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) 2026-06-12

Design, Implementation, and Evaluation of a Shadowing Program for Medical Students in the Basic Sciences Phase

Introduction Shadowing, as an educational method based on active observation, can foster a realistic understanding of professional roles and enhance the communication skills of medical students. This study aimed to design, implement, and evaluate a shadowing program for basic sciences medical students. Methods This development study was conducted based on the ADDIE model in five phases. The study population consisted of 799 medical students in semesters 2 to 5. The stages included Analysis (determining needs through literature review and expert panels), Design (specifying learning environments and evaluation methods), Development (preparing guides and educational tools), Implementation (within the Medical Ethics course), and Evaluation (using questionnaires and reflection forms). Findings This study aimed to design and evaluate an educational shadowing program based on the ADDIE model. In the Analysis phase, the profiles of 799 students and learning objectives were determined. In the Design phase, a structured program for four types of shadowing was designed. In the Development phase, all guides and educational tools were prepared. In the Implementation phase, the program was carried out with complete coverage and adherence to ethical considerations. Finally, the program evaluation showed that "Motivation to become a good physician" (3.75-3.95) and "Enhancing empathy" (3.50-3.94) received the highest scores, while "Increasing understanding of the basic science-clinical connection" (2.53-2.89) and "Willingness to attend on holidays" (1.87-2.31) received the lowest scores. Conclusion The findings indicate that implementing the shadowing program is an effective method for strengthening the professional attitudes and academic motivation of medical students. However, the program did not significantly improve students perception of the basic science-clinical connection, indicating a need for curricular refinement. The continuation and extension of this program to other levels and fields of medical sciences are recommended.

02.
arXiv (quant-ph) 2026-06-12

Scalar Quantum Fields: Theory Space and its Geometry

arXiv:2606.12580v1 Announce Type: cross Abstract: Scalar fields provide perhaps the simplest playground in which to develop our understanding of quantum field theory. In this lecture, we consider what it means to write down a scalar quantum field theory and how we can give geometrical interpretations to the space of such theories: the theory space.

03.
arXiv (CS.AI) 2026-06-25

Agentic Knowledge Tracing: A Multi-Agent LLM Architecture for Stealth Assessment of Financial Literacy in Serious Games

arXiv:2606.25358v1 Announce Type: new Abstract: Assessing financial literacy during gameplay without disrupting the learning experience remains a key challenge in serious games for education. We present the Agentic BKT pipeline, a multi-agent large language model architecture for stealth assessment of financial competencies from open-ended gameplay events. The pipeline processes events from a 2D platformer serious game aligned with the OECD/INFE financial literacy framework through four phases: (1) the game captures every player decision as a structured event log; (2) an LLM event classifier labels each action on a four-point rubric validated against three domain experts (Fleiss kappa = 0.624, substantial agreement); (3) four domain-specific agents specializing in risk mitigation, investing, spending, and credit management perform session-level reasoning over behavioral trajectories, feeding per-competency Bayesian Knowledge Tracing that estimates mastery within each domain; and (4) an expert judge agent synthesizes the domain-level estimates into an overall mastery score. Evaluated with 193 K-12 participants across 264 game sessions, the Agentic BKT pipeline yields mastery estimates significantly correlated with learning gain (r = 0.276, p = 0.0001) and post-test scores (r = 0.333, p < 0.0001) while showing no correlation with pre-test scores, providing both convergent and discriminant validity. The multi-agent approach approximately triples the predictive validity of a single-LLM baseline (r = 0.095, not significant) in this study, demonstrating that domain decomposition and session-level reasoning play a central role in capturing the multidimensional nature of financial literacy from gameplay

04.
arXiv (math.PR) 2026-06-12

Non-commutative Law of iterated logarithm

arXiv:2509.22037v2 Announce Type: replace-cross Abstract: We prove optimal non-commutative analogues of the classical Law of Iterated Logarithm (LIL) for both martingales and sequences of independent (non-commutative) random variables. The classical martingale version was established by Stout [Sto70b] and the independent case by Hartman-Wintner [HW41]. Our approach relies on a key exponential inequality essentially due to Randrianantoanina [Ran24] that improves that from Junge and Zeng [JZ15]. It allows to derive an optimal non-commutative Stout-type LIL just as in [Zen15], from that martingale result we then deduce a non-commutative Hartman-Wintner type LIL for independent sequences of random variables.

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

AdversaBench: Automated LLM Red-Teaming with Multi-Judge Confirmation and Cross-Model Transferability

Scaling adversarial evaluation of large language models requires both a method for generating hard inputs and a reliable way to confirm that resulting failures are real. We present AdversaBench, an end-to-end red-teaming pipeline that mutates seed prompts with five structured operators, queries a target model, and confirms failures through a three-judge panel with a meta-judge tiebreaker. We report experiments on 45 seeds across three categories: reasoning, instruction-following, and tool use. Every seed produced a confirmed failure. Four findings stand out. First, operator effectiveness varies sharply by category: inject_distractor scores 0.00 mean reward on instruction-following seeds but 0.80-0.83 on reasoning and tool-use. Second, binary failure rate hides difficulty: instruction-following seeds required 2.4 attacker iterations on average versus 1.1 for other categories, a gap visible in survival curves. Third, pairwise judge agreement of 80-87% coexists with near-zero Cohen's kappa due to label skew; category-level disagreement rates are more informative. Fourth, adversarial prompts generated against Llama 3.1 8B transfer zero-shot to Llama 3.3 70B, suggesting the mutations exploit general behavioral patterns rather than model-specific weaknesses. Code, dataset, and analysis scripts are available at https://github.com/khanak0509/AdversaBench .

07.
arXiv (quant-ph) 2026-06-12

Approximate quantum error correction theory of non-isometric codes

arXiv:2606.13559v1 Announce Type: new Abstract: Non-isometric encoding arises in various important contexts in quantum error correction, most notably in the finite-energy, non-ideal codewords inevitable in experimental realizations of continuous-variable codes, and holographic quantum gravity. In this work, we present a general and systematic theory of non-isometric quantum error-correcting codes. In particular, we employ the approximate quantum error correction framework to quantitatively study the fundamental limitations imposed by non-isometric encodings on the accuracy of quantum error correction and implementation of logical operations. We apply our theory to analyze GKP and tiger codes under energy constraints, and discuss the implications to holography.

08.
arXiv (quant-ph) 2026-06-25

Halo-Independent Quantum Sensor Probes of Low-Velocity Dark Matter

arXiv:2606.25129v1 Announce Type: cross Abstract: We present a halo-independent framework for sub-GeV dark matter (DM) direct detection using quantum sensors with sub-eV energy thresholds. Such detectors enable access to low DM velocities and may be sensitive to departures from the Standard Halo Model that are challenging to probe with conventional direct DM detection experiments. The method expresses the DM scattering event rate in terms of a detector and particle model-dependent response function, and a universal halo function common to all experiments to be determined from data. This allows the local DM velocity distribution to be constrained. As representative implementations, we consider TES (Al) and MKID (TiN)-like sensors and show that their differing material responses probe complementary regimes of the DM velocity distribution. Applying the framework to mock data derived from several benchmark local halo models, we demonstrate how the assumed halo function could be reconstructed. This framework demonstrates the potential of quantum sensors as a new avenue for mapping the local DM velocity distribution.

09.
arXiv (quant-ph) 2026-06-25

Note About Koopman-von Neumann Theory and Density Matrix

Authors:

arXiv:2606.25085v1 Announce Type: new Abstract: In this short note we study Koopman-von Neumann theory for N-particle system. We argue that it is natural to identify classical N-particle distribution function as diagonal form of density matrix operator in coordinate representation. We also determine generalized BBGKY hierarchy for reduced density matrix in coordinate representation.

10.
arXiv (CS.CL) 2026-06-12

Multi-Turn Reasoning When Context Arrives in Pieces: Scalable Sharding and Memory-Augmented RL

When a user reveals task-critical information across several conversation turns, LLM accuracy drops by up to 65% despite full context availability. We show that this Lost in Conversation degradation can be substantially mitigated by training models to maintain a compact rolling memory instead of attending to a growing history. To make such training scalable, we introduce a low-cost sharding pipeline that converts single-turn QA datasets into multi-turn fragmented-information episodes, eliminating the need for hours of manual annotation. Training only on sharded GSM8K, our memory-augmented policy significantly improves multi-turn accuracy and generalises zero-shot to harder math and out-of-domain long-context QA. Moreover, memory-trained models outperform full-history baselines even when given the full history at test time, suggesting that learning to compress induces more robust incremental reasoning than full-context exposure alone.

11.
medRxiv (Medicine) 2026-06-22

Climatic Drivers of Malaria risk in Children Under Five: A Large-Scale Analysis of individual-level data for 350,000 children in 26 Sub-Saharan African Countries

Background Malaria risk is influenced by climatic conditions, and children under five are particularly vulnerable due to their limited acquired immunity. We investigate the association between climatic factors and malaria risk in 350,000 children aged 5-59 months in sub-Saharan Africa over 18 years. Methods We included children aged 5-59 months with malaria tests from Demographic and Health Surveys (DHS) in 26 sub-Saharan African countries between 2006 and 2023. We linked these data to high-resolution climate exposures: temperature, precipitation, soil moisture, actual evapotranspiration and specific humidity. We fitted a mixed-effect logistic regression model incorporating Distributed Lag Non-linear Models (DLNM) over 1-6 month lag window for each exposure, controlling for seasonality and long-term trends. We examined effect modification by maternal education, household wealth, residential type, water source, sanitation facility, child age and sex, use of insecticide-treated bed nets (ITNs), and the age of the household head. Results Malaria prevalence was 19.5%. Malaria risk was highest at 24 degrees (OR: 1.45, 95% CI: [1.36, 1.54]), followed by a decline at higher temperatures. This elevated risk was mainly driven by short-term exposures (1-2 months). Precipitation increased risk up to 59 ~ 120 mm (1.10, [1.07, 1.12]), after which heavier rainfall reduced risk, particularly at short- to medium-term lags (1-4 months). Soil moisture was associated with increasing risk up to ~80 mm (1.11, [1.08, 1.14]), with a plateau at higher levels. Evapotranspiration showed a strong, near-linear positive association with malaria risk. Higher specific humidity levels (>14 g/kg) presented a lower risk, reaching a 45% reduction at 17 g/kg (0.55, [0.49, 0.61]), with the strongest protective effects at short-term lags (1-2 months). Elevated malaria risk at low and moderate average temperatures was particularly evident among children who did not sleep under an ITN net. Conclusion Malaria risk in children under five is strongly shaped by climatic factors, with complex and delayed associations. The findings provide evidence to guide targeted interventions and early-warning strategies for vulnerable populations.

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

Graph-based Target Back-Propagation for Context Adaptation in Multi-LLM Agentic Systems

Context adaptation automates prompt engineering in LLM-based systems by iteratively revising tunable prompts from task feedback, without modifying model weights. Extending this paradigm to multi-LLM agentic systems is crucial: existing methods suffer from inaccurate credit assignment and lack convergence guarantees. We propose Graph-based Target Back-Propagation (GTBP), a context adaptation framework for agentic workflows modeled as directed acyclic graphs. GTBP propagates local target outputs backward through the workflow graph and uses target–output discrepancies to guide a stage-wise prompt update mechanism. Theoretically, we show that GTBP's stage-wise prompt updates become stable over iterations, and that a sufficiently capable LLM optimizer can decrease the overall objective. Empirically, GTBP consistently outperforms strong baselines across three benchmarks while maintaining comparable computational cost.

13.
arXiv (CS.AI) 2026-06-16

LLM4RTL: Tool-Assisted LLM for RTL Generation

arXiv:2606.15500v1 Announce Type: cross Abstract: Large language models (LLMs) have facilitated impressive progress in software engineering, code generation, tooling, and systems. Concurrently, a significant body of research has developed which explores a growing variety of methods and systems for applying LLMs to hardware and chip design (e.g., systems for RTL code generation based on functional description). However, when it comes to open Verilog/RTL code-generation, we need high-quality training samples to build specialized and more effective LLM systems through fine-tuning or low-rank adaptation. Here, we propose a ``judge-renew-check-renew-check'' (JRCRC) pipeline which updates a current public dataset using a hierarchy of state-of-the-art commercial LLM models differing in their costs and capabilities in RTL code generation. This approach achieves a cost-effective mechanism for filtering and refining code-generation samples into a higher-quality training dataset. Our experiments also identify some common weaknesses of LLMs in rule-based reasoning and logic, and consequently, in RTL code-generation. Having identified these weaknesses, we develop an architecture for incorporating pre-processing tools to dynamically assist the LLMs in inferring logical relationships from tabular data formats. With our tools-assisted architecture for RTL code generation, we achieve significant overall performance gains in the VerilogEval benchmark and outperform many state-of-the-art methods. Our LLM4RTL system achieves performance comparable to that of GPT-4O using a significantly much smaller LLM.

14.
arXiv (CS.AI) 2026-06-17

Surveying GenAI-based Automation in Printed Circuit Board Design and Test

arXiv:2606.17074v1 Announce Type: cross Abstract: Generative artificial intelligence (GenAI) is increasingly used for applications in the hardware and software domains. It purports to reduce the manual effort involved in the development and testing of complex systems before release. Within the hardware space, most tasks have focused on design automation of integrated circuits, particularly with hardware description languages. However, other types of hardware also exist! In this survey, we instead examine how GenAI has been and is being across the printed circuit board (PCB) design life cycle. This includes everything from supply chains, system specification, circuit design, layout and optimisation, validation and test, and PCB assembly and distribution. Through this lens we present a taxonomy of discovered works, categorising them according to their intent and contributions. This survey also identifies key technical challenges that GenAI faces in this space, such as domain-specific data scarcity and limited support for integration with existing PCB tools. Finally, future research directions are discussed: our survey shows that there are many opportunities remaining when considering how GenAI may be integrated into various tasks in PCB design and test.

15.
medRxiv (Medicine) 2026-06-23

Intellectual Property Literacy, Innovation Readiness and Innovation Practice in Syria's Pharmaceutical Sector: A Cross-Sectional Study

Background Innovation in pharmaceutical sectors operating under resource and institutional constraints may depend not only on knowledge and attitudes but also on the conditions that enable innovation-related activities to occur. This study examined the relationships among intellectual property (IP) literacy, innovation attitudes, innovation readiness, and reported innovation practice among pharmaceutical professionals in Syria. Methods A cross-sectional survey was conducted among 303 pharmaceutical professionals between March and April 2026. Four composite indices were constructed to assess IP literacy, innovation attitudes, innovation readiness, and innovation practice. Descriptive statistics, correlation analyses, group comparisons, and multivariable regression models were used to characterize patterns of association among study domains. The analysis was designed to identify empirical patterns rather than infer causal relationships. Results Innovation attitudes were comparatively high (73.56/100), whereas innovation readiness (17.00/100) and innovation practice (12.65/100) were substantially lower. IP literacy was positively associated with innovation readiness (r = 0.384, p < 0.001) and innovation practice (r = 0.205, p < 0.001). In contrast, innovation attitudes were not significantly associated with reported innovation practice (p = 0.332). Regression analyses indicated that the inclusion of innovation readiness improved model fit beyond specifications based on knowledge and attitudes alone ({Delta}R{superscript 2} = 0.058, p = 0.028). Significant differences in readiness and practice were observed across professional groups (p < 0.001), whereas knowledge and attitudes showed limited variation. Conclusions High levels of innovation-related knowledge and positive attitudes did not correspond to high levels of reported innovation practice in this setting. The findings suggest that innovation readiness may capture enabling conditions that are not reflected by knowledge or attitudinal measures alone. These results support the value of examining contextual and institutional factors when assessing innovation capacity in resource-constrained pharmaceutical systems. Given the substantial gap observed between innovation attitudes and innovation practice, educational strategies may represent one avenue for strengthening innovation readiness. In the Syrian context, strengthening innovation-oriented education and university-industry engagement may help cultivate innovation competencies and support the translation of research into practical applications.

16.
medRxiv (Medicine) 2026-06-18

Web-based education on Metabolism and Obesity is associated with improved lifestyle and health behaviours among Brazilian school teachers

Background: Obesity is a major global public health challenge, and teachers play a critical role in school-based health promotion. This study examined the perceived impact of a web-based educational program on metabolism and obesity delivered to Brazilian school teachers. Methods: This analytical cross-sectional study included 217 teachers who responded to the evaluation questionnaire after attending the course between 2017 and 2022. Statistical analyses included logistic regression and chi-square tests. Findings: Course completion rate was 81.98%, substantially exceeding the 5-15% typical of global MOOCs. However, ethnic disparities were observed: White respondents were 4.95 times more likely to complete the course than Black respondents (p=0.00097) and Brown respondents were 3.05 times more likely (p=0.0268) than Black respondents. Among non-completers, lack of time (64.7%) was the primary barrier. Participation was concentrated in Sao Paulo (77%), with no respondents from three northern states. Perceived difficulty showed a non-significant trend (p=0.0893) where by Black respondents had the lowest predicted difficulty; the most challenging course material was Scientific Content/Reading papers (50%). Completion was strongly associated with applying learned activities in teaching (p

17.
arXiv (CS.CV) 2026-06-15

A Robust Point Cloud Analysis Framework Inspired By Primary Visual Cortex

Despite significant advancements in point cloud analysis, reducing energy consumption and improving robustness remain understudied, largely due to the inherent limitations of Convolutional Neural Networks (CNNs). To address this issue, we draw inspiration from the primary visual cortex and propose a Dendritic-Connected Continuous-Coupled Neural Network (DC-CCNN), a novel Brain-Inspired Neural Network (BINN) architecture for point cloud analysis. By combining discrete and continuous encoding, our design replaces traditional Multilayer Perceptrons (MLPs) with more efficient and robust BINNs. Building upon this framework, we further propose an extended model, DC-CCNN++, to improve robustness under complex corruption conditions. Specifically, we introduce a Neuro-Inspired Robust Modulation-and-Readout Module (NRMR) to enhance feature stability and decision robustness through global-context gain modulation and dual-code evidence integration. We also design a Cortically Inspired Progressive Variability Training (CPVT) strategy, which progressively exposes the model to structured environmental variability while preserving stable clean-sample anchors during training. Experimental results show that DC-CCNN++ improves the performance of brain-inspired networks on point cloud analysis while maintaining performance comparable to state-of-the-art methods. Compared with the original DC-CCNN, it achieves stronger results on both classification and part segmentation, and exhibits enhanced robustness against sparsity, occlusion, Gaussian noise, salt-and-pepper noise, and spatial transformations. With its efficiency, robustness, and biologically grounded design, DC-CCNN++ provides a promising alternative to traditional deep learning methods for point cloud analysis. Code is available at https://anonymous.4open.science/r/DC-CCNNpp-44E3.

18.
arXiv (CS.AI) 2026-06-24

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

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.

19.
arXiv (CS.CV) 2026-06-24

ViTexQA: A Multi-Frame Temporal Perception Dataset for Video Text Question Answering

Despite remarkable progress in multimodal understanding, current MLLMs still exhibit limitations in video text understanding, particularly when semantics emerge through the integration of temporally distributed textual cues across multiple frames. This perception challenge fundamentally differs from static image text understanding, yet existing datasets fail to capture: the vast majority of questions remain answerable from single frames, inadequately reflecting real-world video text comprehension demands. To address this, we present ViTexQA, a large-scale video-text QA dataset, and FrameThinker for robust multi-frame temporal reasoning. We build ViTexQA via a quality-controlled Chain-of-Thought (CoT) annotation pipeline boosted with temporal constraints; all its QA pairs demand cross-frame text fusion to solve, enforcing true temporal reliance. FrameThinker adopts two-stage training for explicit temporal modeling: CoT-Guided Supervised Fine-Tuning (SFT) generates frame-aware reasoning chains, followed by Temporally-grounded Reinforcement Learning (RL) optimized with multi-frame coherence rewards. Evaluations show our method outperforms SOTA baselines on ViTexQA, lifting ROUGE-L by 6.3%.

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

EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery

LLM-based agents have shown increasing potential in automating scientific discovery. Given an optimizable metric and an execution environment, they can propose, validate, and iterate scientific solutions, and have produced results that outperform human-designed approaches. As model capabilities continue to improve, we argue that the bottleneck for autonomous scientific discovery is shifting from prescribing agent workflows to designing agent environments: the resources, constraints, and interfaces that shape agent behavior. We frame this as environment engineering: building environments that amplify productive behaviors, such as open-ended exploration, systematic artifact management, and inter-agent collaboration, while suppressing harmful behaviors, such as reward hacking and high-friction human oversight. We present EurekAgent, an environment-engineered agent system for metric-driven autonomous scientific discovery. EurekAgent engineers the environment along four dimensions: permissions engineering for bounded agent execution and isolated evaluation; artifact engineering for filesystem and Git-based collaboration; budget engineering for budget-aware exploration; and human-in-the-loop engineering for easy human supervision and intervention. EurekAgent sets new state-of-the-art results on multiple mathematics, kernel engineering, and machine learning tasks, including new state-of-the-art 26-circle packing results discovered with less than $11 in total API cost. We open-source our code and results, and call for environment engineering as a core research direction for developing reliable autonomous research agents.

21.
Nature (Science) 2026-06-24

‘Megacluster’ of genes enables bacteria to make potent antibiotic mixture

Soil bacteria make cocktails of molecules that synergistically inhibit the growth of microbial pathogens — suggesting a strategy for tackling antibiotic-resistant infections. Soil bacteria make cocktails of molecules that synergistically inhibit the growth of microbial pathogens — suggesting a strategy for tackling antibiotic-resistant infections.

22.
arXiv (quant-ph) 2026-06-24

Multipartite synchronization residuals in driven-dissipative spin networks

arXiv:2606.24360v1 Announce Type: new Abstract: We introduce a phase-space measure of quantum synchronization that quantifies relative phase localization for two-qubit and three-qubit systems. This measure is built from the first angular moments of phase distributions obtained from Husimi-Q quasiprobability functions. Using this framework, we formulate a new class of synchronization residuals, motivated by subadditivity-type hierarchies of information-theoretic measures. We investigate these residuals in a driven-dissipative quantum Rabi network in the dispersive adiabatic regime. We show that, for two qubits, collective synchronization remains bounded by single-qubit contributions yielding a non-negative bipartite residual. The three-qubit nonequilibrium steady state exhibits a negative tripartite residual, which indicates collective phase synchronization, which cannot be described by pairwise decomposition. The corresponding entropy-based residuals, however, remain non-negative in both cases. Our results therefore, underscore that phase-sensitive synchronization measures and entropic correlation measures probe distinct aspects of open-system dynamics.

23.
arXiv (CS.LG) 2026-06-16

The Complexity of Min-Max Optimization for Quadratic Polynomials

arXiv:2606.17000v1 Announce Type: cross Abstract: We prove that computing approximate stationary points of min-max optimization over the hypercube is PPAD-hard for quadratic polynomials. This holds even when the polynomials are multilinear, each variable appears in at most three monomials, and the approximation factor is inverse polynomial. As a direct consequence, we obtain the first PPAD-hardness results for two-team zero-sum polymatrix games.

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

SHERLOC: Structured Diagnostic Localization for Code Repair Agents

LLM agents solve repository-level coding tasks through multi-turn tool use, but utilize half their budget on locating faults before editing. Dedicated localization frameworks have emerged, yet are still evaluated as file retrieval rather than actionable diagnosis, producing locations without the diagnostic context a repair agent needs. We introduce SHERLOC (Structured Hypothesis-driven Exploration and Reasoning for Localization), a training-free framework pairing a reasoning LLM with compact repository tools and self-recovery, without fine-tuning or multi-agent orchestration. SHERLOC reaches state-of-the-art localization across model scales: 84.33% accuracy@1 on SWE-Bench Lite and 81.27% recall@1 on SWE-Bench Verified; at ~30B parameters, it matches or outperforms other agentic methods. Injecting our locations and diagnostic findings into repair agents yields, on average, +5.95 pp resolve rate on SWE-Bench Verified while cutting localization and total tokens by 36.7% and 23.1%.

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

Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models

arXiv:2606.19297v1 Announce Type: new Abstract: Embodied Vision-Language-Action (VLA) models are typically obtained by fine-tuning powerful pretrained VLMs on robotics data, yet it is unclear how much commonsense and factual knowledge they retain after adaptation. Failures on knowledge-sensitive tasks are ambiguous, conflating missing knowledge with poor generalization of low-level control. We introduce Act2Answer, a lightweight protocol that adapts VLM knowledge benchmarks to VLA evaluation by requiring agents to answer through action. Each question becomes a short tabletop episode where the agent performs a single object-placement action to select among candidate answers, yielding an action-grounded success rate with reduced control confounds. We curate a test suite of such environments across diverse commonsense and world-knowledge categories and introduce layerwise intent probing to localize answer-relevant information across the VLM backbone and action head. In a large-scale study of 7 VLA models and 9 VLM baselines, we systematically rank models across categories, finding that VLAs show solid performance on simple concepts while exhibiting larger gaps on richer semantic categories relative to their source VLMs, that VQA co-training is associated with better knowledge retention, and that answer-relevant signals peak in middle VLA layers but attenuate in upper layers. Act2Answer is available at https://tttonyalpha.github.io/act2answer/.