Heterogeneous AI systems composed of multiple models, architectures, harnesses, or inference-time settings can improve quality and efficiency by routing queries to the specialist who can answer most effectively at the lowest cost. Routing requires estimating each specialist's expected return, but this value estimation has a cost. Cheap estimators (e.g., embedding-based predictors) are fast but noisy, while accurate estimators (e.g., fine-tuned models with access to retrieval results or partial reasoning traces) are expensive. We formalize this tradeoff as an instance of Pandora's Box, the classical problem of optimal search with costly inspection. Under a Gaussian signal model, the resulting policies have closed-form value-of-information expressions that determine, for each specialist and input, whether refining the value estimate is worth its cost. We call the centralized policy Pandora's Router. We extend this to a decentralized setting, Pandora's Bidder, where specialists independently decide whether to invest in self-assessment before accepting an offered price to claim a query. Experiments across three domains---a standard multi-LLM benchmark, retrieval-augmented specialists, and LLMs with variable inference-time reasoning---show that Pandora's Router matches the routing quality of exhaustive estimation, while querying the expensive estimator far less often. In the decentralized setting, value-of-information reasoning improves allocative efficiency when competing estimates are accurate; when competing estimates are noisy, however, it can increase the strategic specialist's utility at the expense of others.
Predictive models over structured electronic health records (EHRs) remain central to machine learning for healthcare, but few have jointly emphasized quantitative laboratory information and interpretability with respect to input medical events. We present BERT-LER, a BERT-style model for coded EHR timelines pretrained and fine-tuned from a de-identified EHR dataset of 75 million patients, that encodes laboratory test results as discrete tokens while retaining graded information through percentile-based binning, paired with Integrated Gradients for token-level attributions grounded in the input EHR sequence. We benchmark our approach on the public EHRShot benchmark suite and on an asthma severity progression study based on real-world data. This addresses a methodological gap in EHR foundation-style modeling by unifying laboratory value representation and explainability in a single framework, while assessing whether both predictive performance and explanations generalize beyond standard clinical prediction tasks. Across EHRShot and asthma tasks, BERT-LER achieves predictive performance that is competitive with, and on laboratory-related tasks often exceeds, publicly available benchmark models, and provides attributions that align with clinically known risk factors. Our architecture and explainability approach can be applied to many therapeutic areas and prediction tasks using language models trained on structured EHRs.
Assine o Pro, sem anúncios
Faça upgrade para uma leitura sem interrupções e acesso prioritário a novas fontes.
Mid-training is increasingly recognized as a critical stage for shaping the capabilities of large language models. Recent work has shown that targeted mid-training can strengthen reasoning-intensive abilities such as math and science, and can also improve agentic capabilities in software-engineering settings. In this work, we study the parallel but less explored agentic capability: general tool use. We present MidTool, an open corpus construction pipeline for agentic tool-use mid-training that combines large-scale web, PDF, and code data with synthesized supervision from real-world tool APIs, MCP skills, and document-grounded workflows. MidTool is designed to teach models how to recognize tool affordances, ground arguments from context, compose tool call workflow, and recover from incomplete information. We mid-train Qwen3-4B-Base and Qwen3-8B-Base on MidTool-Mix, and then apply follow-up post-training with both supervised fine-tuning and reinforcement learning. Compared with baselines, MidTool-Mix consistently improves downstream performance under both SFT and RL on BFCL, tau2-Bench, and MCP Universe. These results suggest that general tool use, like other important LLM capabilities, benefits from dedicated mid-training rather than being left entirely to post-training.
Sparse pursuit after dictionary learning can yield a precise atom support even when its physical interpretation is not justified by the calibration data, especially for highly coherent dictionaries where alternative calibration-compatible dictionaries may assign different physical meanings to the same selected support. We develop resolution-aware physical-support inference that jointly accounts for uncertainty in the learned dictionary and in the representation of a deployment signal. Our cross-dictionary confidence correspondence retains calibration-compatible dictionaries and deployment-compatible sparse representations, then projects the surviving explanations onto physical-support space. For local coherent-atom classes with separation scale s, once the deployment data resolve the coherent-block explanation and its atom support, the minimax physical resolution from N calibration signals satisfies δ_{opt}(N,s)\{s,{1}{{N}s^2}\}, with relative resolution governed by the orientation-information scale Ns^6. Deployment replication improves physical localization only when orientation changes cannot be absorbed by adjusting the active coefficients. For computation, we introduce active endpoint bracketing (AEB), an adaptive finite-bank procedure that evaluates only candidates that can still affect the physical report and otherwise safely coarsens or abstains. Finite-bank experiments, including a four-region synthetic application, show that a point-valued plug-in selector can be physically overprecise, whereas AEB avoids unsupported refinement with fewer candidate evaluations.
Affected users told TechCrunch say they were using Grok Lite, and noticed the issues as early as Wednesday morning.
Whether a language model has improved itself is increasingly judged not by mean accuracy but by which individual problems it gains and loses. Tracking these transitions means differencing two noisy estimates, leaving them vulnerable to measurement artifacts. Auditing three rounds of rank-32 LoRA self-training on Qwen3-8B against a frozen control pushed through the identical pipeline, we identify seven measurement failures, each of which inverts a reported finding when its control is absent. Several are standard practice. A ledger built on a single greedy decode manufactures capability changes on an untrained model, largely an artifact of inference batching; the expansion statistic separating acquisition from sharpening assigns that same model a rate of 0.280. The natural threshold repair does not survive replication: estimated across the frozen comparisons such a design already contains, its null stays non-zero. We replace it with a per-problem exact test against a pooled baseline under false-discovery-rate control, which detects nothing on any held-out replicate and is unchanged under the multiple-testing rule, error rate and pool size. Applied to a ladder of arms matched in stream, volume and evaluation, the audit finds that external distillation improves problems the base model rarely reaches while three forms of self-training do not; a regression rejects this asymmetry as a by-product of distillation's larger overall gain (p < 10^{-8}). On the far smaller set of problems the base model never reaches, the evidence is inconclusive, while self-training corrupts problems solved at baseline at rates well above the measured floor. Transition-level auditing therefore requires a separately measured null for every statistic it reports: nulls that cost no new experiments, built from baseline replicates a multi-arm study already owns, though not from as few as most possess.
The causal dynamics of sleep-disordered breathing are complex and vary across patient populations, hindering the development of targeted interventions. We learn dynamic causal graphs of sleep-disordered breathing from Home Sleep Apnea Test (HSAT) recordings, revealing systematic differences in causal structure across sex and age subcohorts. We do so using the PCMCI+ algorithm on windowed fractional variables derived from 105 HSAT recordings, exploiting domain knowledge via edge blacklisting and employing bootstrap aggregation to address small subcohort sizes. The learned graphs show that temporal self-dependencies and the apnea-desaturation relationship persist across all cohorts, while other relationships vary substantially.
ChatGPT and other AI models are now authoring and editing much of the new web.
Large language models often fail to answer questions about a bounded document collection when the source documents are not retrieved at inference time. We study this setting as document knowledge internalization: converting a fixed corpus into usable parametric knowledge for retrieval-free question answering. We propose IAR (Inject, Align, and Recover), a three-stage post-training framework that separates structured document knowledge injection, QA behavior alignment, and general ability recovery. Unlike conventional continued pretraining, Inject converts source documents into continuation, rewrite, and instruction-conditioned reconstruction objectives. Align then adapts the injected model with answer-only QA supervision, while Recover merges the domain-adapted model with the base instruction model to recover general capabilities. Across Common Corpus (CC) and CCI, and across Llama, Phi, Qwen, and SmolLM model families, IAR improves the domain-primary domain-general frontier for retrieval-free document internalization. In the main comparison, IAR improves over Vanilla SFT on all four reported metrics in 7 of 8 dataset-model settings, with average gains of 3.6 percentage points in domain QA accuracy and 12.1 percentage points in mean general performance across IFEval, MMLU, and MSBench. Extended CC baselines show that LoRA and FAPM can win individual general metrics, but among methods that also reach leading or near-leading domain internalization, IAR retains one of the strongest general profiles.
Semantic caches reuse an LLM response when the incoming query embedding lies near a cached query, but proposed eviction policies have rarely been compared under one protocol. Using CLEVER, we evaluate FIFO, LRU, LFU, ARC, GDSF, a single-pass streaming adaptation of SISO, and a semantic-redundancy policy across three ordered, deduplicated query corpora, three cache capacities, and two encoders. No evaluated policy improves on LFU by more than 0.041 percentage points in any of the eighteen settings. Replacement is not irrelevant: FIFO and streaming SISO trail LFU by as much as 8.67 and 8.55 points, respectively, at tight capacity. We explain the missing upside with a conditional packing result. Under exact lookup and insert-on-miss, a newly inserted entry cannot have a resident neighbor within the hit radius, so a geometry-aware eviction rule receives little new redundancy signal. A separate audit exposes a larger problem with the evaluated operating point. At MiniLM's median nearest-neighbor threshold, only 2.1-3.9% of sampled LMSYS and QQP hits are judged answer-substitutable, reducing raw hit rates of 51-60% to quality-adjusted rates of 1.1-2.2%. The cross-encoder study further shows that thresholds do not transfer between embedding models. LFU is the strongest simple default in this protocol; deployment decisions should first establish answer validity and then test sub-point policy differences with exact search.
Large language model (LLM) agents can induce skills from completed tasks and reuse them later to grow more capable with experience. In practice, induced skills may transfer unreliably and can even harm the agent that retrieves them. When agent-induced skills transfer reliably across tasks remains an open question. We conduct a comprehensive and controlled study of how the way skills are induced shapes their transfer across tasks. Specifically, we compare task-level with subtask-level skill induction and text with code skill formats, the two axes along which existing methods differ. Task-level skills mostly reduce the agent's performance below its no-memory baseline while subtask-level skills raise it above on average, and text skills transfer better than code skills. To further understand our findings, we examine two complementary properties of the induced skills: specificity, which measures how closely a skill matches real tasks, and abstractness, which measures how evenly its relevance spreads across tasks. Neither property alone predicts task success, but their combined effect does, which we propose as a skill utility score. The score correlates consistently with task success when skills are transferred, and subtask-level and text skills score higher. Computing skill utility only needs the skills and task descriptions but not any task execution, so our score serves as a practical diagnostic of a skill memory before any new task runs.
The rapid proliferation of memecoins on blockchain platforms has increased the risk of fraudulent activities, particularly rug pulls. While previous studies have focused on Ethereum-based tokens, this paper shifts the spotlight to Solana, the leading blockchain for memecoins by trading volume and token count. Unlike Ethereum, where rug pulls often exploit smart contract backdoors, Solana memecoin rug pulls are predominantly driven by liquidity manipulation and social dynamics. This research pioneers large-scale rug pull early detection in the Solana ecosystem by assembling a dataset of 6.4 million tokens over 7 months. Market analysis reveals that a vast majority of these memecoins exhibit rug pull characteristics within one hour of launch, highlighting the urgency of short-horizon prediction. Despite the absence of code-level features, we demonstrate that classic machine learning models, particularly Gradient Boosting (XGBoost), achieve robust performance in detecting potential rug pulls using only the first 5 minutes of trading data. Furthermore, we evaluate cross-platform generalization between PumpFun and Raydium, revealing that multi-source data fusion significantly mitigates domain shift and improves detection reliability. This study advances the understanding of DeFi fraud on high-throughput chains and provides a practical framework for protecting investors.
Decision tree-based models are widely used in machine learning due to their interpretability and strong empirical performance. However, training decision trees can be computationally expensive, particularly for large and high-dimensional datasets, largely due to the exhaustive search over candidate splits at each node. To improve computational efficiency, we propose Data-Informed Centroid Splitting (DICS), a clustering-based framework that constructs a compact and informative set of candidate splits using data-driven priors. By incorporating class-aware structure, DICS significantly reduces the split search space for classification tasks while preserving predictive performance. We further provide theoretical analysis showing that under the stated assumptions, DICS does not degrade the performance of classification trees compared to exhaustive split search. DICS can be incorporated into classification trees, random forests, and gradient-boosting models. Extensive experiments demonstrate that DICS achieves comparable accuracy while substantially reducing training time across synthetic and benchmark datasets, highlighting the benefit of integrating data-informed priors into split selection for scalable classification tree learning.
Reasoning language models trained with reinforcement learning typically operate under a fixed token budget rather than an explicitly adaptive one, which can lead to over-computation on easy problems and insufficient computation on difficult ones. We study whether a model can learn to allocate its own reasoning effort by choosing, as the first token of its response, one of three modes: NoThink (answer as quickly as possible), Short (brief reasoning), or Long (extended reasoning). The choice is learned inside Group Relative Policy Optimization (GRPO) with no separate router, through a shaped reward that makes each mode worthwhile at a different response length, together with hard per-mode token caps that keep the modes distinct. On a 1.5B distilled model trained on MATH, the three modes emerge without collapsing to a single choice, and the brief modes end up more accurate than Long, which shows that the router sorts problems by difficulty rather than at random. Averaged over three seeds, the resulting policy stays close to the base model's accuracy on the held-out MATH500 (0.782 vs.\ 0.796) while cutting the mean response length from 4{,}796 to 2{,}811 tokens (a 41\% reduction). Interestingly, it also transfers to other benchmarks without retraining, with the largest savings where problems are easier, with for instance 76\% token reduction on GSM8K and at higher accuracy than the baselines at similar response length. In short, we build a reasoning model that adaptively chooses how much to reason for each problem.
This paper develops a general transfer learning framework for nonparametric regression with data consisting of multiple groups. Under the assumption that groups share a common structure along with group-specific deviations in additive form, the proposed method employs a two-stage offset learning procedure: the first stage pools data from all groups to estimate an overall mean function, and the second stage estimates offsets for each group, yielding final group-level estimators through additive combination. Upper bounds on the L_2 error are established for the proposed framework, covering a broad class of nonparametric estimators under mild complexity and noise conditions. When instantiated with deep ReLU networks, explicit convergence rates are derived under hierarchical composition models, demonstrating the ability to overcome the curse of dimensionality. Conditions that enable positive transfer with faster rates are considered, including learning with simpler functions and data augmentation through pooling samples across groups. Various simulations and real-data experiments further validate the effectiveness of the proposed method.