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 (math.PR) 2026-06-17

Optimal Impulse Control for Cyber Risk Management

arXiv:2410.17706v2 Announce Type: replace-cross Abstract: We explore an optimal impulse control problem wherein an electronic device owner strategically calibrates protection levels against cyber attacks. Utilizing epidemiological compartment models, we qualitatively characterize the dynamics of cyber attacks within the network. We determine the optimal protective measures against effective hacking by formulating and solving a stochastic control problem with optimal switching. We demonstrate that the value function for the cluster owner constitutes a viscosity solution to a system of coupled variational inequalities associated with a fully coupled reflected backward stochastic differential equation (BSDE). Furthermore, we devise a comprehensive algorithm alongside a verification procedure to ascertain the optimal timing for network protection across various cyber attack scenarios. Our findings are illustrated through numerical approximations employing deep Galerkin methods for partial differential equations (PDEs). We visualize the optimal protection strategies in the context of two distinct attack scenarios: (1) a constant cyber attack, (2) an exogenous cyber attack strategy modeled with a Poisson process.

02.
arXiv (quant-ph) 2026-06-24

Low Spatial Cost CCZ Magic State Factory

arXiv:2606.24170v1 Announce Type: new Abstract: We propose a design framework for reconstructing gate-based magic state distillation protocols as compact joint-measurement architectures implementable with the surface code. The goal is to reduce the surface-code resource cost of a magic state factory while preserving the logical function and error-detection structure of the distillation protocol. We construct a reduced architecture for implementing an eight-to-three CCZ distillation protocol using smaller surface-code patches. The proposed factory preserves the single-fault-detection property and the leading-order error suppression of the protocol, while producing CCZ magic states with lower spatial cost than the design of Gidney and Fowler. The proposed design perspective can also be applied to T-state factories and other multiqubit non-Clifford resource-state factories. Our approach provides a framework for extending the design space of surface-code magic state factories beyond a single CCZ layout optimization.

03.
arXiv (quant-ph) 2026-06-25

Quantum-inspired Topographic Stereovision

arXiv:2606.02197v2 Announce Type: replace Abstract: We revisit the conventional triangulation in distant stereovision, when shape rather than distance is the relevant observable. We show through the information-regret analysis that the optimal measurements for absolute distance and relative topography are unexpectedly different and incompatible, exposing an observable-measurement mismatch. To resolve this, we introduce stereo regularization to address stereo anisotropies that violate prevailing emitter-number conservation. Accordingly, we propose a topographic interferometer, which exploits cross-detector correlations to probe topography without measuring the distance profile. Our Fizeau-imaging interferometer turns parallax paths into Mach-Zehnder arms and employs a central path as the local oscillator for balanced homodyne detection, saturating the quantum Fisher information with improved topographic error scaling. This enables topographic stereovision of thermal sources beyond the Rayleigh limit, with feasible experimental demonstrations within existing techniques for remote sensing and astronomy.

04.
arXiv (CS.CV) 2026-06-15

Value-order Decomposition for Generalist Anomaly Detection

Industrial anomaly detection suffers from limited data, making cross-domain generalization particularly challenging. Generalist Anomaly Detection (GAD) aims to train a unified model on a source domain that can effectively detect anomalies in unseen target domains. In the initial semantic feature space, strong entanglement between anomalies and object categories or defect types hinders effective generalization across domains. Recent works address this issue by projecting features into a residual space; however, such methods primarily increase cross-domain overlap for normal features, while anomalous features remain specific to object categories, defect types and data domains, leading to poor alignment and generalization. To address this limitation, we propose Value-order Decomposition (VOD), a simple yet effective technique that bridges three types of generalization gaps across object categories, defect types (including real and synthetic defects), and data domains. VOD disentangles and suppresses object-category-, defect-type-, and domain-specific information, promoting alignment within normal and abnormal samples while preserving their separability, thereby enabling robust generalization across the three gaps. Leveraging the strong alignment between real and synthetic defects within the same object, we perform anomaly detection using only normal and synthetic-abnormal reference, and effectively generalize to unseen real defect types. Experiments on diverse industrial and medical benchmarks demonstrate that our method, using a simple cut-and-paste anomaly simulation strategy, achieves strong generalization across the three gaps.

05.
arXiv (CS.CL) 2026-06-15

Trusted Uncertainty in Large Language Models: A Unified Framework for Confidence Calibration and Risk-Controlled Refusal

Deployed language models must decide not only what to answer but also when not to answer. We present UniCR, a unified framework that turns heterogeneous uncertainty evidence including sequence likelihoods, self-consistency dispersion, retrieval compatibility, and tool or verifier feedback into a calibrated probability of correctness and then enforces a user-specified error budget via principled refusal. UniCR learns a lightweight calibration head with temperature scaling and proper scoring, supports API-only models through black-box features, and offers distribution-free guarantees using conformal risk control. For long-form generation, we align confidence with semantic fidelity by supervising on atomic factuality scores derived from retrieved evidence, reducing confident hallucinations while preserving coverage. Experiments on short-form QA, code generation with execution tests, and retrieval-augmented long-form QA show consistent improvements in calibration metrics, lower area under the risk-coverage curve, and higher coverage at fixed risk compared to entropy or logit thresholds, post-hoc calibrators, and end-to-end selective baselines. Analyses reveal that evidence contradiction, semantic dispersion, and tool inconsistency are the dominant drivers of abstention, yielding informative user-facing refusal messages. The result is a portable recipe of evidence fusion to calibrated probability to risk-controlled decision that improves trustworthiness without fine-tuning the base model and remains valid under distribution shift.

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

4DSloMo: 4D Reconstruction for High Speed Scene with Asynchronous Capture

Reconstructing fast-dynamic scenes from multi-view videos is crucial for high-speed motion analysis and realistic 4D reconstruction. However, the majority of 4D capture systems are limited to frame rates below 30 FPS (frames per second), and a direct 4D reconstruction of high-speed motion from low FPS input may lead to undesirable results. In this work, we propose a high-speed 4D capturing system only using low FPS cameras, through novel capturing and processing modules. On the capturing side, we propose an asynchronous capture scheme that increases the effective frame rate by staggering the start times of cameras. By grouping cameras and leveraging a base frame rate of 25 FPS, our method achieves an equivalent frame rate of 100-200 FPS without requiring specialized high-speed cameras. On processing side, we also propose a novel generative model to fix artifacts caused by 4D sparse-view reconstruction, as asynchrony reduces the number of viewpoints at each timestamp. Specifically, we propose to train a video-diffusion-based artifact-fix model for sparse 4D reconstruction, which refines missing details, maintains temporal consistency, and improves overall reconstruction quality. Experimental results demonstrate that our method significantly enhances high-speed 4D reconstruction compared to synchronous capture.

07.
arXiv (CS.LG) 2026-06-11

How Low Can You Go? Active Learning for Sparse Model Discovery in the Ultra-Low-Data Limit

arXiv:2606.12182v1 Announce Type: new Abstract: Identifying the governing equations of complex dynamical systems remains a fundamental challenge across science and engineering. While early approaches relied on empirical data and heuristics, modern data-driven methods offer greater flexibility and fewer assumptions. However, data acquisition in real-world settings is often expensive. This work addresses this challenge by introducing an active learning strategy for dynamics discovery in the ultra-low data limit. Rather than sampling randomly, our method iteratively prioritizes regions that are most informative for model identification. This approach builds on Sparse Identification of Nonlinear Dynamics (SINDy), and utilizes an ensemble extension, E-SINDy, to estimate epistemic uncertainty and guide the sampling for both ordinary and partial differential equations (ODEs/PDEs). For ODEs, an exhaustive analysis is conducted on the Lorenz system across varying data budgets and noise levels. For PDEs, two systems with contrasting dynamical characteristics are examined: the Burgers' equation, where a sharp shock front creates a distinction between informative and uninformative regions, and the Kuramoto-Sivashinsky equation, which presents a more spatially complex sampling landscape. Across all scenarios, the proposed method accurately identifies the governing dynamics with significantly fewer data samples than random sampling.

08.
arXiv (quant-ph) 2026-06-15

Quantum Simulation of Spin-Dependent Electron Transfer in a Synthetic Chiral Lattice with a Trapped Ion

arXiv:2606.13930v1 Announce Type: new Abstract: Electron transfer through chiral structures can exhibit spin asymmetry, known as the chiral-induced spin selectivity effect, whose microscopic origin remains an open question. While path-interference within the chiral moiety has been proposed as a key mechanism, its experimental validation requires precise and versatile tunability of system parameters. Here we implement a programmable quantum simulation of spin-dependent electron transfer in a donor–chiral-bridge–acceptor model using a trapped ion. The bridge is encoded in internal states of the ion with tunable nearest- and next-nearest-neighbor couplings, while donor and acceptor states are coupled via a spectator bosonic motional mode. We observe spin-dependent interference within the bridge, and further reveal spin-dependence in donor-to-acceptor transfer dynamics, controlled by amplitude and phase of the coupling parameter. Our results identify interference among spin-dependent pathways as a microscopic origin of spin-dependent transfer, and open a route toward quantum simulations of complex chiral lattices with multi-level and bosonic degrees of freedom.

09.
arXiv (CS.AI) 2026-06-18

SwitchBraidNet: Quantisation-Aware Lightweight Architecture for Hybrid Brain-Computer Interface

arXiv:2606.18816v1 Announce Type: cross Abstract: Hybrid brain-computer interfaces (BCIs) that integrate motor imagery (MI) and steady-state visual evoked potentials (SSVEP) provide high-dimensional neural decoding but typically exceed the computational limits of embedded hardware. To address this, we propose SwitchBraidNet, a compact EEG classification architecture designed for low-power deployment. The model employs a dual-path temporal braid to extract multiscale oscillatory features, an adaptive squeeze-and-excitation spatial switch for electrode gating, and a log-variance readout layer for direct band-power encoding. Furthermore, through systematic quantisation-aware training on the OpenBMI dataset, we compared SwitchBraidNet against four established baselines across FP32, FP16, and INT8 precisions. Experimental results demonstrate superior efficiency and performance, achieving MI accuracy of 69.49% (FP16), SSVEP accuracy of 93.48% (FP32), and a hybrid information transfer rate of 64.82 bits/min (FP16). With an INT8 footprint of only 3.03 KB, SwitchBraidNet maintains high accuracy across varying numerical precisions, demonstrating its suitability for low-power embedded BCI deployment.

10.
arXiv (CS.CV) 2026-06-25

A Leakage-Aware Comparative Benchmark of Machine Learning, Deep Learning, and Transformer Models for Reliable Leukemia Detection

Automated classification of acute lymphoblastic leukemia (ALL) from peripheral blood smear images has often reported near-perfect performance on the C-NMC 2019 dataset. We show that such results can be inflated by patient-level data leakage caused by random image-level partitioning, where cells from the same subject may appear in both training and test folds. We establish a leakage-aware benchmark under a strict subject-disjoint protocol, comparing LightGBM, RBF-SVM, EfficientNet-B0, EfficientNet-B1, and ViT-Tiny. Models are developed using three subject-disjoint folds from 73 subjects and evaluated on an external preliminary-phase test set of 1,867 images from 28 unseen subjects with zero patient overlap. Beyond discrimination, we assess calibration using expected calibration error, Brier score, and temperature scaling. Under honest evaluation, EfficientNet-B1 achieves the best performance, with AUROC 0.913, sensitivity 0.87, specificity 0.80, and calibrated ECE 0.024. Frozen-feature classifiers and ViT-Tiny show high sensitivity but poor specificity, indicating a tendency to over-predict the malignant class. A random-versus-subject-disjoint ablation shows that random splitting inflates AUROC by about 0.04 even in the conservative frozen-feature setting. These findings caution against image-level evaluation on C-NMC 2019 and provide a reproducible, calibration-aware benchmark for future work.

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

A prior-free blind detection of information leakage from model predictions

arXiv:2606.11267v1 Announce Type: new Abstract: Data leakage – contamination of a model with information unavailable at baseline – is the dominant reproducibility failure in machine-learning-based science, yet detection tools require training code, external data, or domain expertise. None operates on the artifact an auditor most often holds: the model's output. We ask what can be decided about leakage from predictions and outcomes alone. We give a decision-theoretic framework in which leakage diagnostics are functionals of the predicted-risk/outcome law, parameterized by a threshold-weighting linked to proper scoring rules and decision-curve analysis. We prove a sharp impossibility: a recalibrated leak matching an honest model's calibration and discrimination is indistinguishable from honest performance by any function of the predictions, so the broad class is detectable only against an externally supplied ceiling on achievable discrimination. We then prove what leakage cannot hide: a near-deterministic subgroup – the signature of a near-label leak – produces a sustained unit-purity head that no legitimate predictor of a non-deterministic outcome can manufacture, yielding a prior-free test. These results organize leakage into a trichotomy – miscalibrated, broad-calibrated, and deterministic – each with a matched detector and failure mode. We validate on UK Biobank using time-windowed comorbidity leakage with known, graded severity, measuring a detection floor of $\Delta\cstar \approx 0.007$ on this endpoint, below which residual leakage is undetectable from output and too small to alter conclusions. The numerical floor is cohort- and endpoint-specific; the structural lesson is general: output-only detection fails where residual leakage is indistinguishable from an honestly stronger predictor. The test returns a verdict on a prediction vector in under a second on commodity hardware.

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

Pepti-Agent: An AI Agent for Peptide Design and Optimization

Therapeutic peptides occupy a valuable design space between small molecules and biologics, but their development requires satisfying several competing constraints at once: solubility, hemolytic activity, and nonspecific surface fouling are governed by overlapping sequence features, so improving one property often degrades another. Computational design addresses this by pairing generative models with sequence-based property predictors, iteratively proposing and refining candidates. However, these components are typically wired together as monolithic scripts that are difficult to inspect, extend, or reuse, and they often refine sequences by natural-language reasoning rather than by tracking the evolving multi-property state of each candidate. We present Pepti-Agent, a closed-loop, peptide-specific framework that exposes generation, property prediction, and single-residue mutation as independently inspectable Model Context Protocol (MCP) tools. A large language model controller invokes these tools and consults live predictor output between calls, so refinement is guided by each sequence's current property profile rather than by language reasoning alone. Task-specific PeptideGPT models generate candidates, ProtBERT-based classifiers score solubility, hemolysis, and non-fouling, and two interchangeable mutation operators propose sequence edits. By recording a per-step trace of controller decisions, predictor outputs, and accepted mutations, Pepti-Agent offers a reproducible substrate for benchmarking multi-objective design strategies and for prioritizing candidates for experimental validation.

13.
Nature Medicine 2026-06-24

Automated reanalysis of genomic data for rare disease diagnostics at scale

Reanalysis of genomic data in rare disease is highly effective in increasing diagnostic yields but remains limited by manual approaches. Automation and optimization for high specificity will be necessary to ensure scalability, adoption and sustainability of iterative reanalysis. We developed Talos, an open-source tool that automates variant prioritization by integrating dynamically updated gene−disease and variant-level evidence with inheritance-aware filtering and validated its performance using data from 1,089 individuals with rare disease. Trio-based analysis identified 90% of known diagnoses, returning 1.3 variants per case on average. Variant burden reduced to one variant per 200 cases on iterative monthly reanalysis. Application to an unselected cohort of 4,735 undiagnosed individuals identified 241 diagnoses (5.1% yield): 78 (32%) due to new gene−disease relationships, 54 (22%) due to new variant-level evidence and 109 (45%) due to improved analysis strategies. Our automated, iterative reanalysis model demonstrates the feasibility of delivering frequent, systematic reanalysis at scale. Talos, a new tool for the automated analysis of genomic data, demonstrates the feasibility and diagnostic utility of systematic reanalyses of data in rare diseases.

14.
bioRxiv (Bioinfo) 2026-06-11

PhyloZoo: a unified framework for phylogenetic network analysis in Python

Authors:

Reticulate evolutionary processes (events in which lineages merge, such as hybridization, recombination, and horizontal gene transfer) are widespread across nature but cannot be represented by phylogenetic trees alone. Phylogenetic networks have therefore become an important modelling tool, yet existing software is typically tied to specific inference paradigms and provides limited support for working with multiple network representations in a unified and programmable environment. PhyloZoo is an open-source Python framework that lowers the barrier to developing practical, easy-to-use software for phylogenetic network analysis. It provides data structures and algorithms covering the main representations used in the field, together with dedicated visualization tools and robust I/O for all major phylogenetic file formats. A particular emphasis lies on semi-directed phylogenetic networks, which explicitly represent root uncertainty and have so far received limited support in existing software. By offering a shared foundation for developing interoperable tools and a combinatorial layer that supports computational proofs and theoretical exploration, PhyloZoo enables reproducible workflows for applied, methodological, and theoretical studies of reticulate evolution. Availability and implementation: PhyloZoo is implemented in Python and installable from PyPI, with source code, documentation, and examples available at https://github.com/nholtgrefe/phylozoo.

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

Detecting Sensitive Personal Information in Japanese Pre-Training Corpora for Large Language Models

Sensitive personal information can appear in large-scale pre-training corpora for large language models (LLMs). Detecting and filtering such information is therefore essential to ensure compliance with privacy regulations and prevent unintended information leakage. However, in contrast to English and other languages, research into sensitive personal information has been limited in the Japanese language. In this study, we focus on sensitive personal data defined as special care-required personal information (SCPI) under Japan's Act on the Protection of Personal Information (APPI). We construct an SCPI dataset using LLM-based annotation and train machine learning models to rapidly detect SCPI in text. As a result, our SCPI classifier can effectively identify information related to SCPI. This study is the first to explore SCPI detection in Japanese text corpora, highlighting the challenges of accurate detection.

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

TokenPilot: Cache-Efficient Context Management for LLM Agents

As LLM agents are deployed in long-horizon sessions, context accumulation drives up inference costs. Existing approaches utilize text pruning or dynamic memory eviction to minimize token footprints; however, their unconstrained sequence mutations alter layouts, introducing prefix mismatches and cache invalidation. This reveals a critical trade-off between text sparsity and prompt cache continuity. To address this, we present TokenPilot, a dual-granularity context management framework. Globally, Ingestion-Aware Compaction acts as a framework harness to stabilize prompt prefixes and eliminate open-world environmental noise at the ingestion gate. Locally, Lifecycle-Aware Eviction monitors the ongoing residual utility of context segments, enforcing a conservative batch-turn schedule to offload content segments only when task relevance expires. Experiments on PinchBench and Claw-Eval under both isolated and continuous modes demonstrate that TokenPilot reduces costs by 61% and 56% in isolated mode, and 61% and 87% in continuous mode, while maintaining competitive performance compared to prior systems. TokenPilot has been integrated into LightMem2 at https://github.com/zjunlp/LightMem2.

17.
arXiv (math.PR) 2026-06-12

(Non)-hyperuniformity of perturbed lattices

arXiv:2405.19881v3 Announce Type: replace Abstract: We ask whether a stationary lattice in dimension $d$ whose points are shifted by identically distributed but possibly dependent perturbations remains hyperuniform. When $d = 1$ or $2$, we show that it is the case when the perturbations have a finite $d$-moment, and that this condition is sharp. When $d \geq 3$, we construct arbitrarily small perturbations such that the resulting point process is not hyperuniform. As a side remark of independent interest, we exhibit hyperuniform processes with arbitrarily slow decay of their number variance.

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

Can I Buy Your KV Cache?

Authors:

arXiv:2606.13361v1 Announce Type: new Abstract: Right now, across the world, AI agents are repeating the same absurd act: to read one document, they each recompute it from scratch. Every agent re-runs prefill, the most compute-intensive step a large model takes, over identical text, only to rebuild a key-value (KV) cache identical to the one the agent before it just built. The same answer, computed a million times. We make a proposal that is almost offensively simple: compute it once. Let a publisher precompute a document's KV cache, and let every other agent buy the right to load it and skip prefill. It works, and it is token-exact: loading a precomputed KV and continuing matches prefilling from scratch (24/24 greedy tokens, and at the logits level), with no accuracy cost. On Qwen3-4B, reuse is 9-50x cheaper in compute than prefill, and the gap widens with length (prefill's attention scales with L^2), so a single reuse already pays it back. Then the part that matters: where the KV lives. Shipping it fails, because KV is nearly incompressible, so per-load egress costs more than the prefill it saves. Hosting it provider-side, exactly as production prompt-caching works, removes egress entirely. The size of the prize is set by our measured compute saving: serving one hot 3774-token document to 80M agents costs ~$1.5M to re-prefill but only ~$0.03M of reuse compute (49.7x less). The 0.1x cache-read tariff APIs charge passes a 10x discount to users while sitting inside this measured envelope, so the 10x is a floor that the measured ~50x compute saving clears, and the gap to the physical ~50x is provider margin: millions of dollars per popular document. We frame the resulting agent-native prefill CDN and leave lossless KV compression and a cross-party payment layer as the open problems.

19.
arXiv (CS.LG) 2026-06-25

Bridging Spherical Black-Box Optimizers

arXiv:2606.25761v1 Announce Type: new Abstract: When gradient information is unavailable, black-box optimization (BBO) methods provide a practical alternative. While Evolution Strategies (ES), Consensus-Based Optimization (CBO), Optimization via Integration (OVI), and related methods have each been studied independently, their connections remain underexplored. We unify these approaches within a common theoretical framework, revealing that they differ primarily in two design choices: fitness aggregation (controlling sharpness preference) and consensus scope (controlling modality). Leveraging these insights, we introduce hybrid optimizers that interpolate between existing methods. Our ES-OVI hybrid allows explicit control over the preference for flat minima, enabling a trade-off between performance and robustness in continuous control tasks. Our CBO-OVI hybrids combine the higher-dimensional efficiency of parametric methods with the multimodal capabilities of particle-based approaches, achieving competitive results on language model merging under limited evaluation budgets. We validate our methods on standard BBO benchmarks and higher-dimensional locomotion tasks, demonstrating that the hybrid methods can outperform their constituent algorithms.

20.
arXiv (CS.AI) 2026-06-19

LLM Doesn't Know What It Doesn't Know: Detecting Epistemic Blind Spots via Cross-Model Attribution Divergence on Clinical Tabular Data

arXiv:2606.19509v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly applied to structured clinical data, yet whether they can recognize the limits of their own knowledge on such tasks remains unexplored. We study this question through the lens of cross-model attribution divergence with the goal of reducing epistemic uncertainty for structured tasks, comparing Qwen 2.5 7B and XGBoost on a prediction task via attribution divergence analysis. We report four findings. First, LLM verbalized confidence is epistemically vacuous, it outputs a near-constant (0.856-0.937) regardless of whether accuracy is 49% or 75.3%, tracking prompt format rather than prediction quality. Second, the LLM exhibits an inverse difficulty effect: accuracy drops to 64.8% when XGBoost is 99% correct, but matches XGBoost (73.8% vs. 73.1%) when it is moderately uncertain. Third, few-shot examples and SHAP-derived feature evidence are orthogonal, super-additive interventions: they reduce the Attribution Disagreement Score (ADS) from 1.54 to 0.38 and improve accuracy from 49% to 75.3% without training. Fourth, a cross-model calibrator that determined LLM reliability using attribution divergence signals reduces expected calibration error from 0.254 to 0.080, replacing uninformative verbalized confidence with patient-specific reliability estimates, without accessing model internals or requiring repeated inference. We frame these findings as a cold start problem for LLMs on structured data and outline a path toward genuine epistemic self-awareness.

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

CoffeeBench: Benchmarking Long-Horizon LLM Agents in Heterogeneous Multi-Agent Economies

arXiv:2606.16613v1 Announce Type: new Abstract: As LLM agents become capable of increasingly long-horizon tasks, evaluating their performance in economic systems is becoming increasingly important. Unlike existing benchmarks that primarily evaluate a single agent interacting with a passive environment, economic systems are inherently multi-agent, requiring autonomous agents to communicate, negotiate, and transact while pursuing their own objectives over extended periods. We introduce CoffeeBench, a benchmark for evaluating LLM agents in a long-horizon multi-agent economy composed of heterogeneous firms. In CoffeeBench, two farmers, two roasters, and two retailers autonomously operate their businesses over a 90-day simulation, each seeking to maximize cumulative net income through communication and transactions while managing cash, inventory, and pricing. The evaluated model controls one coffee roaster, while the remaining firms are controlled by fixed reference agents. Across several recent open-weight and proprietary LLMs, all models outperform a passive baseline that takes no actions, with most achieving positive net income. Analysis of agent behavior reveals substantial differences in long-horizon economic interaction: higher-performing models communicate more actively with other firms, whereas Claude~Haiku~4.5 exhibits an idle-drift failure mode, repeatedly choosing inaction despite producing coherent assessments and plans. We release our code and agent trajectories to support future research.

22.
arXiv (CS.AI) 2026-06-11

Steering Where to Listen: Instruction-Based Activation Steering Redirects Temporal Attention in Large Audio-Language Models

arXiv:2606.11400v1 Announce Type: cross Abstract: Large Audio-Language Models (LALMs) excel at audio understanding but expose little about where in an audio signal they attend. We introduce instruction-based vector steering, which constructs a steering vector by contrasting activations from differently instructed prompts while keeping the audio fixed. Through a systematic probe of LALM attention, we find that - unlike standard prompting or audio-based steering - this intervention significantly redistributes the temporal attention allocated to audio tokens, concentrating it on acoustically relevant regions. We then show that this attention shift is behaviorally meaningful: in a controlled three-event setting, reading out the temporal position of maximal steering-induced attention change recovers the location of a queried sound event without any training, attaining 60.87% and 68.72% overlap with ground-truth intervals on Qwen2-Audio and Audio Flamingo 3, far above direct prompting (31.84%, 46.75%) and random baselines (27.74%). Our results characterize a mechanistic property of instruction-based steering in LALMs and provide a training-free probe for the latent temporal structure these models encode.

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

Schützen: Evaluating LLM Safety in Bulgarian and German Contexts

Large language models are increasingly deployed across professional domains, bringing hard-to-predict risks, including the generation of harmful or disrespectful content. Although substantial progress has been made in developing safety evaluation datasets, existing resources remain overwhelmingly English- and Chinese-centric. This limitation is particularly pronounced when evaluating languages that operate within shared sociocultural, legal, and ethical contexts. To address this gap, we introduce Sch\"{u}tzen: a German–Bulgarian safety dataset designed to assess model answerability under risk, covering both a low-resource language (Bulgarian) and a high-resource language (German). Experiments with multilingual and language-specific LLMs reveal pronounced cross-language differences in safety behavior, highlighting the necessity of tailored, region-specific evaluation resources to support the responsible deployment of LLMs in Germany and Bulgaria. Datasets and code are available at https://github.com/xnlp-lab/Schutzen. Warning: this paper contains examples that may be offensive, harmful, or biased.

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

Rethinking Scaffolding in LLM Tutors: The Interactional Mismatch Between Benchmarks and Real-World Deployments

arXiv:2606.15766v1 Announce Type: new Abstract: A central pedagogical value evaluated in AI tutor benchmarks is scaffolding: guiding students through graduated steps toward a solution. Alignment and evaluation methods for embedding scaffolding behaviour into chatbots, however, rest on an implicit assumption: that students will take up the scaffolding and engage in the conversation. To examine whether this assumption holds, we introduce an evaluation pipeline around two metrics - Chatbot Scaffolding and Student Uptake - and apply them across nine datasets of 9,490 chats, spanning AI tutor benchmarks and real-world deployments of educational chatbots. Our analysis reveals that while benchmarks assume a high-scaffolding, high-student-uptake environment, students in real-world settings exhibit lower levels of uptake overall - frequently bypassing the chatbot's pedagogical framing to drive the interaction toward their own learning goals at little interpersonal cost. We argue that bypassing scaffolding is not necessarily detrimental; rather, it frequently highlights a mismatch between a chatbot's pedagogical framing and the student's learning goals. To meaningfully evaluate the effectiveness of a chatbot's assistance, future benchmarks must move beyond the assumption that students will simply take up the scaffolding, and instead evaluate how these chatbots navigate diverse learning contexts and student-driven interaction patterns.

25.
arXiv (CS.CL) 2026-06-25

Sarashina2.2-TTS: Tackling Kanji Polyphony in Japanese Speech Generation via Data Scaling and Targeted Data Synthesis

While large language model (LLM)-based text-to-speech (TTS) systems have achieved high-quality speech synthesis, most existing systems focus on English and Chinese. Japanese, however, remains under-explored, and its unique linguistic challenges, such as widespread context-dependent kanji polyphony, have yet to be adequately tackled. Here we introduce Sarashina2.2-TTS (https://github.com/sbintuitions/sarashina2.2-tts), a Japanese-centric LLM-TTS system that tackles these challenges through a dual approach: data strategy and evaluation methodology. First, we scale training to approximately 361k hours of speech, incorporating a balanced mix of Japanese and English data. Furthermore, we design a targeted data augmentation pipeline covering all 2,136 Joyo (regular-use) kanji designated by Japan's Agency for Cultural Affairs to efficiently address kanji polyphony disambiguation. Second, we introduce the Joyo Kanji Yomi Benchmark (https://github.com/sbintuitions/JoyoKanji-Yomi-Benchmark), covering all 2,136 Joyo kanji and their 4,378 readings. Alongside this benchmark, we propose Kana-CER, a metric that compares synthesized speech against reference readings in the kana space, eliminating orthographic variations to directly measure pronunciation correctness. Experiments demonstrate that our targeted data augmentation significantly improves reading accuracy. Overall, Sarashina2.2-TTS achieves state-of-the-art kanji-level reading accuracy and matches top baselines on general sentence-level pronunciation, while delivering the highest speaker similarity in zero-shot Japanese speech synthesis. Furthermore, cross-lingual evaluation reveals that Sarashina2.2-TTS is the only system that maintains stable Japanese pronunciation regardless of the prompt language, confirming that our balanced training approach improves cross-lingual robustness.