Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

01.
arXiv (quant-ph) 2026-06-16

Against probability: A quantum state is more than a list of probability distributions

arXiv:2601.18872v2 Announce Type: replace Abstract: The state of a quantum system can be represented by listing the outcome probabilities for a tomographically complete set of measurements. Such representations appear throughout physics, for example, in quantum field theory via correlation functions and in quantum foundations within generalized probabilistic frameworks. In this paper, we show a no-go result: To enable useful statements, the probability representation must be topologically robust$\unicode{x2014}$preserving the notion of closeness between states. Yet, a topologically robust probability representation cannot simultaneously retain other essential structure, such as the subsystem structure.

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

Keep Policy Gradient in Charge: Sibling-Guided Credit Distillation for Long-Horizon Tool-Use Agents

Long-horizon tool-use reinforcement learning can learn from outcome verification, but its trajectory-level advantage is broadcast across many reasoning, API, and answer tokens. Self-distillation promises a denser signal by reusing a policy's own rollouts or a privileged teacher. We show, however, that direct token-level self-distillation can silently destroy tool use: it rehearses teacher behavior without knowing which actions the verifier rewards, so useful skills and harmful shortcuts are amplified together. We introduce Sibling-Guided Credit Distillation (SGCD), which uses distillation for credit assignment rather than as a competing actor loss. Dynamic sampling produces mixed successful and failed sibling rollouts; an external LLM summarizes their contrast into a training-only stepwise credit reference; dense teacher/student divergence drives credit reassignment; and bounded detached credit weights reshape GRPO token advantages. The deployed student sees no external LLM, sibling evidence, or oracle. Across AppWorld and $\tau^3$-airline, SGCD improves over matched GRPO comparators: AppWorld TGC $42.9 \to 45.6$ on test_normal and $24.7 \to 27.0$ on test_challenge, and $\tau^3$-airline pass@1 $0.583 \to 0.602$.

03.
arXiv (CS.CL) 2026-06-15

SANA: What Matters for QA Agents over Massive Data Lakes?

Exploratory question answering (EQA) over data lakes requires an LLM agent to discover relevant sources, analyze retrieved data, and adapt its actions based on intermediate results. End-to-end accuracy alone cannot distinguish failures in search, planning, data analysis, or the agent's Action Policy: its decisions about what to do next and when to submit an answer. We present SANA (Search Agent Navigation Ablation framework), a diagnostic ablation framework that transforms EQA tasks into runtime profiles containing gold source sequence, sanitized subquestions, and execution records. SANA uses these profiles to construct idealized search, planning, and data-analysis tools, allowing each component to be ablated; the residual gap is diagnostic evidence for policy failures. To illustrate SANA as a reusable evaluation framework, we adapted two recent EQA benchmarks, LakeQA and KramaBench, and evaluated lightweight and mid-sized agents under fixed prompts, budgets, data lakes, and runtimes. Across both benchmarks, data analysis is a consistent bottleneck while planning is less so. Search is a major limitation in LakeQA's large data-lake setting, but less so for the smaller-scale KramaBench. SANA thus deconstructs end-to-end task accuracies into a diagnosis of where data-lake agents fail, and allows for systematic comparisons of progress in search, planning, data analysis, and agent design.

04.
arXiv (CS.LG) 2026-06-17

Uncertainty Quantification for Flow-Based Vision-Language-Action Models

arXiv:2606.18043v1 Announce Type: cross Abstract: Vision-language-action models (VLAs) combine vision-language backbones with expressive generative action heads trained via flow matching on large-scale robotic datasets. Despite their strong empirical performance in robotic manipulation, VLAs lack mechanisms to quantify confidence in their predictions and to detect when their actions may be unreliable. This presents a critical limitation for real-world deployment in non-stationary environments, where models inevitably encounter scenarios outside their pretraining distribution and may fail without warning. To address this, we derive an efficient method for quantifying epistemic uncertainty in flow-matching models by leveraging velocity-field disagreement (VFD) across a small ensemble. We successfully use this uncertainty estimate for failure detection during deployment and active fine-tuning of flow-based VLAs. To this end, we propose SAVE, a framework for uncertainty-guided active multitask fine-tuning that reduces the number of costly expert demonstrations required to adapt VLAs to new tasks. Through extensive experiments on the LIBERO benchmark, we demonstrate that VFD yields better-calibrated uncertainty estimates predictive of downstream performance, that VFD achieves strong performance in detecting failures, and that uncertainty-guided data acquisition with SAVE requires at least 22% fewer samples than baselines. In summary, our work shows that quantifying epistemic uncertainty in flow-based VLAs improves both failure awareness and adaptation. Project website: tum-lsy.github.io/uq_vla/.

05.
arXiv (quant-ph) 2026-06-16

MAPS: A Novel Multi-Axial Projective Sphere for Geometrically Visualizing Higher d-Valued Quantum State-Space of Qudits

Authors:

arXiv:2606.15801v1 Announce Type: new Abstract: Visualizing the d-valued quantum state-space of quantum systems serves as a foundational pillar for the scientific research and practical applications in quantum computing and information science, where d >= 2. The 2-valued quantum states of a qubit are elegantly visualized on the three-dimensional Bloch sphere. In contrast, expanding this geometrical paradigm to visualize higher d-valued quantum states of a qudit (d >= 3), e.g., a qutrit (d=3), ququadit (d=4), and quintit (d=5), leads to severe structural and topological complexities. This paper introduces a new generalized three-dimensional framework to effectively visualize higher d-valued quantum states of a qudit, in the aspects of ease of illustration, structural simplicity, and natural representation for researchers and engineers. We called this new framework the "multi-axial projective sphere (MAPS)", which consists of n projectional intersecting spatial axes, where d-1

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

Geometry-Aware Post-Hoc Uncertainty Quantification in Operator Learning

arXiv:2606.17513v1 Announce Type: cross Abstract: Neural operators provide fast surrogates for PDEs but their deterministic predictions limit their use in tasks requiring uncertainty quantification (UQ), especially under geometric variability. Existing approaches primarily model uncertainty in network parameters, largely overlooking the geometry-aware representations learned by the operator itself. We propose REEF-GP (Residual on Embedded Features Gaussian Process), a post-hoc UQ framework that fits a GP to the residuals of a frozen neural operator whose internal embeddings define the kernel feature space. Rather than learning a separate feature map, REEF-GP adapts the operator's intrinsic coordinate-feature representations to construct geometry-aware uncertainties. To ensure stability and scalability on unstructured domains, REEF-GP incorporates spectral-normalized projections, heteroscedastic geometry-aware noise, and efficient subset-based training that avoids restrictive low-rank approximations. Across five PDE benchmarks with varying geometries, REEF-GP preserves predictive accuracy while achieving calibrated uncertainty estimates competitive with deep ensembles but at a fraction of their cost. Our approach remains robust under geometric distribution shift, with uncertainty concentrating in physically meaningful regions (e.g., shock fronts). Our results demonstrate that accurate and scalable post-hoc UQ for neural operators can be achieved directly in their learned feature space, offering a practical alternative to parameter-centric approaches.

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

PERRY: Policy Evaluation with Confidence Intervals using Auxiliary Data

arXiv:2507.20068v2 Announce Type: replace Abstract: Off-policy evaluation (OPE) methods estimate the value of a new reinforcement learning (RL) policy prior to deployment. Recent advances have shown that leveraging auxiliary datasets, such as those synthesized by generative models, can improve the accuracy of OPE methods. Unfortunately, such auxiliary datasets may also be biased, and existing methods for using data augmentation within OPE lack principled uncertainty quantification. In high stakes domains like healthcare, reliable uncertainty estimates are important for ensuring safe and informed deployment of RL policies. In this work, we propose two methods to construct valid confidence intervals for OPE with data augmentation. The first provides a confidence interval over $V^{\pi}(s)$, the policy value conditioned on an initial state $s$. To do so we introduce a new conformal prediction method suitable for Markov Decision Processes (MDPs) with continuous state spaces, extending prior work to higher-dimensional settings. Second, we consider the more common task of estimating the average policy performance over all initial states, $V^{\pi}$; we introduce a method that draws on ideas from doubly robust estimation and prediction powered inference. Across simulators spanning inventory management, robotics, healthcare, and a real healthcare dataset from MIMIC-IV, we find that our methods can effectively leverage auxiliary data and consistently produce confidence intervals that cover the ground truth policy values, unlike previously proposed methods. Our work enables a future in which OPE can provide rigorous uncertainty estimates for high-stakes domains.

08.
bioRxiv (Bioinfo) 2026-06-14

Prediction of parsimonious and temporally sensitive sets of cell fate engineering transcription factors with IMCell

Transcription factor (TF) cocktails used in cell identity reprogramming protocols have largely been developed from experimental approaches. A handful of computational approaches have been reported, though have not been widely adopted by the scientific community. To standardize their use and assess their performance, we built CompForce, a platform that integrates these tools. Using CompForce, we found that existing computational methods offer modest improvements over differential expression on both synthetic and literature-curated data, and that their lackluster and inconsistent performance could be attributed to a reliance on local centrality metrics. To improve upon these methods, we developed IMCell, a prediction method that is inspired by the influence maximization problem. Unlike existing tools, IMCell returns optimized TF sets rather than ranked TF lists. We demonstrate that IMCell vastly out-performs existing tools, and further extend it to dynamic, stepwise contexts. The tools presented here are available in the R packages CompForce and IMCell.

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

Early Diagnosis of Wasted Computation in Multi-Agent LLM Systems via Failure-Aware Observability

arXiv:2606.01365v2 Announce Type: replace Abstract: Failure-aware observability diagnoses wasted computation in multi-agent LLM systems before final-answer evaluation can explain what went wrong. We propose a trace-based framework for a three-agent architecture – orchestrator, search agent, and execution agent – that converts structured events into online signals for loops, budget pressure, low information gain, and tool instability, then adds offline semantic grounding metrics and selective LLM-as-judge evaluation. On 165 GAIA validation traces under identical caps, 98 runs produce usable final answers and 67 fail or stop without one. Among warned failed runs, 58.1% of tokens are spent after the first warning on average, indicating substantial opportunity for intervention. A 10-task Level-2 pilot uses warnings to diversify search or require evidence, reducing post-warning token fraction from 0.638 in the baseline to 0.304. The results support a layered design: cheap online signals help the orchestrator redirect or halt redundant behavior, while deeper semantic checks identify whether completed answers are grounded enough to trust.

10.
arXiv (quant-ph) 2026-06-16

Watching a Superconducting Coplanar Waveguide Heat Up with a Single Color Center

arXiv:2606.15398v1 Announce Type: new Abstract: Single color centers in diamond offer a local probe of their cryogenic environment, providing a direct way to quantify heating in spin-control hardware. Here, we establish a single spectrally stable tin-vacancy (SnV) center as an on-chip thermometer for a diamond membrane and use it to characterize microwave- and radio-frequency-induced heating in a superconducting coplanar waveguide patterned on the same chip. We first calibrate the temperature dependence of the optical C-transition frequency and linewidth from $20\,\mathrm{K}$ down to the few-kelvin regime. At lower temperatures, where the optical response becomes weakly temperature dependent, we use the spin-lattice relaxation time $T_1$ as a complementary thermometer and tune its sensitivity with the transverse magnetic-field component. Applying this local thermometer to a niobium coplanar waveguide, we observe magnetic-field-dependent superconducting breakdown under GHz drive, accompanied by abrupt heating of the diamond. In contrast, at $20\,\mathrm{MHz}$ and $400\,\mathrm{mT}$, relevant for nuclear-spin control, we detect no measurable heating up to the breakdown threshold of $9.4\,\mathrm{dBm}$, corresponding to $B_\mathrm{ac}\sim1.2\,\mathrm{mT}$. These results define a safe operating window for superconducting microwave and RF control structures in diamond-based quantum nodes.

11.
medRxiv (Medicine) 2026-06-12

The Acceptability of Three Co-Created Peer Support Interventions for People Living with Leprosy Reactions in Indonesia: A Mixed-Methods Pilot Study

Background: Leprosy reactions (LR) are immune-mediated complications associated with disability, emotional distress, and social isolation. We identified a gap in affected-individual-informed interventions that aim to improve the management of LR in healthcare settings. To address this gap, we assessed the acceptability of three peer-support interventions co-created with people affected by LR in Indonesia. Methods: Using an interactive learning and action approach, we co-created peer counselling, telesupport groups, and participatory video interventions which were piloted in an urban hospital and 13 rural community clinics. A mixed-methods design was applied with interviews, focus group discussions, and pre-post assessments involving four participant groups. Data were analyzed thematically using an acceptability framework. Results: One hundred participants were enrolled, and 92 completed the pilot intervention between November 2022 and July 2023. Qualitative findings showed that all interventions were acceptable. Peer counselling provided emotional reassurance through shared experiences and was perceived as trustworthy and supportive. Perceived burdens differed by setting, with time constraints in urban facilities and geographical barriers in rural clinics. Knowledge improved significantly among participants of peer counselling and telesupport groups in rural settings. Telesupport groups facilitated connection, information exchange, and continuity of care. Digital access and literacy limited participation for some, particularly in rural areas. The participatory video was perceived as reassuring and informative. Improvements in knowledge, attitude, practices, and mental well-being domain scores were observed among urban participants, but responses in rural settings showed less change. Participants and co-implementers reported increased self-efficacy, participants confidence to perform required behaviors within peer support interventions, with effects shaped by intervention and setting. Conclusions: The three co-created peer-support interventions were acceptable for individuals with LR in diverse healthcare settings. These outcomes highlight the importance and effectiveness of selective, and context-sensitive implementation of one or more peer-support modalities.

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

A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle

The emergence of writable, cross-session persistent memory in LLM agents introduces a qualitatively different threat landscape from conventional input-centric security concerns, characterized by three properties: persistence, statefulness, and propagation. To systematically characterize this landscape, we propose a Memory Lifecycle Framework that organizes attacks, defenses, and their cross-phase dependencies along two axes: six lifecycle phases (Write, Store, Retrieve, Execute, Share & Propagate, Forget & Rollback) and four security objectives (Integrity, Confidentiality, Availability, Governance). This analysis in turn exposes the need for formal security guarantees at the system level, motivating Verifiable Memory Governance(VMG), a framework of five architectural primitives that specifies what verifiable mechanisms a long-term-memory system must provide to maintain auditable, recoverable control over its memory state. Our analysis indicates that robust Long-Term Memory (LTM) security cannot be retrofitted at retrieval or execution time alone, but must be anchored in storage-time provenance, versioning, and policy-aware retention from the outset.

14.
arXiv (CS.AI) 2026-06-11

Physics-Distilled Neural Network enabled by Large Language Models for Manufacturing Process-Property Predictive Modeling

arXiv:2606.11605v1 Announce Type: cross Abstract: Predicting process-property relationships in manufacturing is often challenged by high experimental costs and the limited interpretability of complex 'black-box' models. This paper proposes a novel knowledge distillation framework designed to achieve high-accuracy predictions in data-scarce scenarios. The framework integrates analytical physics priors, which are systematically extracted from scientific literature via Large Language Models, into a privileged teacher model. We employ a Graph-Masked Attention layer to capture the complex physical dependencies among input variables showing strict setpoints or a combination of static and high-frequency temporal signatures. This privileged knowledge is distilled into a lightweight student predictor for inference. The feasibility and robustness of the framework are evaluated through a comprehensive experiment across five diverse manufacturing processes. To ensure statistical reliability, given the small dataset sizes, a repeated K-fold cross-validation technique is employed to quantify model stability and generalization. Results indicate that the proposed framework consistently achieves high predictive accuracy across all evaluated domains. Most importantly, the architecture demonstrates significant fault tolerance by maintaining robust predictive performance even in scenarios where LLM-derived analytical priors are suboptimal or incomplete. Furthermore, the student predictor achieves an inference frequency exceeding 6000 Hz, which facilitates real-time edge deployment on standard industrial hardware. This work provides a scalable solution for bridging the gap between theoretical physics and real-time industrial monitoring in data-limited environments.

15.
medRxiv (Medicine) 2026-06-16

Optimal Clinical Trials Platform for Progressive Multiple Sclerosis (OCTOPUS): protocol for an international, multi-arm, multi-stage, platform, randomized controlled, double-blind, phase 3 clinical trial.

Introduction Current treatments for multiple sclerosis (MS) do not address the pathological processes of neurodegeneration and chronic demyelination. This, coupled with the significant challenges of translating promising phase 2 results to phase 3 trial success, highlights the need for more efficient trial designs, such as platform multi-arm multi-stage (MAMS) trial approaches. MAMS trials have demonstrated success in areas such as oncology and infectious diseases. They are typified by a statistically robust core trial design that allows the addition of further treatment arms and utilisation of interim outcome analyses at pre-defined timepoints, to determine whether to terminate a treatment arm early or proceed to the final outcome analysis. To address the challenges in progressive multiple sclerosis (PMS) treatment discovery, the Optimal Clinical Trials Platform for PMS (OCTOPUS) trial was developed. It currently utilises MRI whole-brain atrophy as its interim outcome measure and the clinically relevant composite Expanded Disability Status Scale Plus (EDSS-Plus) as its final outcome measure. A rigorous and systematic drug selection process that assessed preclinical in vitro and animal model evidence, along with additional human data, led to the prioritisation of R/S-alpha lipoic acid (R/S-ALA) and metformin for testing against placebo, targeting pathobiological mechanisms relevant to PMS. All participants will be eligible to receive the current standard of care, including disease-modifying treatments (DMTs). Method and analysis OCTOPUS will be a multi-centre, randomised, placebo-controlled, double-blind, phase 3, MAMS trial of participants aged 25 to 70 years (inclusive) with PMS and an EDSS score of 4.0 to 8.0 (inclusive). Steady progression must be the major cause of increasing disability rather than relapse in the preceding 2 years. In the trial s first candidate drug cycle, participants will be allocated to R/S-ALA, metformin, or placebo in a 1:1:1 ratio. Cycle 1 active treatments will start as R/S-ALA 600 mg once daily, increased after 4 weeks to 600 mg twice daily, or metformin 1 g once daily, increased after 4 weeks to 1 g twice daily. The trial will be multinational, with participation from 28 hospitals across the UK and 10 hospitals in Australia. Clinician-reported measures will include: the EDSS-Plus and the individual components: EDSS, Timed 25 Foot Walk (T25FW); 9 Hole Peg Test (9HPT); Symbol Digit Modalities Test (SDMT); Sloan Low Contrast Visual Acuity (SLCVA); and Relapse assessment. Patient-reported outcomes include MS specific walking, fatigue, pain, and impact scales. We will include a health economic analysis. Analysis stage 1 will require randomisation of 125 participants per arm and utilise MRI percentage brain volume change (PBVC) with the Structural Image Evaluation using Normalisation of Atrophy (SIENA) technique from baseline to 78 weeks. A positive outcome in analysis stage 1 will detect a 0.15% per year whole brain atrophy difference with a one-sided alpha of 0.35 and power of 95%, ensuring a low probability of erroneously rejecting a treatment arm at this stage. Any arms that show a positive effect will proceed to final analysis stage 2. Analysis stage 2 will require 600 participants per arm. Participants included in stage 1 will also be included in the stage 2. Analysis stage 2 will evaluate time to 6-month confirmed disability progression in the EDSS-Plus, in order to detect a 25% hazard ratio reduction with 90% power and an alpha of 0.05. Assuming one treatment arm proceeds to analysis stage 2, the trial will recruit approximately 1,200 participants and last about 6 years. This is approximately two-thirds the size and half the duration of separately conducted two-arm phase 2 and 3 trials. Ethics and dissemination The protocol was approved by the London Hampstead REC (22/LO/0622). This manuscript is based on protocol version 8.0, 28th August 2025. The findings of this trial will be disseminated through peer-reviewed publications and conference presentations. There will be a close communication strategy developed with the UK MS Society (MSS) and full patient and public involvement and engagement (PPIE). Trial registration ISRCTN: 14048364 EudraCT number: 2021-003034-37 CTA 20363/0445 IRAS number: 1003943 Secondary identifying numbers: ND001, CPMS 54274 Strengths and limitations - The OCTOPUS trial will be the first platform multi-arm multi-stage phase 3 trial in PMS, offering the potential to significantly expedite clinical trial processes with advantages in cost- and time-efficiency, focusing specifically on the poorly treated pathobiological processes of chronic neurodegeneration and demyelination - It will begin by assessing two promising drug candidates, immediate-release metformin and R/S-ALA, and will expand over the duration of the trial to include more drug arms under the same trial master protocol - The flexible and statistically robust trial design means that several components of the design (such as the early analysis stage 1 interim outcome) can be updated in line with evolving scientific knowledge - It will ultimately be the largest ever investigator-initiated phase 3 trial in PMS - It will include a range of national and international trial sites, including neuroscience centres and district general hospitals - It will have a high inclusion limit for age (up to 70 years) and disability (up to EDSS 8.0) - Several components (the telephone EDSS and virtual patient-reported outcome measures) will be amenable to remote collection increasing inclusivity and thus addressing public and participant suggestions, while minimising the risk of missing data - The main challenges in this trial design are the statistical and methodological complexity involved in design and implementation, and interpretation of interim trial results. Conclusion The trial launched cycle 1 in January 2023. Analysis stage 1 recruitment of 375 participants was achieved in November 2024, enabling planned interim analysis stage 1 to be conducted by late 2026 (Figure 1). On the 1st of June 2026, in the UK, 24 sites are active with a further 4 in set-up as part of stage 2, and in the Australian extension, Platform Adaptive Trial for Remyelination and Neuroprotection in Multiple Sclerosis (PLATYPUS), 1 site is active, with 9 additional sites in set-up.

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

Modeling Sarcastic Speech: Semantic and Prosodic Cues in a Speech Synthesis Framework

Sarcasm is a pragmatic phenomenon in which speakers convey meanings that diverge from literal content, relying on an interaction between semantics and prosodic expression. However, how these cues jointly contribute to the recognition of sarcasm remains poorly understood. We propose a computational framework that models sarcasm as the integration of semantic interpretation and prosodic realization. Semantic cues are derived from an LLaMA 3 model fine-tuned to capture discourse-level markers of sarcastic intent, while prosodic cues are extracted through semantically aligned utterances drawn from a database of sarcastic speech, providing prosodic exemplars of sarcastic delivery. Using a speech synthesis testbed, perceptual evaluations show that semantic and prosodic cues enhance perceived sarcasm, with the combined system achieving the best downstream F1 while maintaining high subjective sarcasm ratings. These findings highlight the complementary roles of semantics and prosody in pragmatic interpretation and illustrate how modeling can shed light on the mechanisms underlying sarcastic communication.

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

Runtime Analysis of Cartesian Genetic Programming in Evolving Boolean Functions

arXiv:2606.15923v1 Announce Type: cross Abstract: Cartesian Genetic Programming (CGP) is among the practical and popular forms of Genetic Programming as it uses a graph-based representation of programs. This paper presents a first runtime analysis of CGP in evolving Boolean functions using complete training sets. We prove an asymptotic bound $O(n D^5)$ for the expected number of fitness evaluations of CGP to construct a conjunction of $n$ inputs using at most $D \geq n-1$ binary gates, a minimal function set, and even with a strict survival selection. When the non-strict selection is used, the bound is improved to $O(n D^4)$. Our analysis reveals interesting characteristics of CGP induced search, which have been only observed empirically. In particular, enabling the acceptance of equally good solutions, including those with connected gates non-contributing to fitness, can lead to a speedup, and consequently a better asymptotic time bound. In contrast to conjunctions, we also prove a negative result which shows that CGP requires exponential time to evolve an exclusive disjunction. Experiments evolving conjunctions complement our theoretical findings. The use of incomplete training sets is found to further reduce the average number of fitness evaluations while maintaining a good level of generalisation.

18.
arXiv (CS.LG) 2026-06-19

AgentArmor: A Framework, Evaluation, \& Mitigation of Coding Agent Failures

arXiv:2606.19380v1 Announce Type: cross Abstract: Software engineering and deployment are increasingly being delegated to AI coding agents. The scale of their adoption is surfacing rare, but highly destructive, failure modes. In this paper, we study these failure modes as stemming from three distinct mechanisms: underspecification, where default model behavior is unsafe; capability errors, where the safe action is available but the model does not adhere to it due to bias or capability limitations; and agent harness errors, where the model fails to execute the safe action through the harness. We evaluate these across 8 different evaluations, each inspired by real-life deployment failures, totaling 20 coding environments and 59 synthetic transcript templates. Based on this evaluation, we propose AgentArmor, an agent harness modification, to mitigate these errors. By adding an extended system prompt, a separate command classifier, a ``3 strikes'' policy, deterministic guardrails, and tools for the agent to edit its own context, we show that AgentArmor is safer across a statistically significant number of samples. Thus, we suggest concrete mitigations for current coding agents and a design philosophy for future agent harness features.

19.
arXiv (math.PR) 2026-06-19

On creating convexity in high dimensions

arXiv:2502.10382v3 Announce Type: replace-cross Abstract: Given a subset $A$ of $\mathbb{R}^n$, we define \begin{align*} \mathrm{conv}_k(A) := \left\{ \lambda_1 s_1 + \cdots + \lambda_k s_k : \lambda_i \in [0,1], \sum_{i=1}^k \lambda_i = 1 , s_i \in A \right\} \end{align*} to be the set of vectors in $\mathbb{R}^n$ that can be written as a $k$-fold convex combination of vectors in $A$. Let $\gamma_n$ denote the standard Gaussian measure on $\mathbb{R}^n$. We show that for every $\varepsilon > 0$, there exists a subset $A$ of $\mathbb{R}^n$ with Gaussian measure $\gamma_n(A) \geq 1- \varepsilon$ such that for all $k = O_\varepsilon(\sqrt{\log \log(n)})$, $\mathrm{conv}_k(A)$ contains no convex set $K$ of Gaussian measure $\gamma_n(K) \geq \varepsilon$. This result acts as a complement to the recent affirmative resolution of Talagrand's convexity conjecture by Hua, Song, and Tudose, which states that a universal dilation of the threefold Minkowski sum $A+A+A$ of a large set $A$ guarantees a large convex subset. Our approach utilises concentration properties of random copulas and the application of optimal transport techniques to the empirical coordinate measures of vectors in high dimensions.

20.
arXiv (CS.CL) 2026-06-11

uva-irlab-conv at SemEval-2026 Task 8: Multi-Turn RAG with Learned Sparse Retrieval and Listwise Reranking

This report describes our participation in SemEval-2026 Task 8 on multi-turn retrieval and question answering. The task evaluates conversational systems across four domains (finance, cloud documentation, government, Wikipedia), and includes unanswerable queries where the available collection does not contain sufficient evidence to produce a complete response. We propose a multi-turn retrieval-augmented generation pipeline that combines learned sparse retrieval with LLM-based reranking and generation. Using sparse retrieval as the primary retrieval method, we leverage its strong generalization across domains. In addition, we make use of the long-context capabilities of LLMs for conversational query rewriting, pointwise and listwise reranking, and generating the final response, each conditioned on the full conversational history. This multi-step design enables effective integration of conversational context throughout retrieval and generation, improving robustness across domains.

21.
arXiv (CS.AI) 2026-06-19

FlowFake: Liquid Networks for Audio Deepfake Detection

arXiv:2606.19579v1 Announce Type: cross Abstract: Audio deepfakes generated by neural text-to-speech and voice-cloning systems threaten speaker verification and public discourse at scale. The core challenge is cross-dataset generalization: detectors trained on one synthesis pipeline collapse on unseen forgeries. We argue that this failure is primarily because of structural synthetic speech artifacts which are multi-timescale trajectory anomalies. Though every existing detector aggregates a fixed-window frame statistics, this misaligns the architecture with the signal. We propose FlowFake, a Liquid Time-Constant (LTC) architecture whose hidden state evolves via a learned ODE, with per-neuron adaptive time constants simultaneously resolving spectral (10ms) and prosodic (2s) cues. At only 34K parameters FlowFake achieves formal BIBO stability and O(dt^4) integration error. On a four-dataset cross domain benchmark (ASVspoof2019-LA, FakeOrReal, InTheWild, MLAAD), FlowFake reaches 75.29% on ASVspoof2019 trained only on FakeOrReal and 79.97% trained only on MLAAD. It outperforms RawGAT-ST and Whisper-DF on every evaluated pair and matching SSL Wav2vec2 (300x larger) at 0.01% of its parameter count. The source code is available on : https://github.com/GhostRider2023/FlowFake

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

EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning

arXiv:2606.03108v2 Announce Type: replace Abstract: Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static. This limitation sharpens in agentic RL, where shifting bottlenecks and scalar rewards mask diverse failure modes. We introduce EvoTrainer, an autonomous training framework that co-evolves LLM policies and training-side harnesses through empirical feedback: it diagnoses rollout-level evidence, revises diagnostics, backtests interventions, and accumulates reusable skills. Evaluated on mathematical reasoning, competitive-programming code generation, and repository-level software engineering, EvoTrainer matches or exceeds the human-engineered RL references under the same data, codebase, and evaluation protocol, with the largest gain on long-horizon agentic SWE. Trajectory analyses show that retained strategies diverge across domains, evolving diagnostics prevent invalid high-scoring branches from being promoted, and reusable skills shape later search. Autonomous LLM RL should move beyond recipe search toward joint evolution of policies and the training harnesses that interpret them.

23.
arXiv (CS.AI) 2026-06-11

Automating Geometry-Intensive Compliance Checking in BIM: Graph-Based Semantic Reasoning Framework

arXiv:2606.12065v1 Announce Type: new Abstract: Automating compliance check for geometry-intensive regulations remains a significant technical bottleneck in Building Information Modeling (BIM), primarily due to the semantic disparity between high-level regulatory logic and structured IFC data. Existing methods, often reliant on static rule templates, struggle to traverse multi-hop reasoning chains or resolve latent spatial dependencies across multiple building entities. To address these challenges, a Spatial-Geometric Reasoning System for Building Information Modeling (SGR-BIM) is proposed as an integrative graph-driven reasoning framework. SGR-BIM dynamically constructs a cross-modal knowledge graph that aligns user intent, regulatory semantics, and BIM geometry, enabling interpretable reasoning without rigid hard-coding. Validated on 679 expert-verified queries from fire safety codes, the framework achieves 84.3% accuracy, representing an 8.6% improvement over enhanced-tool single-agent baselines. This research provides a graph-based semantic reasoning paradigm, enhancing the transparency and flexibility of automated geometric compliance check workflows in the Architecture, Engineering, and Construction (AEC) industry.

24.
arXiv (CS.LG) 2026-06-12

From Uncertain Judgments to Calibrated Rankings: Conformal Elo Estimation for LLM Evaluation

arXiv:2606.13221v1 Announce Type: new Abstract: Evaluating new large language models typically requires costly human annotation campaigns at scale. LLM-as-a-judge offers a cheaper alternative, but judge scores carry systematic errors - such as position bias, self-preference, or intransitivity - that can strongly miscalibrate the resulting rankings. We quantify the resulting judge-human disagreement at two complementary levels. At the local level, we estimate per-battle uncertainty from the judge's own score differences by propagating calibrated win probabilities rather than hard labels into the Bradley-Terry procedure. This alone provides a drastic improvement to Elo estimation accuracy, bringing LLM-derived ratings within 17.9 Elo MAE of human-derived ones when averaged over 55 held-out models on LMArena. At the global level, we apply split conformal prediction to the residual gap between LLM-derived and human-derived Elo ratings across held-out models, producing prediction intervals with distribution-free marginal coverage guarantees that account for irreducible LLM-human disagreement. Together, these two layers yield a low-cost evaluation tool that provides developers with calibrated Elo estimates and honest uncertainty bounds, without access to large-scale human annotations.To facilitate reproducibility, we release our code at https://github.com/kargibora/SoftElo .

25.
arXiv (CS.AI) 2026-06-16

LabOSBench: Benchmarking Computer Use Agents for Scientific Instrument Control

arXiv:2606.16802v1 Announce Type: new Abstract: Current computer-use benchmarks primarily focus on software operation tasks in virtualized systems, whereas scientific instrumentation scenarios require coordinated control over complex interfaces, and feedback-driven parameter adjustment. However, directly evaluating agents on physical high-precision instruments is impractical due to high cost, safety risks, limited accessibility, and difficulty in ensuring reproducible evaluation. This motivates the need for a simulated yet realistic testbed that preserves the operational challenges of scientific instruments while enabling scalable and safe benchmarking. To this end, we introduce LabOSBench, a challenging benchmark for multimodal GUI agents built on a suite of web-based scientific-instrument simulators. Operating directly via a browser, LabOSBench avoids resource-heavy OS virtualization while supporting flexible task configuration and execution-based evaluation. Specifically, LabOSBench constructs 96 subtasks across eight instrument simulators, covering workflows from sample loading, alignment, parameter tuning, and data acquisition to result inspection. We evaluate general-purpose vision-language models, specialized GUI agent models, and advanced agentic frameworks at both subtask and end-to-end levels. Our experiments reveal that while existing agents can complete many structured GUI subtasks, they still struggle with feedback-driven operations and long-horizon workflow execution. Overall, LabOSBench provides a reproducible, low-cost testbed for advancing computer-using agents toward scientific-instrument control.