中 EN
Sign In Register

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.

Sign In Register
01.
PLOS Computational Biology 2026-06-18

Ten simple rules for turning your qualifying exam into an NIH-style fellowship proposal: A guide for graduate students

Authors:
Courtney Peña-Lima↗

by Courtney Peña-Lima, Cameron S. Bader, Brendan K. Ball, Troy C. Dildine, Mekhala V. Dissanayake, Iris van ‘t Erve, Albina Ibrayeva, Amy Nippert, M.K. Quinn, Chelse Spinner, Samuel Thompson, Antonio Tomasso, Crystal M. Botham Qualifying exams, often referred to as “quals” or candidacy exams, are an important milestone in doctoral programs. Although the style of quals varies greatly by program and institution, it is usually a proposal that requires students to develop research ideas as well as their scientific writing skills. Many quals are modeled after funding mechanisms that graduate students can apply to and on a topic that the student will pursue in their dissertation. This paper offers graduate students a step-by-step guide on how to turn their quals into a fellowship-style research proposal, using National Institutes of Health (NIH) mechanisms as a benchmark, as this is the norm within US research institutions. This paper will be most useful for students who have completed or are in the process of completing proposal-based qualifying exams, usually in the second year of a doctoral program.

Read & Discuss → View Source →
02.
arXiv (CS.CV) 2026-06-18

Aerial-ground LiDAR place recognition with patch-level self-supervised learning and expanded reciprocal re-ranking

Authors:
Yandi Yang↗Xianghong Zou↗Jianping Li↗Haofeng Xie↗Saurav Uprety↗Hongzhou Yang↗Naser El-Sheimy↗

LiDAR place recognition determines one's position on a prior point cloud map. The most studied ground-level LiDAR place recognition suffers from pre-visit requirements, incomplete coverage, and limited perspectives. Using pre-acquired, full-coverage Airborne Laser Scanning (ALS) data as an aerial prior map overcomes these drawbacks, making cross-view place recognition necessary and advantageous. However, aerial-ground LiDAR place recognition faces significant challenges, including the domain gap between aerial and ground point clouds, and false positives during initial retrieval. To address these challenges, we present a novel retrieval and re-ranking framework for aerial-ground LiDAR place recognition. Based on the priors that neighboring point cloud patches share similar semantics with anchor patch, our retrieval network introduces patch-level self-supervised learning modules at multiple scales and integrates with scene-level learning to improve global feature discriminativeness between aerial and ground point clouds. Furthermore, leveraging the structured spatial distribution of ALS point clouds, we introduce an Expanded Reciprocal (ER) re-ranking algorithm to exploit neighborhood information maximally and refine each feature based on neighbor features, which are then used to update the similarity matrix for final ranking. Extensive experiments demonstrate that our retrieval network outperforms existing state-of-the-art (SOTA) methods, achieving a 9.8\% improvement in average Recall@1 and a 3.2\% improvement in average Recall@1\% on the CS-Urban-Scenes, while also showing the best performance on the CS-Campus3D dataset. Additionally, our ER re-ranking algorithm further boosts the average Recall@1 by 4.9\% on CS-Campus3D and 10.2\% on CS-Urban-Scenes without additional training.

Read & Discuss → View Source →
03.
arXiv (CS.LG) 2026-06-16

Surrogate-Assisted Framework for SI-Compliant Interconnect Design Optimization Using the Earth Mover's Distance

Authors:
Emre Ecik↗Werner John↗Julian With\"oft↗Ralf Br\"uning↗J\"urgen G\"otze↗

arXiv:2606.15234v1 Announce Type: cross Abstract: This work presents a deterministic, machine-assisted framework for SI-compliant PCB design based on the Earth Mover's Distance (EMD). In contrast to conventional surrogate-based optimization methods that rely on iterative black-box search procedures, the proposed approach follows an interpretable, sequential evaluation strategy. Neural surrogate models are first used to efficiently predict waveform describing features from topology-dependent design parameters. A decision tree then acts as a physically motivated quality gate that identifies SI-compliant waveforms according to predefined SI criteria. Within the resulting valid solution space, the Earth Mover's Distance is employed as a similarity metric to rank candidate designs according to their proximity to an ideal reference signal. This enables not only the deterministic identification of admissible parameter regions but also a transparent prioritization of physically superior solutions without inverse modeling or stochastic search procedures. The methodology is demonstrated using a large-scale set of simulated DDR3 fly-by waveforms. By combining surrogate prediction, interpretable classification, and EMD-based waveform evaluation, the framework provides an explainable and computationally efficient alternative to conventional optimization strategies for supporting PCB development with AI-based methods.

Read & Discuss → View Source →
04.
arXiv (CS.AI) 2026-06-24

ReM-MoA: Reasoning Memory Sustains Mixture-of-Agents Scaling

Authors:
Heng Ping↗Arijit Bhattacharjee↗Peiyu Zhang↗Shixuan Li↗Wei Yang↗Ali Jannesari↗Nesreen Ahmed↗Paul Bogdan↗

arXiv:2606.24437v1 Announce Type: new Abstract: Mixture-of-Agents (MoA) architectures improve inference-time scaling by organizing multiple LLM agents into layered reasoning pipelines. However, existing MoA variants fail to sustain gains as depth increases, exhibiting degradation, early plateauing, or saturation. We propose ReM-MoA, a memory-augmented MoA framework that sustains scaling through two mechanisms: (1) a Ranked Reasoning Memory that persistently stores and ranks reasoning traces from all layers using a comparative Reviewer Agent, and (2) a Curated Diversified Memory Routing scheme that exposes different agents to distinct combinations of successful and failed traces, preserving exploration diversity while propagating high-quality reasoning. We further introduce an optional multi-domain Reviewer distillation pipeline that improves ranking quality through frontier-model supervision. Across five reasoning benchmarks spanning math, formal logic, code, knowledge, and commonsense, ReM-MoA consistently outperforms prior MoA variants across both depth and width scaling, and its advantage widens with depth, establishing structured cross-layer reasoning memory as a key missing mechanism for scalable multi-agent inference.

Read & Discuss → View Source →
05.
medRxiv (Medicine) 2026-06-17

Brain age gap correlates with DTI-derived microstructural abnormalities in multiple sclerosis.

Authors:
Lea↗Al-Ledani↗Bardell↗Maltby↗Ramadan↗R. A↗Lechner-Scott↗

Background: Brain age gap (BAG) is increased in multiple sclerosis (MS), but whether it reflects microstructural pathology beyond conventional atrophy remains unclear. Objective: To test whether BAG is elevated in MS and correlates with conventional and diffusion tensor imaging (DTI) abnormalities relative to healthy controls. Methods: A case-control study of 43 people with MS and 18 healthy controls was performed. BAG was estimated from T1-weighted MRI using brainageR. Controls were used as MRI reference distributions. MRI values were expressed as deviation z-scores and correlated with BAG within MS. Conventional MRI and DTI domains were analysed using age/sex-adjusted partial correlations with domain-wise Benjamini-Hochberg FDR correction, where appropriate. Results: BAG was higher in MS than controls (4.79 vs -2.58 years; p

Read & Discuss → View Source →
06.
arXiv (CS.LG) 2026-06-12

Estimating Individualized Treatment Effects in Acute Ischemic Stroke with Causal Transformation Models (TRAM-DAG): A Multi-Centre Observational Study with External RCT Validation

Authors:
Oliver D\"urr↗Lisa Herzog↗Pascal B\"uhler↗Susanne Wegener↗Beate Sick↗

arXiv:2606.12623v1 Announce Type: cross Abstract: Personalized medicine in acute ischemic stroke requires moving beyond average treatment effects (ATE) to individualized treatment effect (ITE) estimates to support treatment decisions. In acute ischemic stroke, mechanical thrombectomy has been shown to be more effective on average than lysis in randomized controlled trials (RCTs), such as the MR CLEAN study. We aim to identify which individual patients benefit most from mechanical thrombectomy compared to lysis. The outcome of interest is the modified Rankin Scale (mRS) at three months, an ordinal measure of functional disability (0: no symptoms, 6: death). We demonstrate that causal transformation models on directed acyclic graphs (TRAM-DAG) can be used for ITE estimation after being fitted on observational MAGIC multi-center stroke patient data. To ensure comparability with the MR CLEAN population, which we use for validation, we train the TRAM-DAG on a MAGIC sub-population with NIHSS at admission >= 6, corresponding to one inclusion criterion of MR CLEAN. The fitted model is then used to estimate ITEs for stroke patients in the MR CLEAN population. While these ITE estimates cannot be confirmed experimentally, we show that their average is consistent with the trial's reported ATE. Furthermore, the ITE estimates correctly rank trial patients by their observed frequency of a good outcome (mRS at three months

Read & Discuss → View Source →
07.
arXiv (CS.AI) 2026-06-18

Short-Term-to-Long-Term Memory Transfer for Knowledge Graphs under Partial Observability

Authors:
Taewoon Kim↗Vincent Fran\c{c}ois-Lavet↗Michael Cochez↗

arXiv:2605.22142v2 Announce Type: replace-cross Abstract: Reinforcement learning under partial observability requires deciding what information to retain, yet most memory-based approaches do not explicitly model short-term-to-long-term transfer of symbolic observations. We study this transfer process in a temporal knowledge-graph memory setting and cast it as a neuro-symbolic value-based decision problem: for each observed triple, the agent chooses whether to keep or drop it before long-term insertion. To handle variable-sized short-term buffers, we use a per-item Q-learning design with shared parameters and a practical temporal-difference update over matched items across consecutive steps. On the RoomKG benchmark at long-term memory capacity 128, learned transfer decisions outperform symbolic and neural baselines, including symbolic baselines with temporal annotations and history-based LSTM/Transformer baselines. Across transfer-policy ablations, a lightweight local short-term-only variant performs best, and step-level behavior shows that the policy keeps navigation- and query-relevant facts while discarding lower-value candidate facts, supporting explicit and interpretable memory decisions under memory constraints.

Read & Discuss → View Source →
08.
arXiv (CS.AI) 2026-06-12

Once-for-All: Scalable Simultaneous Forecasting via Equilibrium State Estimation

Authors:
Beinan Xu↗Andy Song↗Jiti Gao↗Feng Liu↗

arXiv:2606.13285v1 Announce Type: cross Abstract: We introduce Equilibrium State Estimation (ESE), a novel paradigm for simultaneous prediction, where multiple interacting systems require separate yet coordinated forecasts. Such scenarios often arise in real-world settings such as economics and healthcare modeling. Unlike existing approaches that predict one system at a time, ESE forecasts all systems in a single pass. It first estimates the equilibrium state across systems, then generates holistic forecasts based on the difference between the current state and the estimated equilibrium. Extensive experiments on synthetic and real-world datasets, including currency exchange and COVID-19 spread modeling, demonstrate that ESE is at least as accurate as state-of-the-art (SOTA) methods while being significantly faster. In addition, ESE integrates seamlessly with conventional predictors, combining their accuracy with its exceptional efficiency and delivering a 10-70x speedup. With linear-time complexity, ESE scales far better than SOTA methods as the number of systems increases. Moreover, it remains accurate under diverse perturbations, establishing ESE as a fast, generalizable, robust, and scalable multi-prediction method.

Read & Discuss → View Source →
09.
arXiv (CS.LG) 2026-06-19

An Information Theoretic Framework for Graph Novelty Generation via Latent Mixture Modeling

Authors:
Itsuki Nakagawa↗Kenji Yamanishi↗

arXiv:2606.19770v1 Announce Type: new Abstract: We propose an information-theoretic framework for graph novelty generation, which aims to generate data that are distinct from existing patterns while preserving global structural consistency. Our approach embeds data into a latent space, models the latent distribution using finite mixture models, and generates novel samples by imposing explicit novelty and reliability conditions formulated in terms of description length. Specifically, novelty is enforced by requiring generated samples to be poorly explained by all existing mixture components, while reliability constrains their impact on the overall mixture structure under the Minimum Description Length (MDL) principle. We provide a theoretical analysis showing that, with appropriate threshold choices, the probabilities of misclassifying non-novel or unreliable samples converge to zero with explicit rates. Experiments on synthetic and benchmark graph datasets demonstrate that the proposed method enables principled novelty generation with quantifiable risk.

Read & Discuss → View Source →
10.
arXiv (CS.CL) 2026-06-17

PseudoBench: Measuring How Agentic Auto-Research Fuels Pseudoscience

Authors:
Xinyang Liao↗Lingyu Li↗Huacan Liu↗Tianle Gu↗Yang Yao↗Tong Zhu↗Yan Teng↗Yingchun Wang↗

As Large Language Model based agents enter autonomous scientific research, their ability to resist pseudoscience becomes increasingly important. Otherwise, such systems may rapidly generate plausible yet misleading studies that contaminate academic literature and erode trust in science. We present PseudoBench, an adversarial benchmark for evaluating whether agentic auto-research systems can identify and resist pseudoscientific narratives. PseudoBench contains 200 curated pseudoscientific claim-evidence pairs across five domains and evaluates agents through an end-to-end research pipeline from experiments to writing. Testing seven state-of-the-art agents, we find that current systems readily produce persuasive reports that align with pseudoscientific premises with near-zero refusal rates and the highest resistance of only 27.4%. Stronger agents risk packaging pseudoscience in more sophisticated scientific language, increasing its apparent credibility. These findings reveal an alarming capacity to fuel pseudoscience, calling for scientific alignment before widespread deployment.

Read & Discuss → View Source →
11.
arXiv (quant-ph) 2026-06-24

Improved State Readout in NV Centers using Regression Models and Rabi Driving

Authors:
Fritz Haltenberger↗Manpreet Singh Jattana↗

arXiv:2606.23454v2 Announce Type: replace Abstract: Readout of state populations in nitrogen-vacancy centers from fluorescence measurements at room-temperature is routinely achieved via contrast-based calibration. The fidelities achieved by this conventional approach are limited by reducing the dynamical fluorescence behaviour of the NV center to a scalar value, and calculating the population of each possible state independently. To address these limitations, we use regression models trained on experimental data to map the fluorescence signals onto ideal simulated populations. Additionally, we enhance the informational content of the fluorescence signals by performing measurements during induced Rabi oscillations. Our results demonstrate that including these dynamical signals significantly reduces state readout errors across multiple tested models. Notably, linear ridge regression performs nearly on par with a non-linear kernel-based model, showing that simple models already capture the relevant mapping between the enhanced fluorescence signals and the underlying state populations. This data-driven approach provides a robust alternative that achieves higher fidelities than conventional calibration in our setting, paving the way for high-fidelity state readout in solid-state quantum registers.

Read & Discuss → View Source →
12.
arXiv (CS.AI) 2026-06-24

Legal Reasoning Is Not Lawyering: Rethinking Legal Benchmarks for Pro Se Access to Justice

Authors:
Andrew Lou↗David Shin↗

arXiv:2606.23716v1 Announce Type: cross Abstract: Legal AI benchmark research frequently invokes the assumption that large language models can improve access to justice, including for people who cannot access lawyers in order to understand and exercise their legal rights. We argue that current benchmarks are not equipped to support this assumption because they evaluate legal reasoning over inputs that have already been preprocessed by legal experts, which measures the upper bound of model performance. Access to justice depends on a lower bound: how models perform when inputs come from pro se litigants, whose prompts may contain noisy narratives, buried facts, omissions, folk-legal assumptions, and surface-level errors. These degradations are comparable to conditions under which LLMs are known to degrade in the general machine learning literature, including long-context sensitivity, underspecification, hallucination, and typographical perturbations. We connect evidence from pro se literature with this body of machine learning research and present a small perturbation experiment on LEXam, a legal benchmark, to illustrate the gap between these two bounds. If model development continues to focus on benchmarks that measure only the upper bound, this gap may remain hidden or even widen. We conclude by calling for legal benchmarks that directly measure robustness under pro se-like inputs so that access-to-justice claims about legal AI can become empirically testable.

Read & Discuss → View Source →
13.
arXiv (CS.CV) 2026-06-16

Understanding Cross-Modal Contributions in Continual Vision-Language Models: A Theoretical Perspective

Authors:
Salimeh Sekeh↗Mary Wisell↗

Continual vision-language models are commonly addressed through sequential fine-tuning; however, although this paradigm enables adaptation to new environments (tasks), it inherently emphasizes the contribution of previously learned environments (tasks) at the expense of the stability required to preserve previously acquired knowledge. While existing approaches have adequately studied continual learning and catastrophic forgetting in vision-language models (VLMs), the theoretical understanding of modality-specific contributions across a sequence of environments remains largely unexplored. In this paper, we present a new theoretical perspective to understand the cross-modal (vision-language) contributions to consecutive environments. We empirically evaluate our theoretical findings on large VLMs and demonstrate their effectiveness in capturing environment-level cross-modal contributions. Our analysis provides deeper insights into continual VLMs, highlighting their contribution robustness to varying task orders and inter-task similarities, and their improved generalization performance.

Read & Discuss → View Source →
14.
arXiv (CS.LG) 2026-06-16

CacheMuon: Using Temporal Preconditioning To Approximate Polar Factor

Authors:
Bishnu Dev↗Sushil Bohara↗Martin Tak\'a\v{c}↗Samuel Horv\'ath↗

arXiv:2606.16371v1 Announce Type: new Abstract: Muon is an optimizer that computes updates using the polar factor of the momentum matrix and has shown strong empirical performance across a range of training settings. A key component of Muon is the Newton-Schulz iteration used to compute this polar factor. Although this avoids the cost of an exact singular value decomposition, it remains expensive in practice because it is applied at every optimization step. At the same time, the momentum matrix changes smoothly over training, suggesting strong temporal correlation in the corresponding polar factors. In this paper, we exploit this structure and propose CacheMuon, a temporal preconditioning method that reuses information from previous optimization steps to approximate the polar factor at the current step. This reduces redundant orthogonalization computation across iterations. We analyze CacheMuon as an inexact Muon update, with error controlled by fresh-solver error and cache staleness. Empirically, CacheMuon provides a controllable quality-efficiency frontier: conservative thresholds closely match fresh Muon on language-model and vision training while reducing orthogonalization FLOPs, whereas more aggressive thresholds yield larger arithmetic savings at the cost of modest validation-quality degradation.

Read & Discuss → View Source →
15.
arXiv (CS.AI) 2026-06-18

HeRo-Q: A General Framework for Stable Low Bit Quantization via Hessian Conditioning

Authors:
Jinhao Zhang↗Yunquan Zhang↗Zicheng yan↗Boyang Zhang↗Jun Sun↗Daning Cheng↗

arXiv:2601.21626v2 Announce Type: replace-cross Abstract: Post Training Quantization (PTQ), a mainstream model compression technique, often leads to the paradoxical 'low error, high loss' phenomenon because it focuses solely on minimizing quantization error. The root cause lies in the Hessian matrix of the LLM loss landscape: a few high curvature directions are extremely sensitive to perturbations. To address this, we propose the Hessian Robust Quantization (HeRo Q) algorithm, which applies a lightweight, learnable rotation-compression matrix to the weight space prior to quantization. This joint framework reshapes the loss landscape by reducing the largest Hessian eigenvalue and reducing its max eigenvalue, thereby significantly enhancing robustness to quantization noise. HeRo-Q requires no architectural modifications, incurs negligible computational overhead, and integrates seamlessly into existing PTQ pipelines. Experiments on Llama and Qwen models show that HeRo Q consistently outperforms state of the art methods including GPTQ, AWQ, and SpinQuant not only achieving superior performance under standard W4A8 settings, but also excelling in the highly challenging W3A16 ultra low bit regime, where it boosts GSM8K accuracy on Llama3 8B to 70.15\% and effectively avoids the logical collapse commonly seen in aggressive quantization.

Read & Discuss → View Source →
16.
arXiv (CS.AI) 2026-06-15

Refusal Beyond a Single Direction: A Preliminary Comparison of Diff-in-Means and INLP

Authors:
Elisabetta Rocchetti↗Alfio Ferrara↗

arXiv:2606.13720v1 Announce Type: new Abstract: Arditi et al. (2024) has shown that refusal in safety fine-tuned chat models is mediated by a single linear direction in the residual stream, recoverable by a difference-in-means (DiM) of harmful and harmless activations. We compare DiM-based interventions (activation addition and directional ablation) with two interventions derived from Iterative Nullspace Projection (INLP) – nullspace projection and counterfactual flipping – on five open-weight chat models, asking whether INLP can match DiM at steering refusal and whether its richer parameterisation yields more tweakable interventions. INLP counterfactual flipping is competitive with DiM directional ablation on refusal suppression, while nullspace projection is consistently weaker. Restricting INLP to the leading directions of the extracted subspace preserves most of the suppression effect at near-baseline perplexity, giving a tunable capability. Geometrically, the two INLP interventions land in qualitatively different regions of activation space: nullspace projection collapses transformed activations between the harmful and harmless clusters, while counterfactual flipping moves them into the opposite cluster, suggesting that the model encodes the absence of a concept differently from its opposite – an intriguing distinction that warrants further investigation in future work.

Read & Discuss → View Source →
17.
arXiv (quant-ph) 2026-06-24

Dynamical low-rank methods for the Wigner equation I: separable difference potential

Authors:
Sihong Shao↗Yuehan Shao↗

arXiv:2606.24190v1 Announce Type: cross Abstract: Recent advances in dynamical low-rank approximation (DLRA) have demonstrated its effectiveness in high-dimensional simulations. However, existing DLRA algorithms still face significant challenges when handling systems that involve complex collision terms, including the pseudo-differential operator ($\Psi$) in the Wigner equation, a representative operator characterized by nonlocality. It is deserving to carry out a series of works to develop the DLRA algorithms for solving the Wigner equation. As the first step in this series of works, we propose an efficient DLRA algorithm for the Wigner equation, using a separable decomposition of the difference potential. We combine this separable assumption with two often-used truncations of $\Psi$, namely $\mathcal{K}$-truncation and $\mathcal{Y}$-truncation, to obtain a kind of separated representation of $\Psi$. Complexity analysis and several challenging experiments, including harmonic oscillators, Gaussian barrier scattering, electron-electron scattering, and a Helium-like system, all of which satisfy the separable assumption, confirm that the proposed DLRA algorithm has significant advantages, achieving a reduction in computational effort by one to two orders of magnitude in both runtime and memory requirements compared to the full-grid approach. It is worth noting that, even in the absence of a predetermined low-rank structure for the solution, DLRA can still serve as a numerical scheme that balances efficiency and accuracy.

Read & Discuss → View Source →
18.
arXiv (CS.CV) 2026-06-11

MultiToP: Learning to Patch Visual Tokens to Mitigate Hallucinations in Video Large Multimodal Models

Authors:
Yuansheng Gao↗Wenbin Xing↗Jiahao Yuan↗Kaiwen Zhou↗Han Bao↗Zonghui Wang↗Wenzhi Chen↗

Video Large Multimodal Models have achieved remarkable progress in video understanding, yet they remain prone to hallucinations, where generated responses are not faithfully supported by the input video. In this paper, we propose MultiToP, a multimodal-context-aware visual token patching framework that mitigates hallucinations by refining unreliable visual tokens before language generation. MultiToP introduces a lightweight Visual Token Patcher to predict token-level replacement distributions and selectively substitute unreliable visual tokens with a dynamic global patch token. To train the patcher effectively, we further propose information-guided rank calibration, which uses answer-conditioned frame-level information cues derived from the backbone to guide token replacement. Combined with ground-truth answer supervision and sparsity regularization, MultiToP enables localized visual evidence refinement without modifying the original model. Extensive experiments demonstrate that MultiToP effectively reduces hallucinations on Vript-HAL with negligible inference overhead, improving the F1 scores of Qwen3-VL-4B-Instruct by 50.60% over the vanilla model. Meanwhile, MultiToP preserves general video understanding ability, yielding an 18.58% relative accuracy gain on ActivityNet-QA for Video-LLaVA-7B.

Read & Discuss → View Source →
19.
arXiv (CS.AI) 2026-06-19

Measuring Biological Capabilities and Risks of AI Agents

Authors:
Patricia Paskov↗Jeffrey Lee↗Kyle Brady↗Alyssa Worland↗

arXiv:2606.19899v1 Announce Type: cross Abstract: This paper addresses a rapidly emerging policy challenge: how to generate and interpret credible evidence about the biological capabilities and risks of AI scientists, or agentic AI systems capable of autonomously or collaboratively performing multi-step scientific tasks. As these systems enter real research workflows, decision-makers increasingly face evaluation results whose meaning depends on underlying design choices that are often implicit or under-documented. We synthesize current evidence on AI-enabled biological risks and introduce biological agentic evaluations as a promising, but interpretation-sensitive, tool for assessing these systems. Our central contribution is a set of practical, experience-grounded considerations – drawing from our own evaluations – that show how choices around defining, designing, running, scoring, and documenting evaluations materially shape what results do and do not imply about risk. The analysis is intended to help policymakers interpret biological evaluation outputs with appropriate caution; guide public and private funders toward high-leverage investments in AI-biology evaluation research; and support biosecurity practitioners assessing emerging AI systems. A secondary audience includes researchers designing or conducting agentic evaluations within frontier AI labs, AI providers, scientific institutions, and third-party evaluation organizations.

Read & Discuss → View Source →
20.
arXiv (CS.CV) 2026-06-17

MODE-RAG: Manifold Outlier Diagnosis and Energy-based Retrieval-Augmented Generation Evaluation

Authors:
Zehang Wei↗Jiaxin Dai↗Jiamin Yan↗Xiang Xiang↗

While Multimodal Retrieval-Augmented Generation (M-RAG) enhances Large Vision-Language Models, it remains highly susceptible to cross-modal hallucinations, causal fabrications, and sycophancy. Furthermore, existing mitigation pipelines often face an intervention paradox: static rules tend to unnecessarily disrupt accurate generations, whereas leaving the multi-modal reasoning completely unguided allows existing mismatches to cascade into severe logical fabrications. To quantify and mitigate these hallucinations, we propose a Multi-Agent system, MODE-RAG, driven by Variational Free Energy (VFE) and internal attention states to dynamically gate interventions. High-risk queries are routed to five stage-specific agents, integrating Monte Carlo Tree Search (MCTS) for rigorous causal derivation and logit perturbations to penalize sycophancy. Dedicated Correction and Overseer agents ensure formatting stability and perform post-hoc factual verification. To objectively evaluate our approach, we introduce ModeVent, a challenging subset derived from the MultiVent dataset. Extensive experiments indicate that our system effectively reduces hallucination rates and logical fabrication, significantly improving the robustness of M-RAG systems.

Read & Discuss → View Source →
21.
arXiv (CS.AI) 2026-06-17

CMIP-Forge: An Agentic System that Retrieves, Computes, and Self-Reviews Climate Science

Authors:
Dmitrii Pantiukhin↗Boris Shapkin↗Ivan Kuznetsov↗Thomas Jung↗Nikolay Koldunov↗

arXiv:2606.17076v1 Announce Type: cross Abstract: The Coupled Model Intercomparison Project Phase 6 (CMIP6) has generated thousands of peer-reviewed publications documenting model configurations, evaluation procedures, emergent constraints, and projection uncertainties. As the community transitions toward CMIP7, efficiently extracting and operationalizing this unstructured knowledge alongside live data analysis represents a critical bottleneck. Here we present CMIP-Forge, a hybrid retrieval-augmented generation (RAG) and autonomous analysis system that bridges the gap between scientific literature and Earth System Grid Federation (ESGF) data archives. The system pairs a curated corpus of 6,581 CMIP6-related open-access publications (101,828 indexed chunks) with an agentic pipeline in which a tool-augmented worker plans and executes Python workflows over live climate data, while a panel of independent reviewer models audits its methodology end to end. CMIP-Forge introduces a multi-layered Defense-in-Depth architecture that enforces physical and methodological invariants through executable mechanisms: Abstract Syntax Tree (AST) static analysis, audited scientific primitives, and an autonomous adversarial peer-review protocol. We demonstrate the system's capabilities through end-to-end autonomous research pipelines spanning atmospheric teleconnections, ocean dynamics, regional extremes, and global warming projections. An agentic analysis system grounded in peer-reviewed literature, constrained by automated code guardrails, and audited by an independent adversarial review loop can complete complex climate-research workflows autonomously. The same experiments expose concrete failure modes of the review loop (sycophantic regression, REVISE verdicts that are never resolved, and the submission of stub code for review), each diagnosable from the immutable telemetry and provenance record released with the article.

Read & Discuss → View Source →
22.
arXiv (CS.AI) 2026-06-24

EG-VQA: Benchmarking Verifiable Video Question Answering with Grounded Temporal Evidence

Authors:
Linpeng Huang↗Weixing Chen↗Zexin Chen↗Yang Liu↗Liang Lin↗

arXiv:2606.24797v1 Announce Type: cross Abstract: Recent advances in Video Large Language Models (Video-LLMs) have yielded promising performance on video question answering (VideoQA). Nevertheless, existing benchmarks are predominantly evaluated through answer correctness, while the grounding of predictions in relevant video evidence remains largely unexamined. This disconnect between answer generation and evidence understanding motivates the construction of the Evidence-Grounded Video Question Answering Benchmark (EG-VQA), an open-ended evaluation protocol in which each QA pair is explicitly annotated with supporting temporal evidence, thereby requiring joint reasoning and precise evidence localization. EG-VQA is comprised of 2,067 videos and 11,838 QA pairs with fine-grained evidence annotations. To evaluate predicted evidence, Evidence-Grounded F1 (EG-F1) is introduced as a unified metric in which temporal alignment and semantic consistency against ground-truth evidence are jointly measured. Experimental evaluation reveals that even strong proprietary models struggle to accurately ground their predictions, exposing a fundamental discrepancy between answer correctness and faithful evidence localization. To bridge this gap, EG-Reasoner, an evidence-grounded reasoning model trained with explicit supervision, is proposed. State-of-the-art performance is achieved among open-source models, with results competitive against proprietary systems, particularly pronounced gains are observed on reasoning-intensive tasks such as counterfactual questions. These findings demonstrate that scaling alone is insufficient for robust video understanding and that structured evidence supervision is essential for the development of more reliable and interpretable VideoQA systems.

Read & Discuss → View Source →
23.
arXiv (CS.AI) 2026-06-12

Valid Inference with Synthetic Data via Task Exchangeability

Authors:
Lezhi Tan↗Tijana Zrnic↗

arXiv:2606.13629v1 Announce Type: cross Abstract: There is a proliferation of work arguing for the use of synthetic data in scientific research. For example, social scientists are arguing for the use of LLM-generated "silicon samples" in pilot studies; AI evaluations increasingly rely on "LLM-as-a-judge" outputs; and proteomics research is accelerated by generative models that produce synthetic protein structures. These developments raise an intriguing possibility: synthetic data may help researchers ask more questions, run more studies, and accelerate discovery. But they also raise a fundamental concern: synthetic data can be biased, noisy, and misspecified. In this work, we propose statistical principles for using synthetic data in scientific research with provable validity guarantees. The key insight is a new technical condition that we call task exchangeability. Informally, this is a requirement that the researcher can identify historical tasks, for which real data is available, such that their current task of interest is exchangeable with the historical tasks in an appropriate mathematical sense. We develop methods for valid inference under task exchangeability, together with extensions that provide guarantees even beyond exchangeability. We demonstrate the framework on public opinion surveys with silicon samples and AI evaluation with autoraters.

Read & Discuss → View Source →
24.
arXiv (CS.AI) 2026-06-19

AI Economist Agent: An Agentic Framework for Model-Grounded Economic Analysis with RAG, Knowledge Graphs, and Large Language Models

Authors:
Masahiro Kato↗

arXiv:2606.20041v1 Announce Type: cross Abstract: We propose a model-grounded RAG-based AI economist with an agentic framework for economic scenario analysis using large language models (LLMs) and knowledge graphs. While LLMs can generate fluent economic narratives, economists are often required to make economic claims grounded by economic theory and real-world data. Based on this motivation, this study proposes an RAG-based AI economist, which utilizes knowledge graphs including economic data and theory and LLM-based agents to plan the analysis, retrieve relevant evidence, select appropriate models, and generate reports. In our framework, we do not produce quantitative claims directly with the language model alone; instead, we generate narratives grounded in explicit model-based computations and linked to the retrieved evidence via AI agents. We refer to our framework as an AI economist agent. We evaluate the AI economist agent in two applications: economist report generation for U.S. inflation persistence and Federal Reserve policy, and bank stress-test narrative generation for U.S. commercial real estate refinancing stress. The results illustrate how grounding the generated reports improves their economic coherence and traceability.

Read & Discuss → View Source →
25.
arXiv (CS.CL) 2026-06-18

LLMZero: Discovering Adaptive Training Strategies for RL Post-Training via LLM Agents

Authors:
Haoyang Fang↗Wei Zhu↗Boran Han↗Alex Zhang↗Zhenyu Pan↗Shuo Yang↗Shuai Zhang↗Jiading Gai↗Peng Tang↗Cuixiong Hu↗Xuan Zhu↗Huzefa Rangwala↗…

RL post-training strategies are dataset-dependent and reveal a recurring empirical pattern: capacity parameters accumulate monotonically across stages, while regularization parameters predominantly oscillate in response to shifting training dynamics. This distinction matters because fixed schedules commit all parameters to fixed trajectories and therefore cannot express the non-stationary exploration-exploitation tradeoffs that regularization must track; the principle provides actionable design rules for multi-stage training. We discover this through LLMZero, a system where LLM agents search over training trajectories via tree search, diagnosing pathologies at each checkpoint and proposing coordinated multi-parameter transitions. Across 4 diverse GRPO tasks, LLMZero discovers strategies that improve over the base model by 9% to 140% relative and over grid search by 6% to 15% relative, consistently outperforming random search and the skill-based agent. The structural principle transfers across tasks, providing an explanation for why discovered strategies take qualitatively different forms yet share similar parameter dynamics.

Read & Discuss → View Source →