (Risk Aware Diff Auto Review), a multi-stage funnel that classifies each diff by authorship and source type, applies eligibility gates, static heuristics, a machine-learned Diff Risk Score, LLM-based Automated Code Review, and deterministic validation before landing qualifying changes. We evaluate RADAR through telemetry covering 535K+ RADAR-reviewed diffs, observational before-after comparisons for policy changes, and difference-in-differences analysis of efficiency outcomes. RADAR has reviewed 535K+ diffs and landed 331K+. Relaxing the Diff Risk Score threshold from the 25th to the 50th percentile increased the approve rate to 60.31%. The revert rate for RADAR-reviewed diffs is 1/3 that of non-RADAR diffs, and the Production Incident rate is 1/50 that of non-RADAR diffs. RADAR reduces median time to close by over 330% and median diff review wall time by 35%. Risk-aware layered automation can materially reduce review bottlenecks created by AI-driven code growth without compromising production safety.

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

Resourcefulness of non-classical continuous-variable quantum gates

arXiv:2410.09226v4 Announce Type: replace Abstract: In continuous-variable quantum computation, identifying key elements that enable a quantum computational advantage is a long-standing issue. Starting from the standard results on the necessity of Wigner negativity, we develop a comprehensive and versatile approach in which the techniques of $(s)$-ordered quasiprobabilities are exploited to provide rigorous statements on the simulability of photonic quantum circuits consisting of previously characterized gates and thereby identifying the contribution of each quantum gate to the potential achievement of quantum computational advantage. This is achieved by means of an analysis of the so-called transfer function, allowing us to highlight the resourcefulness of a gate set. As such this technique can be straightforwardly applied to current continuous-variables quantum circuits, while also constraining the tolerable amount of losses above which any potential quantum advantage can be ruled out. We use $(s)$-ordered quasiprobability distributions on phase-space to capture the non-classical features in the protocol, and focus our technique entirely on the ordering parameter $s$. This allows us to highlight the resourcefulness and robustness to loss of a universal set of unitary gates comprising three distinct Gaussian gates and any non-Gaussian unitary gate, providing important insight on the role of non-Gaussianity.

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

Numbers Already Carry Their Own Embeddings

arXiv:2606.14108v1 Announce Type: cross Abstract: We introduce Adelic operation-preserved embeddings (AOE), a training-free representation that captures both a number's real value and its modular (p-adic) signatures. This construction preserves additive and multiplicative structure by design, turning numerical input into embeddings that "speak in the language of mathematics." Unlike prior approaches that rely on task-specific retraining, AOE is plug-and-play and drops seamlessly into existing architectures. On algebraic combinatorics benchmarks, it delivers consistent gains including the first-ever perfect accuracy on the Weaving Pattern task-while suggesting a principled path forward for overcoming the long-standing "number problem" in AI.

08.
Nature (Science) 2026-06-10

Measurement of reactor neutrino oscillation with the first JUNO data

Neutrino oscillations (see refs. 1,2 and references therein), a quantum effect manifesting at macroscopic scales, are governed by lepton flavour mixing angles and neutrino mass-squared differences3 that are fundamental parameters of particle physics, representing phenomena beyond the Standard Model. Precision measurements of these parameters are essential for testing the completeness of the three-flavour framework, determining the mass ordering of neutrinos and probing possible new physics. The Jiangmen Underground Neutrino Observatory (JUNO)4 is a 20-ktonne liquid-scintillator detector located 52.5 km from multiple reactor cores, designed to resolve the interference pattern of reactor neutrinos with sub-percent precision5,6. Here we report, using the first 59.1 days of data collected since detector completion in August 2025, the first simultaneous high-precision determination of two neutrino oscillation parameters, $${\sin }^{2}{\theta }_{12}=0.3092\,\pm \,0.0087$$ and $$\Delta {m}_{21}^{2}=(7.50\,\pm \,0.12)\times 1{0}^{-5}\,{\mathrm{eV}}^{2}$$ for the normal mass ordering scenario, improving the precision by a factor of 1.6 relative to the combination of all previous measurements. These results advance the basic understanding of neutrinos, validate the design of the detector and indicate the readiness of JUNO for resolving the neutrino mass ordering with a larger dataset. The rapid achievement with a short exposure highlights the potential of JUNO to push the frontiers of precision neutrino physics and paves the way for its broad scientific programme. The first data of the Jiangmen Underground Neutrino Observatory deliver high-precision neutrino oscillation parameters, improving measurements and demonstrating readiness to determine neutrino mass ordering.

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

Distilling latent electrostatics from foundation machine learning interatomic potentials

arXiv:2606.15001v1 Announce Type: cross Abstract: Foundation machine learning interatomic potentials (MLIPs) have enabled atomistic simulations across broad regions of chemical and materials space, but many remain computationally expensive and lack explicit electrostatics, limiting their use for systems governed by long-range interactions and electrical response. Previously, we introduced Latent Ewald Summation (LES), which learns latent atomic charges and long-range electrostatics from density functional theory (DFT) energy and force labels alone. Here, we use LES to extract electrostatics that are latent in foundation models: energies and forces predicted by a teacher model are used to train a lightweight LES-augmented student MLIP, with optional fine-tuning on additional DFT data. The resulting models reduce computational cost while providing access to Born effective charge tensors, and infrared spectra. We benchmark student models distilled from a broad set of foundation MLIPs, including UMA, MACE, Orb, eSEN, GemNet-OC, PET, and EquiformerV2-based models, against experimental infrared spectra for liquid water, concentrated hydrochloric acid, and the anatase TiO2(101)-water interface. Across these systems, electrostatic response can be extracted from most foundation MLIPs. The benchmark further shows that the underlying DFT level and dataset used to train the teacher model play a larger role than architecture in determining electrostatic and spectroscopic accuracy. For the TiO2-water interface, fine-tuning with a modest amount of higher-level DFT data improves structural and infrared predictions. LES-based distillation therefore provides a practical route for converting foundation MLIPs into efficient, electrically responsive models, while also testing the physical fidelity encoded in foundation models.

10.
arXiv (CS.CV) 2026-06-16

Automated 3D Kinematic Monitoring for Circadian Activity and Anomaly Detection in Juvenile Fish

Precision aquaculture faces a "phenotyping bottleneck" in tracking high-resolution behavioral traits, as conventional methods cannot quantify instantaneous three-dimensional (3D) physical exertion. To address this, we present a high-throughput 3D behavioral phenotyping framework integrating deep learning object detection with binocular stereo vision for real-time monitoring of juvenile tilapia in high-density environments. The system automates non-contact body length estimation and reconstructs 3D swimming trajectories from absolute spatial coordinates. By eliminating 2D perspective distortions, this approach precisely quantifies 3D velocity and acceleration, marking the first estimation of true physical swimming speeds in free-roaming juveniles. Results show the framework successfully establishes circadian locomotor baselines, serving as an early warning system for physiological stress and providing an objective metric for fish vitality.

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

LLMs Struggle to Measure What Distinguishes Students of Different Proficiency Levels: A Study of Item Discrimination in Reading Comprehension Assessment

Item discrimination is a fundamental psychometric property of educational assessment, which measures whether an item meaningfully distinguishes students with higher proficiency from students with lower proficiency. While various existing works have explored whether large language models (LLMs) can estimate item difficulty, it remains unclear whether they can capture item discrimination. In this work, we evaluate 42 proprietary and open-weight LLMs in zero-shot settings using two complementary approaches: direct discrimination prediction, where models explicitly estimate an item's discrimination value from its content, and response-based Classical Test Theory (CTT) calibration, where LLM answers are treated as synthetic student responses to compute discrimination scores. Our results show that direct prediction yields weak alignment with human-calibrated discrimination: the best-performing model reaches only a Spearman correlation of 0.152. Response-based CTT calibration provides a stronger but still limited signal, with the all-persona synthetic respondent pool reaching a Spearman correlation of 0.241. These findings highlight item discrimination as an open challenge for LLM-based psychometric evaluation: current LLMs contain non-random discrimination-relevant signal, but they do not yet reliably capture how assessment items distinguish human students.

12.
medRxiv (Medicine) 2026-06-22

Accounting for uncertainty in the expected treatment effect substantially increases the sample size required for randomised trials: implications for the feasibility of clinical trials in anaesthesia and critical care

Background Multicentre trials in anaesthesia and critical care report low rates of statistically significant differences. This finding may partly reflect conventional sample size methods, which assume a fixed treatment effect. Assurance methods use a design prior to represent uncertainty in the expected treatment effect, which may provide a more realistic way of estimating sample sizes. Methods We calculated power curves across a range of effect sizes, design priors, and sample sizes using frequentist and Bayesian assurance methods and compared the sample sizes required to achieve 80% and 90% power to the conventional method. We standardised the design priors across effect sizes using the coefficient of variation. We derived a theoretical limit for achievable power. We validated a normal approximation to the Bayesian posterior distribution. Results Frequentist and Bayesian assurance methods produced similar power curves across all scenarios. At a coefficient of variation of 0.5 - reflecting realistic prior uncertainty in the expected effect size - both methods required sample sizes that were approximately 1.5 to 3.5 times larger than the conventional method. The theoretical power limit depends only on the coefficient of variation of the design prior and holds true across all effect sizes. The normal approximation to the Bayesian posterior distribution matched the results obtained from Markov chain Monte Carlo sampling. Conclusions Incorporating clinical uncertainty in the expected effect size substantially increases the sample size required to achieve adequate power, which has important implications for the feasibility of randomised trials in anaesthesia and critical care.

13.
arXiv (math.PR) 2026-06-17

Convergence Analysis of the Random Bisection Method

arXiv:2603.20483v2 Announce Type: replace-cross Abstract: We propose a generalized version of the bisection method where the cutting point between the two subintervals is chosen at random following an arbitrary distribution. We compute expected convergence rates with respect to any arbitrary a priori distribution for the position of the root in the initial interval and proved that it depends only on the the expectation $\mathbb{E}[c(1-c)]$ of the cut $c$. We also provide a generalization of the method for $K$ random cuts and study its convergence properties. Most probabilistic derivations are kept fairly simple for the ease of understanding of a larger audience. Our theoretical results are then validated numerically using statistical simulation.

14.
arXiv (CS.AI) 2026-06-15

SEVRA-BENCH: Social Engineering of Vulnerabilities in Review Agents

arXiv:2606.13757v1 Announce Type: cross Abstract: Large language model (LLM) reviewers are increasingly used in pull-request (PR) workflows, where their approvals help decide which code is merged into a repository. This raises a question that benchmarks for static vulnerability detection or code generation do not address: can an automated reviewer reject a malicious contribution when the attacker controls both the code change and the accompanying PR text? We introduce SEVRA-BENCH (Social Engineering of Vulnerabilities in Review Agents), a benchmark that measures how often an automated reviewer approves such adversarial pull requests. Each malicious PR in SEVRA-BENCH is built from a real project commit that previously fixed a vulnerability listed in the Common Vulnerabilities and Exposures (CVE) database. We automatically invert that fix to restore the original vulnerable code and submit it as a pull request wrapped in one of 15 social-engineering framings, which vary the claims made, the supporting evidence, the urgency conveyed, signals of prior approval, and appeals to authority. SEVRA-BENCH contains 1,062 malicious PRs drawn from Common Vulnerabilities and Exposures (CVE)-linked fixes across the top 10 entries of the 2025 Common Weakness Enumeration (CWE) Top 25. In a realistic setting, we evaluate 8 current LLMs as code review agents on PRs that introduce vulnerabilities previously reported in public disclosures. Our results reveal a sharp gap in security capabilities between closed- and open-source models. We hope SEVRA-BENCH will serve as a valuable resource for advancing open-source models and narrowing this gap.

15.
arXiv (CS.CL) 2026-06-11

FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse

Large Language Model (LLM)-based multi-agent systems are increasingly powerful, but current agentic workflow optimization paradigms make an unsatisfying trade-off. Task-level methods spend substantial offline compute yet deploy only a single workflow, leaving complementary candidates unused, while query-level methods synthesize a new workflow per query at substantial inference cost. Our motivating analysis shows these paradigms are more complementary than competing: workflows discovered during offline search often solve different subsets of queries, and many queries handled by expensive query-level generation can already be solved by cheaper precomputed workflows. This suggests a different objective: rather than searching for one universally best workflow or regenerating one per instance, we should build a compact bank of reusable, complementary workflows and select among them adaptively at inference time. Doing so requires solving three coupled problems: generating complementary rather than redundant candidates, compressing them into a small deployable portfolio, and assigning each query to the right workflow under a performance-cost trade-off. To this end, we present FlowBank, a three-stage framework for portfolio-based agentic workflow optimization. Diversifying proposes DiverseFlow to steer search toward under-covered queries and produce a high-coverage candidate pool. Curating proposes CuraFlow to compress this pool into a compact portfolio with minimal redundancy. Matching casts deployment as edge-value prediction on a query-workflow bipartite graph and routes each incoming query to the portfolio member with the best predicted utility. Across five benchmarks, FlowBank achieves the highest average score among the evaluated methods while remaining cost-competitive, improving over the strongest automated and handcrafted baselines by 4.26% and 14.92% relative, respectively.

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

SCAN: A Decision-Making Framework for Effective Task Allocation with Generative AI

arXiv:2606.15601v1 Announce Type: cross Abstract: We introduce SCAN – a human-centric decision-making framework to facilitate learners for effective task allocation with Generative Artificial Intelligence (GenAI) based on Vygotsky's Zone of Proximal Development and Metacognition. In SCAN, we systematize and formalize AI-human interaction by introducing a task-identification approach with four "sub-zones": Substitute, Complement, Aid, and Non-negotiable. After describing the four sub-zones, we demonstrate how SCAN framework can be applied for knowledge workers in the workplace and students in education to metacognitively "scan" their use of Generative AI. We then discuss how such framework can be related to cognitive load theory, cognitive offloading, sycophancy, three decision-making modes in human-AI interactions (automation, augmentation, and collaboration), future of work such as upskilling and deskilling, and how it accounts for both human-human and human-AI learning. We propose that SCAN offers a great starting point before discussing whether GenAI complements or replaces our abilities when completing a task, with a general objective of sustaining lifelong learning, and a specific goal of reaching hybrid intelligence.

17.
bioRxiv (Bioinfo) 2026-06-20

A network approach to DNA methylation clocks

Biological age predicts health and lifespan better than chronological age, but remains difficult to measure. One leading molecular proxy for biological age is DNA methylation, which underlies age predictors known as "clocks". These clocks use penalized linear regression to predict chronological age from methylation levels using selected cytosine–guanine pairs (CpGs) along DNA. Although they predict chronological age within a few years and track mortality risk, there are several issues. Different clocks share a vanishingly small number of CpG sites, many of which show weak associations with age. Also, the clocks often do not transfer across methylation array platforms. This paper takes a network approach to better understand these issues. By using 12 public datasets from human blood, we build a co-methylation network of the sites that show the strongest age correlation. After pruning weak links, we find that it has a small number of large modules of covarying CpGs surrounded by many small modules and singleton sites. These modules are biologically interpretable, as they are associated with CpG island contexts and enriched for distinct Gene Ontology functions. We also map five established clocks onto this network (Horvath, Hannum, AltumAge, Skin & Blood, and Han) and find that they select some CpGs from the same module. This suggests that they are more similar than they appear. The network structure also suggests new ways to build clocks. A simple clock that retains one CpG per module matches the performance of established clocks. A second one, built from module-level principal components, outperforms all five established clocks in three validation cohorts and is transferable across array platforms (Illumina Infinium Methylation 450K or EPIC arrays). Overall, the network perspective shifts attention from individual CpG sites to modules of covarying sites. This perspective helps explain why DNA methylation clocks perform so well despite their differences and provides a more systematic approach for developing the next generation of aging biomarkers.

18.
arXiv (CS.LG) 2026-06-12

Uncertainty Estimation for Molecular Diffusion Models

arXiv:2606.13451v1 Announce Type: new Abstract: Diffusion models have seen wide adoption for 3D molecular generation, yet they offer no principled signal of when a generated molecule is likely to be of low quality. We propose a post-hoc method for estimating per-sample uncertainty in pretrained molecular diffusion models. Building on a Laplace approximation of the denoising network, we measure the variability of the noise prediction across the generation trajectory. Empirically, we show that the resulting uncertainty score is informative of sample quality, exhibiting a negative correlation with established sample-level quality metrics. We further study how the proposed uncertainty score can be used to filter generated samples, improving model performance via test-time scaling.

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

Application and quantum properties of superpositions of oppositely squeezed states

arXiv:2511.03204v2 Announce Type: replace Abstract: We show that superpositions of oppositely squeezed states – non-Gaussian Schr{\"{o}}dinger-cat-like states – exhibit enhanced nonclassical features and provide an entanglement advantage in the small-squeezing regime. These states possess photon-number structures distinct from conventional coherent-state cat states, and we analyze their Wigner functions and the entanglement generated when they are injected into a 50-50 beam splitter. As a practical application, we demonstrate that they enable a high-quality heralded single-photon source whose second-order intensity correlation function is smaller than that obtained from a pure two-mode squeezed vacuum state. We further propose a linear-optical heralding scheme that approximates these superpositions without requiring strong Kerr nonlinearities. Our results indicate that the superposition of oppositely squeezed states is a promising non-Gaussian resource for quantum information processing, particularly for single-photon generation.

20.
arXiv (CS.AI) 2026-06-12

PolicyGuard: Towards Test-time and Step-level Adversary Defense for Reinforcement Learning Agent

arXiv:2606.12896v1 Announce Type: cross Abstract: While real-world applications of reinforcement learning (RL) are becoming increasingly popular, the security of RL systems deserve more attention and exploration. In particular, recent work has revealed that RL agents are vulnerable to backdoor attacks, where a victim agent behaves normally under standard conditions but executes malicious actions when a specific trigger is activated. Existing backdoor defenses for RL either require access to the agent's internal parameters, operate only at the model or trajectory level, or are limited to specific attack types. To ensure the security of RL agents, we propose \texttt{PolicyGuard}, a test-time step-level backdoor defense which leverages Gaussian Process (GP) posterior variance and adapts pseudo trajectories to enable uncertainty computation for individual time step. Besides, we also provide theoretical foundations to explain the efficacy of GP posterior variance. Extensive experiments across seven RL games demonstrate that PolicyGuard achieves state-of-the-art detection performance in most cases, with average AUROC of 0.856 for perturbation-based attacks and 0.859 for adversary-agent attacks.

21.
arXiv (CS.LG) 2026-06-11

Conformal Bayes under Label Shift: Post-Hoc Calibration vs. In-Training Adaptation

Authors:

arXiv:2606.11865v1 Announce Type: cross Abstract: Conformal Bayes combines Bayesian posterior predictives with conformal calibration to produce prediction sets that are both statistically valid and geometrically efficient. We study conformal Bayes under label shift from a unified perspective, identifying two complementary approaches that restore nominal target-domain coverage through importance-weighted conformal calibration but operate through independent mechanisms. Post-hoc calibration tilts the posterior predictive toward the target domain and corrects the conformal threshold via an importance-weighted quantile, leaving the parameter posterior unchanged. In-training adaptation tilts the parameter posterior itself to the target domain, producing a corrected predictive whose highest predictive density region serves as the highest predictive density (HPD) based prediction set under the fitted target predictive; efficiency is model-dependent and does not imply finite-sample conditional optimality. Two controlled experiments show that in an unbiased training regime both strategies achieve valid coverage equally, while in a lead-optimization regime in-training adaptation acts as a debiasing operator, reducing interval width at unchanged coverage.

22.
arXiv (CS.CL) 2026-06-15

Deep Dense Exploration for LLM Reinforcement Learning via Pivot-Driven Resampling

Effective exploration is a key challenge in reinforcement learning for large language models: discovering high-quality trajectories within a limited sampling budget from the vast natural language sequence space. Existing methods face notable limitations: GRPO samples exclusively from the root, saturating high-probability trajectories while leaving deep, error-prone states under-explored. Tree-based methods blindly disperse budgets across trivial or unrecoverable states, causing sampling dilution that fails to uncover rare correct suffixes and destabilizes local baselines. To address this, we propose Deep Dense Exploration (DDE), a strategy that focuses exploration on $pivots$-deep, recoverable states within unsuccessful trajectories. We instantiate DDE with DEEP-GRPO, which introduces three key innovations: (1) a lightweight data-driven utility function that automatically balances recoverability and depth bias to identify pivot states; (2) local dense resampling at each pivot to increase the probability of discovering correct subsequent trajectories; and (3) a dual-stream optimization objective that decouples global policy learning from local corrective updates. Experiments on mathematical reasoning benchmarks demonstrate that our method consistently outperforms GRPO, tree-based methods, and other strong baselines. Code is available at https://github.com/AgentCombo/DEEP-GRPO

23.
arXiv (math.PR) 2026-06-24

On the convex hull of a planar Brownian bridge with a random Gaussian endpoint

arXiv:2606.24485v1 Announce Type: new Abstract: We consider a one-parameter family of isotropic planar Gaussian processes \[ X_\sigma(t) =B_t+\sigma t Z,\qquad 0\le t\le 1,\quad 0\le \sigma\le 1, \] where $B$ is a standard ($0$-to-$0$) planar Brownian bridge on $[0,1]$, and $Z\sim \mathrm N(0,I)$ is a standard Gaussian random vector independent of $B$. The family interpolates between standard planar Brownian bridge ($\sigma=0$) and standard planar Brownian motion ($\sigma=1$). As the main result of the paper we compute the expected perimeter and area of the convex hull of the random set $\left\{X_\sigma(t) \colon 0\le t\le 1\right\}$ as closed formulas in terms of $\sigma$, and recover the classical Brownian bridge and Brownian motion values at $\sigma=0$ and $\sigma=1$. We also consider the convex hull spanned by multiple independent processes of this type and the possibilities for closed formulas in special cases. The key observation in our argument is that the isotropy property reduces the expected perimeter and area to one-dimensional quantities through the support function and Cauchy's formulas.

24.
arXiv (CS.AI) 2026-06-16

A Model-Free Universal AI

arXiv:2602.23242v3 Announce Type: replace Abstract: In general reinforcement learning, all established optimal agents, including AIXI, are model-based, explicitly maintaining and using environment models. This paper introduces Universal AI with Q-Induction (AIQI), the first model-free agent proven to be asymptotically $\varepsilon$-optimal in general RL. AIQI performs universal induction over distributional action-value functions, instead of policies or environments like previous works. Under a grain of truth condition, we prove that AIQI is strong asymptotically $\varepsilon$-optimal and asymptotically $\varepsilon$-Bayes-optimal. We also apply our novel proof techniques to show asymptotic $\varepsilon$-optimality of Self-AIXI without any ad-hoc assumptions. Our results significantly expand the diversity of known universal agents.

25.
arXiv (CS.LG) 2026-06-11

Learning What to Say to Your VLA: Mostly Harmless Vision Language Action Model Steering

arXiv:2606.12299v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models provide a natural language interface to robot control, but the mapping from language to behavior is often brittle and unintuitive: semantically similar instructions can induce drastically different behaviors, while some capabilities may not be elicitable through prompting alone. As a result, both human instructions and zero-shot language models can fail to reliably steer VLAs toward successful task execution. In this work, we propose a framework that interactively searches for language sequences that improve closed-loop VLA task performance, distills these sequences into a test-time language feedback policy (LFP), and learns an improvement head that predicts when language steering will improve performance. We conformalize this improvement head to prevent harmful steering interventions, where the LFP decreases task performance relative to the original instruction on out-of-distribution scenarios. Crucially, our approach operates on arbitrary frozen pre-trained VLAs, requiring neither access to the original training distribution nor fine-tuning of the underlying model. On seen environments, our conformalized LFP improves base VLA performance by 24.7% in simulation and 65.0% in hardware. On visual and semantic perturbations, our conformalized LFP has strong harmlessness guarantees, and produces recovery behaviors not observed with open-loop prompting.