AI technology must serve human cognitive development, not the other way around
Letter to the Editor
Academic Intelligence · Curated Daily
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.
Letter to the Editor
We introduce LibriConvo, a synthetic conversational speech corpus for speaker diarization and automatic speech recognition (ASR), built by instantiating the previously proposed Speaker-Aware Simulated Conversation (SASC) framework in a dataset and benchmarking setting. The main contribution of this paper is a corpus construction pipeline and benchmark derived from that framework. To make the data more suitable for downstream ASR and diarization, conversational timing statistics are estimated from English CallHome using external voice activity detection, long pauses are compressed, LibriTTS utterances are grouped by book to improve local semantic continuity, and room impulse responses are selected with a spatial-plausibility heuristic. The resulting corpus contains 240.1 hours of audio across 1,496 dialogues involving 830 speakers, partitioned into speaker-disjoint train, validation, and test splits. We report baseline results for both diarization and ASR. On the test split, Sortformer outperforms the pyannote pipeline in diarization (11.1\% vs.~24.4\% DER). For ASR, a Fast Conformer-CTC XLarge model fine-tuned with Serialized Output Training achieves 7.29\% WER and 6.97\% cpWER, outperforming zero-shot Whisper-large-v3. These results position LibriConvo as a practical benchmark for studying synthetic conversational speech and for evaluating multi-speaker speech processing systems.
arXiv:2606.19410v1 Announce Type: cross Abstract: Signed pairwise interaction scores fundamentally conflate uniqueness (U), redundancy (R), and synergy (S). We prove this on a minimal 3-way XOR structural causal model: faithful indices such as Shapley-Taylor return zero per pair, whereas projective indices such as Shapley Interaction spread the third-order effect into pair scalars that conflate the three mechanisms. We introduce Stochastic Hi-Fi, a post-hoc, retraining-free predictability decomposition that estimates per-feature U/R/S profiles by interventional masked inference. The estimator provides exact interventional semantics, finite-sample Monte Carlo bounds, strict variance reduction from coupled diamond sampling, and uniform finite-vocabulary convergence. Across tabular SCMs, Stochastic Hi-Fi recovers structure missed by scalar baselines (up to 411x larger interaction-magnitude recovery ratios). It also separates redundant and synergistic heads in the GPT-2 IOI circuit. On NIH ChestX-ray14, Stochastic Hi-Fi matches GradCAM on Pointing Game and improves substantially on Deletion AUC.
arXiv:2504.01579v3 Announce Type: replace Abstract: Quantum timeless approaches solve the problem of time by recovering the usual unitary evolution of quantum theory relative to a clock in a stationary quantum Universe. For some Hamiltonians of the Universe, such as those including an interaction term with the clock, the dynamics is substantially altered and can be non-unitary. This work derives necessary and sufficient conditions for the relative dynamics to be unitary and finds the general form of the unitary evolution operator. A physical interpretation of these conditions is given in terms of the clock's rate. Unitary dynamics is associated with rates that are constant in time and independent of the clock's internal structure.
Genome sequencing of the heterogeneous primary mitochondrial disorders (PMD) frequently reveals variants of uncertain significance that require functional tests for diagnosis, and does not identify variants in all patients. We analyzed mitochondrial enzyme assays, blue native polyacrylamide gel electrophoresis (BN-PAGE) with in-gel activity staining, complex I assembly blot, and select protein abundances in fibroblasts of a case series of 204 PMD patients divided into functional classes, in comparison to 51 controls and 53 differential diagnostic conditions. Overall, sensitivity and specificity for respiratory chain enzyme assays were 46% and 93% respectively, for BN-PAGE 40% and 98%, for complex I assembly assay 49% and 99%. The overall sensitivity of all tests was 76%, specificity 93%, with positive predictive value 96% and negative predictive value 67%. Categories with high sensitivity were isolated complex deficiencies, nuclear DNA-encoded mitochondrial protein synthesis defects, co-factor defects, and mitochondrial amino-acyl-tRNA synthetase conditions when aided by protein abundance. Mitochondrial DNA mutations and maintenance disorders showed poor sensitivities. Secondary dysfunctions were rare. A complete battery of functional tests showed strong diagnostic clinical utility in fibroblasts.
arXiv:2606.14318v1 Announce Type: cross Abstract: We derive an explicit formula for the sectional curvature of the space ${\cal M}(M)$ of finite measures on a Riemannian manifold M. The space ${\cal M}(M)$ is equipped with the Hellinger-Kantorovich metric $HK$. Even in the case M=R^n, the curvature is comprised of two parts: the `lifted part' is negative, and the `twisted part' is positive. It will be analyzed in detail for the multidimensional torus. Our general approach to sectional curvature in geodesic spaces also leads to new insights into the curvature of the space $P_2(M)$ of probability measures on M equipped with the Kantorovich-Wasserstein metric $W_2$.
arXiv:2606.10678v2 Announce Type: replace Abstract: Transformer-based models have emerged as leading paradigms in time-series forecasting in recent years, employing self-attention mechanisms to capture long-range dependencies. Despite their success, these single-stage forecasting architectures exhibit persistent systematic residual biases arising from structural discrepancies, unmodeled stochastic components, or inadequate multi-scale temporal representations. This limitation persists when residuals are treated as irreducible noise, precluding adaptive correction of structured error patterns. To address this limitation, we introduce a two-stage, model-agnostic framework that explicitly decouples forecasting and residual learning into distinct stages of representation learning. A base transformer first generates the initial predictions. Subsequently, a dedicated meta-corrector dynamically models structured error patterns across multivariate channels, preserves cross-variable dependencies, and iteratively refines the residual bias of the base transformer. By formalizing this pipeline as a hypothesis space expansion, our framework addresses approximation limitations inherent in single-stage architectures, removes reliance on restrictive assumptions, and enables end-to-end learning of complex error dynamics. Evaluated on eight popular benchmark datasets using established protocols, our approach achieves state-of-the-art performance, with significant improvements in standard metrics (MSE, MAE). The results demonstrate the framework's ability to mitigate systematic biases and enhance robustness to complex temporal dynamics, advancing the practical applicability of transformer-based forecasting models.
Real-world financial decision-making is a challenging problem that requires reasoning over heterogeneous signals, including company fundamentals derived from regulatory filings and trading signals computed from price dynamics. Recently, with advances in Large Language Models (LLMs), financial analysts have begun to use them for financial decision-making tasks. However, existing financial question-answering benchmarks for testing these models primarily focus on company balance sheet data and rarely evaluate reasoning about how company stocks trade in the market or their interactions with fundamentals. To leverage the strengths of both approaches, we introduce FinTradeBench, a benchmark for evaluating financial reasoning that integrates company fundamentals and trading signals. FinTradeBench contains 1,400 questions grounded in NASDAQ-100 companies over a ten-year historical window. The benchmark is organized into three reasoning categories: fundamentals-focused, trading-signal-focused, and hybrid questions requiring cross-signal reasoning. To ensure reliability at scale, we adopt a calibration-then-scaling framework that combines expert seed questions, multi-model response generation, intra-model self-filtering, numerical auditing, and human-LLM judge alignment. We evaluate 14 LLMs under zero-shot prompting and retrieval-augmented settings and witness a clear performance gap. Retrieval substantially improves reasoning over textual fundamentals, but provides limited benefit for trading-signal reasoning. These findings highlight fundamental challenges in the numerical and time-series reasoning for current LLMs and motivate future research in financial intelligence.
Vision-language-action (VLA) models can describe scenes and reason about them in language, yet still struggle to ground their actions in the dense 3D world around them. Existing approaches either inject features from a frozen 3D foundation model without an objective that ensures the policy uses them, or constrain geometry with sparse box and map losses that provide no dense spatial signal. We introduce VLGA, the first vision-language-action model supervised to reconstruct the dense 3D world it drives through. VLGA introduces geometry as a fourth modality alongside vision, language, and action through a dedicated expert supervised by a per-pixel pointmap regression loss against LiDAR. Extensive experiments conducted on challenging nuScenes and Bench2Drive datasets for open-loop and closed-loop evaluations, respectively, show the superiority of VLGA over counterpart VLA methods. In particular, on open-loop nuScenes, VLGA sets a new state of the art among VLA methods without ego status, with the lowest L2 (0.50\,m average) and 3-second collision rate (0.18\%). On closed-loop Bench2Drive, VLGA attains the state-of-the-art driving score of 79.08, +0.71 over the strongest prior VLA, at comparable efficiency and comfort.
arXiv:2606.18098v1 Announce Type: new Abstract: Advances in Artificial Intelligence (AI) have led AI for Theorem Proving to become a promising means of formally verifying computer systems. Whilst formal verification is traditionally reserved for safety-critical systems due to the required amount of expertise and effort, AI can help to automate a large amount of this workload and make it far more accessible. Blockchain-based systems are becoming increasingly popular and are frequently targeted by malicious actors, often resulting in huge financial losses, highlighting the need to better verify these systems and mitigate vulnerabilities. Arguably the most important component of these systems is the consensus protocol, which allows nodes to agree on decisions in a potentially adversarial environment. In this paper, we improve upon IsabeLLM, the automated theorem proving tool in Isabelle. Namely, we implement a Retrieval-Augmented Generation framework, Error tracing and counterexample generation for improved context supplied to the Large Language Model. Compatibility with the latest version of Isabelle and Sledgehammer is also implemented for improved efficiency. We compare the performance of the two versions of IsabeLLM in their ability to complete the verification of Bitcoin's Proof of Work consensus.
arXiv:2606.18022v1 Announce Type: new Abstract: Masked diffusion models (MDMs) have recently emerged as a promising paradigm for sequence generation. Scaling MDMs is conventionally achieved by increasing the parameter count or the number of denoising steps. We introduce Recursive Masked Diffusion Models (R-MDMs), which add recursive depth as a third scaling axis by repeatedly applying the same denoising transformer within each diffusion step. Recursion enables iterative refinement of the output through parameter reuse, increasing effective model depth without increasing parameter count. Across structured generation tasks, including Sudoku and Countdown, we show that R-MDMs achieve substantially improved parameter efficiency: a model with $L$ recursive iterations often matches the performance of non-recursive baselines with roughly $L\times$ more parameters. Moreover, recursive refinement can partially substitute for additional denoising steps, allowing recursive models to reach the same generation quality with fewer forward passes at inference time. These results suggest that recursive depth is a practically useful scaling mechanism for MDMs, improving both parameter efficiency and the allocation of test-time compute.
arXiv:2605.03460v3 Announce Type: replace Abstract: Time series (TS) reasoning models (TSRMs) have shown promising capabilities in general domains, yet they consistently fail in the financial domain, which exhibits unique characteristics. We propose a general 2 x 2 capability taxonomy for TSRMs by crossing 1) single-entity vs. multi-entity analysis with 2) assessment of the current state vs. prediction of future behavior. We instantiate this taxonomy in the financial domain-where the distinction between deterministic assessment and stochastic prediction is particularly critical-as ten financial reasoning tasks, forming the FinTSR-Bench benchmark based on S&P stocks. To this end, we propose FinSTaR (Financial Time Series Thinking and Reasoning), trained on FinTSR-Bench with distinct chain-of-thought (CoT) strategies tailored to each category. For assessment, which is deterministic (i.e., computable from observable data), we employ Compute-in-CoT, a programmatic CoT that enables models to derive answers directly from raw prices. For prediction, which is inherently stochastic (i.e., subject to unobservable factors), we adopt Scenario-Aware CoT, which generates diverse scenarios before making a judgment, mirroring how financial analysts reason under uncertainty. The proposed method achieves 78.9% average accuracy on FinTSR-Bench, substantially outperforming LLM and TSRM baselines. Furthermore, we show that the four capability categories are complementary and mutually reinforcing through joint training, and that Scenario-Aware CoT consistently improves prediction accuracy over standard CoT. Code is available at https://github.com/seunghan96/FinSTaR.
arXiv:2606.12828v1 Announce Type: new Abstract: Do research topics in artificial intelligence grow gradually, or do they advance through abrupt, detectable jumps? Analyzing 80,814 accepted main-track papers from five premier AI conferences (ACL, CVPR, ICLR, ICML, NeurIPS) spanning 2017 to 2025, we show major AI topics advance through topical phase transitions: remaining marginal for years, then surging across venues within one to three years. Large language models became the dominant cross-venue topic by 2025, diffusion models rose with comparable abruptness, and language-model methods crossed into computer vision via vision-language models, whereas reinforcement learning compounded smoothly, distinguishing genuine phase transitions from ordinary growth. This structure is our primary contribution: a large-scale, cross-venue characterization of how AI research reorganizes. We then ask whether a transition leaves a detectable footprint before it peaks. We define an early-warning signature, four publication-dynamics criteria frozen on 2017-2021 data, and evaluate it out of sample on 2023-2025 transitions, obtaining a precision of 27% and recall of 63% against a 13.5% base rate. Applied to 2025 data, the signature flags reasoning and test-time compute, agentic AI, multimodal LLMs, retrieval-augmented generation, and world models as topics to monitor over 2026-2028. The source code is also publicly available on GitHub at https://github.com/KurbanIntelligenceLab/ai-phase-transitions.
arXiv:2606.15856v1 Announce Type: cross Abstract: Operational disturbance monitoring in power networks requires decisions to be made from waveform windows as they arrive, rather than from completed records after the event. This study evaluates full-vector Wigner–Ville Distribution Slice (WVDS) spectra for sequential anomaly-onset detection in high-voltage grid-voltage waveforms. The approach keeps the bilinear midpoint interaction structure of the Wigner–Ville distribution and represents each 128-sample voltage window by a 128-dimensional slice spectrum, avoiding manually selected fault-frequency markers. WVDS is used with a baseline-normalized deviation (BND) score and is compared against the BND of Fast Fourier Transform (FFT-BND), raw-window autoencoders, FFT autoencoders, and WVDS autoencoders under the same thresholding and three-window persistence rule. A synthetic autoencoder–clustering teacher is used to select RTE fault records that start from an initially normal region and then transition to anomalous behavior. On the filtered test set, FFT-BND achieves the highest sensitivity, whereas WVDS-BND provides the lowest false-alarm operating point, reducing record-level pre-onset false alarms to 0.69%. The autoencoder comparison follows the same selectivity pattern: WVDS reconstruction decreases false alarms relative to FFT reconstruction but misses more examples. The results indicate that preserved WVD cross-term information can form a selective representation for online grid-waveform anomaly monitoring when false alarms are costly.
Background: Suicide is the second leading cause of death in US adolescents aged 10-24. Method use strongly influences lethality and design of prevention strategies, but recent trends remain unclear. We therefore aimed to investigate trends in suicide mortality rates by method, age group, and sex. Methods: This cross-sectional study used suicide mortality data from the National Center for Health Statistics for a quarter-century period, between 1999 and 2024. All individuals aged 10-24 years at the time of death, with suicide as the underlying cause, were included. We estimated suicide mortality rates (i.e., the number of suicide deaths per 100,000 people) and annual percent change by method (firearm, asphyxiation, poisoning, other), age group (10-14, 15-19, 20-24), and sex. Changing trend time points were determined using Joinpoint regression models Results: From 1999 to 2024, 159,241 suicide deaths occurred among individuals aged 10-24. While suicide rates declined across all age groups between 2017 and 2024, the male-to-female gap narrowed by 18.9%. Among 10-14-year-olds, declining rates among males masked a consistent increase in female suicide rates since 2011. Although asphyxiation-related suicides decreased across all groups since 2018, firearm suicide rates increased for females in the 10-14 and 20-24 age groups. Albeit not as common as firearms or asphyxiation, poisoning suicide rates increased in the 15-19 and 20-24 age groups. Since 1999, suicide rates by other less common methods (e.g., jumping) showed significant increases, for both sexes, especially among individuals aged 20-24. Suicide rates were consistently highest in the 20-24 age group across all study years. Conclusion: The decrease in suicide mortality rates among individuals aged 10-24 was largely driven by declines in males and reductions in asphyxiation-related suicides. However, increasing female suicide rates in the 10-14 age group, as well as increasing rates of death by less common means, warrant close attention. While suicide prevention efforts like structural interventions and means restriction have shown effectiveness among male adolescents, priority should now be given to adapting these approaches for female adolescents, particularly those aged 10-14.
arXiv:2606.12871v1 Announce Type: new Abstract: Search Agents (SAs) typically leverage large language models (LLMs) to support complex information-seeking tasks by autonomously exploring web sources and synthesizing information into comprehensive responses. For SAs evaluation, prior benchmarks mainly focus on specialized tasks that are unlikely to arise in real-world user scenarios. Moreover, their reliance on coarse task-level rubrics often limits evaluation interpretability. To bridge this gap, we introduce DailyReport, an open-ended benchmark to evaluate SA capabilities on daily search tasks. It contains 150 open-ended tasks with 3,546 associated rubrics, capturing widely discussed and timely information demands of real-world users. Each task is decomposed into subtasks and evaluated with cascade rubrics across disentangled dimensions. Through cascade performance attribution and user-centric aggregation, we derive highly interpretable scores for each dimension, along with a user preference score. Our results on 17 agentic systems show that current systems still fall short of users' expectations. To facilitate future research, our dataset and code are made publicly available at https://github.com/AGI-Eval-Official/DailyReport.
Background Upper airway disease is common in primary ciliary dyskinesia (PCD), but management evidence is limited. We aimed to describe management practices and identify factors influencing management decisions. Methods Using data from the Ear-Nose-Throat (ENT) Prospective International Cohort of patients with PCD (EPIC-PCD) and an ENT-specialist survey across participating centres, we described management practices recorded at routine follow-up. We assessed clinical factors associated with practices via mixed-effects logistic regression models. In a subgroup of patients, we assessed factors associated with initiation or discontinuation of practices. Results We included 579 patients: median age 15 years, 46% female. Nasal rinsing (54%) and nasal corticosteroids (22%) were most frequently prescribed. Among 466 patients with available data, 47 had grommets (10%) and 42 hearing aids (9%). Nasal corticosteroids and rinsing were more frequently prescribed in patients with polyps (odds ratio [OR] 3.74, 95% confidence interval [CI] 1.80-7.76; OR 3.39, 95% CI 1.37-8.37) or turbinate hypertrophy (OR 1.89, 95% CI 1.03-3.47; OR 2.89, 95% CI 1.55-5.38), and upper airway nebulisation in patients with frequent nasal symptoms (OR 2.86, 95% CI 1.11-7.39). Management practices differed between centres, as seen also by the specialists survey responses. In 177 patients with multiple visits, initiation of nasal rinsing was associated with frequent nasal symptoms (OR 3.18, 95% CI 1.24-8.18) and turbinate hypertrophy (OR 3.21, 95% CI 1.20-8.59). Conclusion Upper airway disease management in PCD varies and is partly guided by symptom burden and clinical findings. This variation across centres highlights the need for care standardisation and PCD-specific management guidelines.
arXiv:2606.18722v1 Announce Type: new Abstract: In this short article we consider a preferential attachment random graph model with edge steps, studied by Alves, Ribeiro and Sanchis. Starting with an initial graph $\mathbb{G}_1$ formed by a vertex with a self-loop attached to it, the model evolves as follows. At every subsequent (discrete) time step, either with probability $p$ we add a vertex to the graph and connect it to exactly one of the older vertices selected with probability proportional to its degree, or with probability $1-p$ we add one edge between two existing vertices, both selected (independently) with probability proportional to their degrees. Let $\omega(\mathbb{G})$ be the clique number of a graph $\mathbb{G}$, i.e.\ the number of vertices in a largest complete subgraph of $\mathbb{G}_{}$. Alves, Ribeiro and Sanchis showed that, for any given $\varepsilon>0$, we have $\omega(\mathbb{G}_{2t})\geq t^{\frac{1-p}{2-p}(1-\varepsilon)}$ with high probability (i.e.\ with probability tending to $1$ as $t\rightarrow \infty$). Here we strengthen this bound by showing that, for any function $f:\mathbb{N}\mapsto \mathbb{N}$ that satisfies $f(t)\rightarrow \infty$ as $t\rightarrow \infty$, with high probability \[\omega(\mathbb{G}_{2t}) = \Omega\left(t^{\frac{1-p}{2-p}}\Big(\log^{\frac{1}{2-p}}(t)f(t)\Big)^{-1}\right).\]
arXiv:2506.01678v2 Announce Type: replace-cross Abstract: Scanning tunnelling microscopy (STM) is a powerful technique for imaging surfaces with atomic resolution, providing insight into physical and chemical processes at the level of single atoms and molecules. A regular task of STM image analysis is the identification and labelling of features of interest against a uniform background. Performing this manually is a labour-intensive task, requiring significant human effort. To reduce this burden, we propose an automated approach to the segmentation of STM images that uses both few-shot learning and unsupervised learning. Our technique offers greater flexibility compared to previous supervised methods; it removes the requirement for large manually annotated datasets and is thus easier to adapt to an unseen surface while still maintaining a high accuracy. We demonstrate the effectiveness of our approach by using it to recognise atomic features on three distinct surfaces: Si(001), Ge(001), and TiO$_2$(110), including adsorbed AsH$_3$ molecules on the silicon and germanium surfaces. Our model exhibits strong generalisation capabilities, and following initial training, can be adapted to unseen surfaces with as few as one additional labelled data point. This work is a significant step towards efficient and material-agnostic, automatic segmentation of STM images.
arXiv:2606.12864v1 Announce Type: cross Abstract: Despite strong performance in competitive programming, the role of Large Language Models (LLMs) in supporting human learning in the same setting remains largely unexplored. In this work, we introduce UOJ-Bench, a benchmark designed to evaluate not only the problem-solving ability of LLMs, but also their ability to identify errors in human-written code – a crucial educational activity traditionally supported by running test cases over online judge systems. UOJ-Bench consists of three distinct tasks: code generation, code hacking, and code repair, all constructed from real-world code submissions on the Universal Online Judge (UOJ) and evaluated through UOJ's native judging infrastructure. Our results show that under one-shot evaluation, even the strongest models fail to identify errors in more than 50% of a set of submissions that have been found to be incorrect by UOJ users. While test-time scaling improves success rates to above 90%, the substantial computational costs incurred from model inference limit its practicality for large-scale deployment. Despite these limitations, we find that the best-performing models under test-time scaling can uncover errors in over 5% of full-score submissions across roughly 30 problems, suggesting that frontier LLMs can already provide complementary signals beyond standard judging systems.
arXiv:2406.09852v2 Announce Type: replace Abstract: We study the asymptotic behavior of a critical decomposable 3-type Galton-Watson process with immigration when its offspring mean matrix is triangular with diagonal entries 1. It is proved that, under second or fourth order moment assumptions on the offspring and immigration distributions, a sequence of appropriately scaled random step processes formed from such a Galton-Watson process converges weakly. The limit process can be described using independent squared Bessel processes $({\mathcal X}_{t,1})_{t\geq0}$, $({\mathcal X}_{t,2})_{t\geq0}$, and $({\mathcal X}_{t,3})_{t\geq0}$, the linear combinations of the integral processes of $({\mathcal X}_{t,1})_{t\geq0}$ and $({\mathcal X}_{t,2})_{t\geq0}$, and possibly the 2-fold iterated integral process of $({\mathcal X}_{t,1})_{t\geq0}$. The presence of the 2-fold iterated integral process in the limit distribution is a new phenomenon in the description of asymptotic behavior of critical multi-type Galton-Watson processes with immigration. Our results complete and extend some results of Foster and Ney (1978) for some strongly critical decomposable 3-type Galton-Watson processes with immigration.
We present Context Window Lifecycle (CWL), a context-management scheme that gives long-horizon LLM agents an effectively unbounded working horizon. As a session accumulates history, CWL keeps the context within budget through graduated, semantically-aware eviction: the agent annotates its trajectory as typed, dependency-linked episodes as work proceeds, and a deterministic, LLM-free policy evicts content in priority order within that structure when a token budget is exceeded. CWL preserves user turns and the exploratory context the agent is actively reasoning over, while aggressively shedding action episodes whose effects are already persisted in the environment, keeping active context near a stable ceiling that also avoids the performance degradation associated with very large prompts. Compared to summarization-based compaction, CWL avoids four well-known limitations: unpredictable lossiness, destruction of causal structure, blocking model cost, and compression-induced hallucination. Compared to recency truncation, CWL is semantically aware: it drops the oldest-and-most-recoverable content according to the dependency graph rather than oldest-in-time regardless of relevance. We describe the annotation protocol, the episode graph, the eviction policy, and the token-accounting loop, and evaluate CWL on long-horizon agentic benchmarks: a single agent session completing 89 sequential tasks across 80 million tokens with no measurable degradation in task accuracy relative to per-task isolated sessions
arXiv:2606.19887v1 Announce Type: cross Abstract: Existing safety benchmarks target general adversarial scenarios but miss finance-specific risks. Financial LLMs face regulatory compliance violations, fraud facilitation, and systemic trust erosion that require targeted evaluation. We introduce FinRED, an expert-guided red-teaming framework for financial LLM safety evaluation developed with financial experts. FinRED uses a novel two-level taxonomy mapping global standards (e.g., FATF and EU DORA) to threats ranging from regulatory evasion to complex fraud, integrated with a scalable pipeline that converts real financial documents into context-rich red-teaming Behavioral Prompts (seeds) through an expert-defined schema. Rigorous expert validation confirms seed plausibility and realism for meaningful LLM safety evaluation. We also provide an expert-validated, finance-specific rubric that goes beyond disclaimer checks, aligns more closely with human experts than static one-size-fits-all rubrics, and reduces critical false negatives from 28 to 12. Aligned with internationally adopted risk-management and information-security standards (e.g., ISO/IEC 27001), FinRED is deployed in South Korea's Financial Security Institute (FSI) regulatory sandbox for generative AI security evaluation in real financial services. To mitigate dual-use risks, the dataset, generation pipeline, prompt template, and evaluation framework are gated for qualified researchers at https://github.com/selectstar-ai/FinRED-paper and https://huggingface.co/datasets/datumo/FinRED.
arXiv:2606.12594v1 Announce Type: new Abstract: Modern Lean theorem provers achieve strong performance only with substantial training and inference compute, driven in part by scarce verified proof data and the long reasoning traces of formal proof search, making both supervised fine-tuning (SFT) and sampling expensive. We introduce Pythagoras-Prover, a compute-efficient open-source family of Lean theorem provers built for practical compute budgets. The family spans two generation paradigms: autoregressive models at 4B and 32B parameters, and a first proof-of-concept diffusion-based prover (4B) that iteratively refines Lean proofs at inference time. For training efficiency, we build a Lean-verified corpus stratified into easy, medium, and hard problems for curriculum SFT, so models acquire proof skills progressively from shorter, simpler proofs to longer, harder ones. During SFT, a dynamic proof-reasoning filtering scheme preserves informative proof traces while keeping each instance within an 8k-token context budget. We also introduce Augmented Lean Formalisation (ALF), which expands scarce verified corpora into variants of formal statements, populated via self-distillation for extra training signal without formally verifying every mutated instance. By perturbing known problems while preserving their formal character, ALF reduces reliance on any statement's surface form. Empirically, Pythagoras-Prover-4B surpasses DeepSeek-Prover-V2-671B at pass@32 on MiniF2F-Test (86.1% vs 82.4%) with ~167x fewer parameters, while Pythagoras-Prover-32B sets the open-source state of the art at 93.0% on MiniF2F-Test and solves 93 of 672 PutnamBench problems. We release MiniF2F-ALF, an ALF-mutated contamination-sensitive benchmark on which every evaluated model loses accuracy; here our 32B remains strongest and our 4B matches the prior state of the art, Goedel-Prover-V2-32B.
arXiv:2601.19810v2 Announce Type: replace-cross Abstract: Unsupervised pre-training can equip reinforcement learning agents with prior knowledge and accelerate learning in downstream tasks. A promising direction, grounded in human development, investigates agents that learn by setting and pursuing their own goals. The core challenge lies in how to effectively generate, select, and learn from such goals. Our focus is on broad distributions of downstream tasks where solving every task zero-shot is infeasible. Such settings naturally arise when the target tasks lie outside of the pre-training distribution or when their identities are unknown to the agent. In this work, we (i) optimize for efficient multi-episode exploration and adaptation within a meta-learning framework, and (ii) guide the training curriculum with evolving estimates of the agent's post-adaptation performance. We present ULEE, an unsupervised meta-learning method that combines an in-context learner with an adversarial goal-generation strategy that maintains training at the frontier of the agent's capabilities. On XLand-MiniGrid benchmarks, ULEE pre-training yields improved exploration and adaptation abilities that generalize to novel objectives, environment dynamics, and map structures. The resulting policy attains improved zero-shot and few-shot performance, and provides a strong initialization for longer fine-tuning processes. It outperforms learning from scratch, DIAYN pre-training, and alternative curricula. Code is available at: https://github.com/Octavio-Pappalardo/ulee-jax