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

Cost-effectiveness of a virtual fracture clinic versus traditional in-person fracture clinic care for adults with acute simple fractures: a protocol for a health economic evaluation within the RECITAL trial

ABSTRACT Introduction Traditional in-person fracture clinics are often overcrowded and inconvenient for patients. Virtual fracture clinics aim to address some of these concerns by improving the efficiency of the orthopaedic service and reducing unnecessary interventions while maintaining safety and quality of care. The RECITAL trial is a non-inferiority randomised controlled trial comparing follow-up care provided at a virtual fracture clinic for people with acute simple fractures to follow-up care provided at an in-person fracture clinic. This study describes the protocol for an economic evaluation of RECITAL where the primary aim is to investigate the cost-effectiveness of a virtual fracture clinic compared with traditional in-person fracture clinic care from a health system perspective. Methods and analysis The RECITAL trial recruited 312 participants with acute simple fractures and randomised them to receive follow-up care provided at a virtual fracture clinic or follow-up care provided at an in-person fracture clinic. We will conduct a within-trial analysis from a health system perspective (primary analysis), as well as a health service, patient and societal perspective. The economic evaluation will estimate the difference in the cost of resource inputs on an intention to treat basis used by participants in the two arms of the trial, allowing comparisons to be made between the in-person and virtual fracture clinics. Data for intervention costs and healthcare utilisation will be collected from trial records, hospital electronic medical records and district performance units. The results of the economic evaluation will be expressed in terms of incremental cost per utility weight gained at 12 weeks and will be plotted on a cost-effectiveness plane. Bootstrapping by resampling will be used to estimate 95% confidence intervals around costs and outcomes, and to calculate the confidence intervals around the incremental cost-effectiveness ratio. A cost-effectiveness acceptability curve (CEAC) will be plotted, which will provide information about the probability that an intervention is cost-effective, given the level of a decision makers willingness to pay for each additional outcome. Ethics and Dissemination The trail was approved by the SLHD Ethics Review Committee (RPAH Zone) (X23-0200 and 2023/ETH01038). The findings will be disseminated through a peer-reviewed journal and conference presentations. Trial registration number The trial was prospectively registered on the Australian New Zealand Clinical Trials Registry (ANZCTR; 12623000934640)

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

Starter-Iterator Neural Operator: A Unified Architecture for High-Fidelity Forward and Inverse PDE Problems

arXiv:2606.18305v1 Announce Type: cross Abstract: Operator learning is an emerging interdisciplinary field that integrates machine learning with scientific computing. By mapping infinite-dimensional function spaces, this approach provides an efficient surrogate modeling framework for high-dimensional partial differential equations (PDEs). Compared to traditional numerical solvers, it achieves a superior trade-off between computational complexity and approximation accuracy, demonstrating significant advantages in many-query tasks such as real-time prediction and parameter sweeps. Given the stringent accuracy requirements of both forward simulation and inverse inference, as well as the precision bottlenecks of existing operator learning methods in handling complex boundaries or long-term evolution, we propose the Starter-Iterator Neural Operator (SINO). Our framework reinterprets the initialization strategies and iterative formats of traditional iterative methods through neural networks, establishing an efficient approach for spectral-spatiotemporal collaborative modeling. Specifically, the frequency-domain initialization module captures globally stable low-frequency features, while the time-domain learning module focuses on optimizing local solution residuals, thereby effectively overcoming the inherent limitations of conventional single-domain modeling approaches. Extensive experiments on typical dynamical systems such as the Navier-Stokes equations and acoustic wave equations, as well as practical applications including super-resolution imaging and weather forecasting, demonstrate that SINO achieves outstanding performance in numerical accuracy, generalization capability, and robustness.

03.
arXiv (CS.AI) 2026-06-17

Towards Understanding and Measuring COGNITIVE ATROPHY in LLM Behaviour

arXiv:2606.18129v1 Announce Type: cross Abstract: Recent incidents involving LLMs used for mental-health support reveal a critical evaluation gap: surface-level safety scores do not capture how models behave across realistic, emotionally sensitive interactions over time. Existing benchmarks measure knowledge, safety, or static response quality, but miss whether LLM interactions help users keep reflecting, coping, and making decisions themselves. We formalize this missing dimension as COGNITIVE ATROPHY, a process-level behavioural measure in AI-mediated mental-health support distinct from safety and helpfulness. To measure it, we introduce COGNITIVE ATROPHY BENCH, a clinically grounded benchmark built from 1,576 fully human-generated counseling conversations, 15,680 turns, and 42,230 responses from five LLMs. Three clinical and neuropsychology experts developed a 20-attribute schema spanning user context, response behaviour, and global risk flags; six trained clinical reviewers applied it with span-grounded evidence, producing 5,324 reviewer judgments. We further introduce the User-Input Risk Index (UIRI), the Cognitive Atrophy Risk Index (ARI), and trajectory summaries. Across five LLMs, models show a consistent moderate-to-high level of atrophy-aligned behaviour across single and multi-turn settings. While models generally respond to overt safety cues, they adapt less reliably when users seek solutions or decisions. The dominant recurring patterns are directive advice, problem-solving, recommendation responses, topic shifts, and forms of validation that may reinforce dependence rather than reflection. Our work makes COGNITIVE ATROPHY measurable and provides a foundation for auditing model behaviour in sensitive LLM conversations.

04.
arXiv (CS.CV) 2026-06-11

NSVQ: Mitigating Codebook Collapse by Stabilizing Encoder Drift in Vector Quantization

Vector quantization is central to modern generative modeling pipelines, but large-codebook VQ models often suffer from codebook collapse. We identify encoder drift as a key driver of this failure: as the encoder moves the latent distribution, sparsely updated code vectors can lag behind, lose assignments, and increase quantization error, creating a feedback loop through the straight-through estimator. We propose NSVQ, a non-stationary-aware VQ training strategy that combines a dense non-stationary embedding loss, codebook replacement, and stage-wise encoder freezing. NSVQ first helps the codebook track encoder drift during early training, then freezes the encoder to consolidate the codebook under a fixed latent geometry, and finally reintroduces adversarial refinement. Experiments on ImageNet-1k show that NSVQ improves reconstruction quality while maintaining full codebook utilization. On ImageNet-1k at 128$\times$128 with 65,536 codes, NSVQ reduces rFID from 2.39 to 2.10 compared with SimVQ, while both methods maintain 100\% utilization. Additional latent diffusion experiments show that NSVQ also improves downstream ImageNet generation FID.

05.
arXiv (CS.LG) 2026-06-18

Trainable Photonic Measurement for Physics-Informed PDE Learning

arXiv:2606.18713v1 Announce Type: new Abstract: Photonic quantum machine learning offers a route to trainable physical representations built from phase, interference and measurement. However, its role in scientific machine learning remains largely unexplored. Physics-informed neural fields provide a natural setting, because differential equations require trial spaces that preserve phase, frequency and derivative structure. Here we introduce a photonic quantum neural field in which coordinates become trainable optical phases, are mixed by multi-photon Fock-space interference and are decoded from photon-number measurements. The photonic circuit is optimized as the neural-field representation itself, not as a fixed feature map or hardware accelerator. Photonic measurement is therefore a trainable representation on which the physics-informed residual is minimized. Across seven elliptic, wave, nonlinear dispersive and inverse PDE benchmarks, we observe a phase-complexity transition: classical coordinate and Fourier-feature networks suffice in smooth regimes, whereas the photonic field is most accurate when residual derivatives amplify phase mismatch. In the hardest regimes it gives the lowest errors, with margins reaching an order of magnitude and about one quarter of the trainable parameters of classical baselines. Frozen and shuffled controls, together with noise stress tests, attribute this gain to learned interference and stable Fock-probability readout under compound perturbations. These results identify photonic quantum measurement as a representation-learning principle for scientific machine learning.

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

DriveReward: A Comprehensive Dataset and Generative Vision-Language Reward Model for Autonomous Driving

Reward models play a pivotal role in reinforcement learning (RL) and multi-modal trajectory selection for autonomous driving. However, acquiring such rewards typically relies on hand-crafted rule-based objectives or perception ground truth, which hinders generalization for data-scaling. While Vision-Language Models (VLMs) have demonstrated feasibility as reward models in other domains, their effectiveness in driving tasks remains underexplored. In this work, we bridge this gap by (1) introducing DriveReward, a reasoning trajectory evaluation dataset rigorously labeled via temporally-grounded visual guidance, and augmented with counterfactual driving behaviors., (2) alongside a specialized Vision-Language Reward Model. To address the scarcity of failure cases in conventional datasets, we propose a counterfactual data annotation scheme to construct cases encompassing diverse driving styles and erroneous behaviors. Evaluations on our proposed benchmark reveal that even leading open-source and proprietary VLMs fail to excel across all tasks, highlighting significant room for improvement in existing models. Building on these findings, we subsequently tailor a specialized 1B reward model that outperforms larger VLMs on task-specific reward alignment. Finally, we validate our reward model's effectiveness by integrating it into RL finetuning and multi-modal trajectory scoring across multiple baselines, achieving performance comparable to rule-based reward calculations in both open-loop and closed-loop evaluation.

07.
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.

08.
arXiv (CS.CV) 2026-06-15

Giving AI a Headache: Acoustic Adversarial Attacks to Computer Vision Applications

Artificial Intelligence (AI) is increasingly used to automate a variety of real-world computer vision (CV) applications, such as autonomous vehicle control, facial recognition, and security cameras. Recent research has shown that acoustic vibration can induce real physical motion in cameras, interfering with their internal stabilization mechanisms. Because the motion falls outside the conditions the stabilization system was designed to handle, the system introduces artifacts into the frame, causing AI-based CV models to misclassify, miss targets, or hallucinate objects. Previous work used ultrasonic frequencies (>20 kHz) to perform short-range attacks, which limits them to short distances due to the attenuation exhibited by high frequencies. In this work, we investigate acoustic attacks using lower frequencies in the audible range (

09.
arXiv (CS.AI) 2026-06-17

LLM-Aided Joint Secrecy Precoding and Trajectory for RSMA-Based Heterogeneous UAV Networks

arXiv:2507.17188v3 Announce Type: replace-cross Abstract: This paper investigates secure communications in rate-splitting multiple access (RSMA) enabled heterogeneous UAV networks, where multiple UAVs collaboratively serve ground terminals in the presence of eavesdroppers. By jointly considering secrecy rate maximization and propulsion energy consumption minimization, we formulate a multi-objective optimization problem involving UAV trajectory design, service association, power allocation, and secrecy precoding under mobility, collision-avoidance, service-capacity, and communication constraints. The formulated problem is highly non-convex due to the coupling among UAV trajectories, RSMA transmission variables, and secrecy constraints.To address the resulting non-convex and highly coupled optimization problem, we propose a hierarchical optimization framework. The inner layer uses a semidefinite relaxation (SDR)-based S2DC algorithm combining penalty functions and difference-of-convex (D.C.) programming to solve the secrecy precoding problem with fixed UAV positions. The outer layer introduces a Large Language Model (LLM)-guided heuristic multi-agent reinforcement learning approach (LLM-HeMARL) for trajectory optimization. LLM-HeMARL efficiently incorporates LLM-generated expert heuristic policy, enabling UAVs to learn energy-aware, security-driven trajectories without the inference overhead of real-time LLM calls. The simulation results show that our method outperforms existing baselines in secrecy rate and energy efficiency, with consistent robustness across varying UAV swarm sizes and random seeds.

10.
arXiv (CS.LG) 2026-06-18

Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation

arXiv:2606.18844v1 Announce Type: new Abstract: Self-distillation improves reasoning in large language models by using the model's own rollouts as training signal, typically through implicit logit-level alignment that minimizes KL divergence toward a privileged target distribution. However, because this supervision is generated via uncontrolled sampling, it provides no diagnostic insight into the model's specific errors or corrective guidance for its individual failure patterns. Consequently, the model learns to imitate a privileged distribution rather than receiving fine-grained corrections that pinpoint where and why its reasoning fails. In this paper, we propose Trajectory-Augmented Policy Optimization (TAPO), which advances self-distillation from implicit distributional alignment to explicit trajectory construction. During RL training, the model produces both correct and incorrect rollouts to the same query, and TAPO leverages this contrastive structure to construct micro-reflective corrections, new training trajectories that retain the model's erroneous reasoning up to the point of failure, then insert a natural-language diagnosis and corrected reasoning guided by a correct reference from the same sampling group. Since each trajectory is anchored in the learner's own prefix and solutions, the corrective signal preserves the model's on-policy distribution to a greater extent than the position-wise alignment imposed by KL-based methods. To integrate these trajectories, TAPO introduces difficulty-aware candidate selection at the model's capability boundary and decoupled advantage estimation to prevent gradient contamination. Experiments on AIME 2024, AIME 2025, and HMMT 2025 show that TAPO achieves consistent improvements over GRPO under the same number of training steps. Further analysis demonstrates that TAPO strengthens both first-pass reasoning and error-correction effectiveness.

11.
medRxiv (Medicine) 2026-06-11

Malaria Risk among Internally Mobile Individuals and Heterogeneous Mobility Patterns in Two Hypoendemic Communities: Implications for Malaria Elimination in the Peruvian Amazon.

Background: Human mobility is increasingly recognized as a key factor influencing malaria transmission dynamics, particularly in low-transmission settings approaching elimination. This study aimed to assess mobility patterns and their association with malaria risk in two hypoendemic communities in the Peruvian Amazon. Method: A longitudinal study was conducted in the communities of Libertad and Urcomirano (Mazan River basin). Monthly population screenings were combined with weekly active and passive case detection. A total of 678 individuals were enrolled. Mobility patterns were assessed through structured questionnaires, and social network analysis was used to characterize travel connections. Log-binomial regression analysis was applied to identify risk factors associated with malaria infection. Result: Internally, mobile individuals in Libertad showed a higher malaria incidence (>32.47 cases per 1,000 person-months) than those in Urcomirano (

12.
arXiv (CS.CV) 2026-06-16

Mitigating Object Hallucinations in LVLMs via Attention Imbalance Rectification

Object hallucination in Large Vision-Language Models (LVLMs) severely compromises their reliability in real-world applications, posing a critical barrier to their deployment in high-stakes scenarios such as autonomous driving and medical image analysis. Through systematic empirical investigation, we identify that the imbalanced attention allocation, both across modalities (i.e., vision and language) and within modalities (among individual tokens), exhibits a strong causal correlation with the occurrence of object hallucination. Leveraging this insight, we introduce a novel concept termed attention imbalance, which not only quantifies the degree of attention disparity but also visually delineates the underlying patterns (e.g., over-attentiveness to irrelevant language tokens or under-attentiveness to discriminative visual features) that drive object hallucination. To mitigate object hallucination, we further propose Attention Imbalance Rectification (AIR), a lightweight decoding-time intervention method that reallocates attention weights and adjusts attention distributions to rectify modality-wise and token-wise imbalances. Extensive evaluations on four mainstream LVLMs and three benchmarks (CHAIR, POPE, and MM-Vet) with seven baselines demonstrate that AIR consistently reduces object hallucination rates, achieving up to a 35.1% reduction compared to the baselines, while improving up to 15.9% of LVLMs' general capability across diverse vision-language tasks.

13.
arXiv (CS.LG) 2026-06-19

When to Trust, How to Distill: Multi-Foundation Model Guidance for Lightweight, Robust Scientific Time Series Forecasting

arXiv:2606.19363v1 Announce Type: new Abstract: The deployment of Time-Series Foundation Models (TSFMs) in physical sciences is hindered by a critical trade-off: while these models encode rich, universal temporal dynamics, they suffer from severe distributional misalignment when applied zero-shot to specific scientific domains, and their computational cost prohibits deployment in edge-computing sensor networks. We address a fundamental challenge: How can we extract latent structural knowledge from misaligned foundation models (FM) to train lightweight, specialized forecasters? We propose Gated Uncertainty-Aware Routing for Distillation (Guard), a novel framework that reframes multiteacher distillation as an instance-wise decision process with two adaptive mechanisms: (1) a Contextual Router that dynamically selects the most relevant teacher based on local input statistics, exploiting complementarity across diverse foundation models; and (2) an Uncertainty-Gated Temperature mechanism that acts as a "circuit-breaker," automatically attenuating distillation strength when teacher confidence diverges from domain reality. We evaluate our proposed lightweight framework on four climate-critical domains: meteorology, ecosystem carbon flux, soil moisture, and energy grids. Our method significantly reduces RMSE relative to a fixed-weight multi-teacher distillation baseline, successfully distilling knowledge from pretrained FMs (teachers) even when they exhibit suboptimal zero-shot accuracy due to distribution shift between the original and target data domains. We demonstrate that these domain-misaligned teachers can still serve as critical correctives, outperforming the globally superior FMs on 28.5% of the hardest instances. Ultimately, this enables high-precision scientific forecasting suitable for resource-constrained edge deployment. Code is available at https://github.com/RupasreeDey/GUARD-KDD2026.

14.
Nature (Science) 2026-06-10

Daily briefing: Ancient ground squirrels ate like ‘zombies of the Pleistocene’

Authors:

Evidence from fossilized poo reveals the diverse diet of ancient ground squirrels. Plus, the science behind the peptide craze and our innate tendency to wander anticlockwise. Evidence from fossilized poo reveals the diverse diet of ancient ground squirrels. Plus, the science behind the peptide craze and our innate tendency to wander anticlockwise.

15.
arXiv (CS.CV) 2026-06-15

Optimizing Rank for High-Fidelity Implicit Neural Representations

Implicit Neural Representations (INRs) based on vanilla Multi-Layer Perceptrons (MLPs) are widely believed to be incapable of representing high-frequency content. This has directed research efforts towards architectural interventions, such as coordinate embeddings or specialized activation functions, to represent high-frequency signals. In this paper, we challenge the notion that the low-frequency bias of vanilla MLPs is an intrinsic, architectural limitation to learn high-frequency content, but instead a symptom of stable rank degradation during training. We empirically demonstrate that regulating the network's rank during training substantially improves the fidelity of the learned signal, rendering even simple MLP architectures expressive. Extensive experiments show that using optimizers like Muon, with high-rank, near-orthogonal updates, consistently enhances INR architectures even beyond simple ReLU MLPs. These substantial improvements hold across a diverse range of domains, including natural and medical images and novel view synthesis, with up to +9 dB PSNR over the same architecture. Code is available at (https://rank-inrs.github.io).

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

Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: From Evaluation to Diagnosis

Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated remarkable multimodal perception and reasoning capabilities. While numerous benchmarks have evaluated LVLMs from holistic or task-specific perspectives, their capabilities on fine-grained image tasks-fundamental to computer vision-remain insufficiently understood. To address this gap, we introduce FG-BMK, a comprehensive fine-grained evaluation benchmark containing 1.01 million questions and 0.28 million images, covering diverse scenarios from common object-centric domains to specialized domains. FG-BMK jointly evaluates dialogue-level fine-grained semantic recognition and feature-level visual discriminability through human-oriented and machine-oriented paradigms, enabling diagnostic analysis of whether LVLM failures arise from insufficient visual representations, weak visual-to-semantic grounding, or limited fine-grained knowledge. Through extensive experiments on a diverse set of representative LVLMs/VLMs, we find that current LVLMs remain inadequate fine-grained recognizers, with failures arising from intertwined bottlenecks in visual representations, semantic grounding, modality alignment, and category-level knowledge. We further analyze training design factors for improving fine-grained capabilities and examine how visual and linguistic perturbations affect LVLM predictions. These findings provide diagnostic insights into the limitations of current LVLMs and offer guidance for future data construction and model design in developing more reliable LVLMs for fine-grained visual tasks. Our code is open-source and available at https://fg-bmk.github.io/.

17.
arXiv (CS.CL) 2026-06-16

Rapid Poison: Practical Poisoning Attacks Against the Rapid Response Framework

The Rapid Response (RR) framework, deployed in production systems, including Anthropic's ASL-3 safeguards, continuously improves jailbreak-detection classifiers. When new jailbreaks emerge that bypass these classifiers, Rapid Response generates synthetic variants for training, helping the model generalize from the new attacks and quickly adapt. We reveal that prompt injection can infiltrate this pipeline to deliver poisoned samples into the classifier's training set, enabling two attack objectives: (I) targeted poisoning attacks that create false positives on harmless samples by categorizing them as a jailbreak, with a specific desired feature (e.g., certain formatting, subject, or keyword), (II) concept-based backdoor attacks that induce false negatives on jailbreak inputs, generalizing even to jailbreaks from attack strategies the defender explicitly trained against, when the backdoor trigger is present. Importantly, our threat model restricts adversaries to modifying only jailbreak samples (not benign data or labels), a constraint unexplored by prior work that makes the second objective particularly challenging. We address this with Omission Attack, which exploits a new phenomenon: when training on concept-absent unsafe samples, the classifier misassociates that concept's presence with the safe label. Both attacks cause substantial and in some cases near-complete label flipping at only a 1% poisoning rate, achieving up to 100% false positive rates and up to 96% false negative rates.

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

Language-Guided Abstraction for Visual Reasoning

The Abstraction and Reasoning Corpus (ARC) is viewed as a critical avenue to Artificial General Intelligence (AGI), as it enables models to learn abstract transformation rules from few-shot examples and then generalize to new tasks. However, prevalent ARC methodology is either pure language or vision-only (i.e., VARC). The former depends heavily on LLMs, consuming billions of parameters. The latter often struggles to capture high-level semantics, leading to overfitting on pixel-level patterns. To bridge this gap, we propose L-VARC, a novel framework that enhances visual reasoning via a language-guided Learning Using Privileged Information (LUPI) branch. Specifically, we design a Semantic Compression Module by feeding a unified, task-agnostic prompt into DeepSeek-V3. In this way, the raw LARC (a crowd-sourced language description dataset) can be substantially refined and structured, fitting with the context length constraint of standard text encoders (e.g., CLIP). Moreover, we design a Cross-Attention Projector to align visual features with semantic embeddings, aiming to guide the training of the ARC model. Notably, the LUPI branch is taken in the training process and will be discarded during inference, thereby yielding a lightweight model with a mere 18 million parameters. Extensive experiments demonstrate that our L-VARC effectively leverages linguistic priors to boost visual reasoning and outperforms state-of-the-art. Ablation studies further confirm the contribution of the two new designs towards the L-VARC framework. The code is available at https://github.com/GZHU-DVL/L-VARC.

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

Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models

arXiv:2510.21978v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has delivered impressive gains in mathematical and multimodal reasoning and has become a standard post-training paradigm for contemporary language and vision-language models. However, the RLVR recipe introduces a significant risk of capability regression, in which models forget foundational skills after prolonged training without employing regularization strategies. We empirically confirm this concern, observing that open-source reasoning models suffer performance degradation on core capabilities such as perception and faithfulness. While imposing regularization terms like KL divergence can help prevent deviation from the base model, these terms are computed on the current task and therefore do not guarantee preservation of broader knowledge. Meanwhile, commonly used experience replay across heterogeneous domains makes it nontrivial to decide how much training emphasis each objective should receive. To address this, we propose RECAP-a replay strategy with dynamic objective reweighting for general knowledge preservation. Our reweighting mechanism adapts online using short-horizon signals of convergence and instability, shifting the post-training focus away from saturated objectives and toward underperforming or volatile ones. Our method is end-to-end and readily applicable to existing RLVR pipelines without training additional models or heavy tuning. Extensive experiments on benchmarks using Qwen2.5-VL-3B and Qwen2.5-VL-7B demonstrate the effectiveness of our method, which not only preserves general capabilities but also improves reasoning by enabling more flexible trade-offs among in-task rewards.

20.
arXiv (CS.AI) 2026-06-18

UBP2: Uncertainty-Balanced Preference Planning for Efficient Preference-based Reinforcement Learning

arXiv:2606.19328v1 Announce Type: cross Abstract: Preference-based RL provides an approach to learning reward models from pairwise comparisons of behaviors, bypassing the need for explicit reward design. However, existing methods typically rely on passive data collection and suffer from poor sample efficiency, especially during the early stages of learning. We introduce a model-based approach that actively directs exploration by jointly reasoning over uncertainties in the reward, dynamics, and value functions. Our method, Uncertainty-Balanced Preference Planning (UBP2), uses ensembles of reward, dynamics, and value function models to evaluate candidate trajectories according to a unified score that combines expected reward, terminal value, and epistemic uncertainty. Planning under this objective yields an explicit tradeoff between exploitation and information acquisition without requiring ad hoc exploration heuristics. Under standard regularity assumptions, we establish sublinear regret guarantees for both finite-horizon and infinite-horizon settings. Empirically, experiments on the Meta-World benchmark show UBP2 achieves substantially higher sample efficiency than model-free preference-based methods and non-optimistic model-based baselines.

21.
arXiv (CS.CV) 2026-06-16

Context-Aware RL for Agentic and Multimodal LLMs

Large language models (LLMs) often fail when answering requires identifying a small but decisive piece of evidence within a long or complex context, such as a single line in a tool trace or a subtle detail in an image. We propose ContextRL, a context-aware reinforcement learning (RL) method that improves long-horizon reasoning and multimodal performance through an indirect auxiliary objective. Instead of supervising only the final answer, ContextRL presents the model with a query, an answer, and two highly similar contexts, and rewards it for selecting the context that supports the query–answer pair, thereby encouraging fine-grained grounding. We construct contrastive context data in two domains: for coding agents, trajectories serve as contexts, yielding 1k pairs built via condition filtering; for multimodal reasoning, images serve as contexts, yielding 7K pairs built via generative editing and similarity search. ContextRL achieves average gains of +2.2% over standard GRPO on 5 long-horizon benchmarks, and +1.8% across 12 diverse visual question answering benchmarks. To disentangle the effect of the proposed objective from that of additional data, we compare against data-augmentation baselines that repurpose the same contrastive contexts as standard query–context–answer examples. These baselines provide little to no improvement, showing that the gains arise from the proposed context-selection objective rather than from the contrastive data alone.

22.
arXiv (CS.AI) 2026-06-18

Robust Regularized Policy Iteration under Transition Uncertainty

arXiv:2603.09344v3 Announce Type: replace Abstract: Offline reinforcement learning (RL) enables data-efficient and safe policy learning without online exploration, but its performance often degrades under distribution shift. The learned policy may visit out-of-distribution state-action pairs where value estimates and learned dynamics are unreliable. To address policy-induced extrapolation and transition uncertainty in a unified framework, we formulate offline RL as robust policy optimization, treating the transition kernel as a decision variable within an uncertainty set and optimizing the policy against the worst-case dynamics. We propose Robust Regularized Policy Iteration (RRPI), which replaces the intractable max-min bilevel objective with a tractable KL-regularized surrogate and derives an efficient policy iteration procedure based on a robust regularized Bellman operator. We provide theoretical guarantees by showing that the proposed operator is a $\gamma$-contraction and that iteratively updating the surrogate yields monotonic improvement of the original robust objective with convergence. Experiments on D4RL benchmarks demonstrate that RRPI achieves strong average performance, outperforming recent baselines including percentile-based methods on the majority of environments while remaining competitive on the rest. Moreover, RRPI exhibits robust performance by aligning lower $Q$-values with high epistemic uncertainty, which prevents the policy from executing unreliable out-of-distribution actions.

23.
arXiv (CS.AI) 2026-06-17

Descriptor: Certus Caliber Classification Gunshot Dataset (C3GD)

arXiv:2606.18135v1 Announce Type: cross Abstract: In this work, we introduce the Certus Caliber Classification Gunshot Dataset (C3GD), a publicly accessible data set developed for the analysis of firearm muzzle blast sounds. The dataset aims to provide a wide variety of firearms, calibers, cartridges, microphones, and microphone locations with metadata detailed beyond what is currently otherwise available. It comprises more than 8000 field-collected data points from 28 firearms across 16 calibers. Because data collection in the field is costly, much of the existing research has been done using gunshot audio collected from the internet, which increases the risk of low-quality data and label noise. This dataset is primarily focused on caliber classification, but can also be used for gunshot detection, audio separation, and audio signal processing, providing a diversified and real-world reference. The dataset aims to provide enough diversity to be able to generalize to more real-world applications while also providing enough metadata for detailed academic analysis.

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

When Should Agent Trust Be Conditional? Characterizing and Attacking Skill-Conditional Reputation in Agent Swarms

arXiv:2606.14200v1 Announce Type: new Abstract: Open platforms increasingly route tasks among heterogeneous LLM agents–differing in base model, scaffold, and tool stack–whose competence varies sharply by skill: an agent excellent at one skill may be useless at another. The standard reputation approach summarizes each agent by a single global trust score, but that scalar is the wrong object here, because routing every task to the globally most-trusted agent leaves the value of specialization unclaimed. We study skill-conditional trust R(i | k)–the trust to place in agent i for a task requiring skill k, rather than one score per agent–and pose three falsifiable questions: when is conditioning worth it, how much cross-skill evidence should be borrowed, and whether that borrowing is safe. A controlled phase-diagram analysis answers the first two: conditional trust wins only in a specific regime–high agent heterogeneity, sparse per-skill evidence, and correlated skills–and the coupling strength beta that buys this data efficiency is dual-use, because the same cross-skill borrowing is also a laundering channel. On a public benchmark of 14 genuinely heterogeneous AppWorld agents, real pools land inside the beneficial regime–a small but genuine gain, with the per-skill best agent genuinely changing across skills. We then show that an attacker with cheap evidence in one skill and none in a target skill hijacks the conditional router, driving routing regret from 0 to 0.94 on a pool our zero-cost Conditional Information Value Test (CIVT) rates GREEN–while the ungated trust verdict it contaminates reads -0.06 instead of the honest +0.19. A zero-evidence gate bounds the attack but does not eliminate it; we characterize the residual cost under an explicit budget. We do not claim Sybil-resistance–we quantify the trade-off.

25.
arXiv (CS.LG) 2026-06-17

Constrained Diffusion Models with Primal-Dual Inference

arXiv:2606.17192v1 Announce Type: new Abstract: This paper develops constrained diffusion models with primal-dual inference (PDI) to sample from optimal distributions of entropy-regularized optimization problems with average constraints. We formalize constrained sampling in the Lagrangian dual domain, where the optimal distribution takes the form of a Gibbs distribution indexed by the optimal dual variable. Rather than estimating this dual multiplier before sampling and freezing it throughout generation, PDI jointly infers the optimal primal distribution and its parametrizing dual variable. Each reverse diffusion step denoises using the score field associated with the current multiplier and then updates the multiplier through dual ascent using the estimated constraint violation of the denoised samples. To enable this conditional score field, we train a single dual-conditioned score network over the family of Gibbs distributions induced by the dual variables encountered during inference. We prove that the time average of the dual variables generated along the inference trajectory converges to a neighborhood of the dual optimum and bound the effect of residual dual mismatch on the terminal distribution through schedule-dependent stability factors. We evaluate PDI on constrained sampling from a mixture of Gaussians, wireless resource allocation, and portfolio management.