新闻与研究

arXiv:2605.28069v1 Announce Type: new Abstract: Adaptive context compression is vital for scaling Large Language Models (LLMs) to complex, multi-turn agent tasks. However, rule-based compression methods may discard task-critical nuances, while Reinforcement Learning (RL) approaches usually struggle to balance information retention and token efficiency under the sparse rewards inherent to long-horizon workflows. To bridge this gap, we propose ZipRL, a novel adaptive compression framework tailored for Reinforcement Learning from Verifiable Rewards (RLVR). ZipRL features a multi-granularity compression mechanism for active, non-uniform information reduction, coupled with Hindsight Response Replay (HRR), a technique designed to densify training signals during RLVR optimization. Theoretically, we prove ZipRL's superior task-relevant utility over uniform methods. Concretely, ZipRL utilizes coarse-to-fine prompts for macro-compression and incorporates HRR into GRPO via generalized advantage r

arXiv:2605.28338v1 Announce Type: new Abstract: Large language models(LLMs) increasingly match expert performance on licensing examinations, yet routine clinical use remains limited because governance requires auditable reasoning, safety and ethics alignment, and resilience to adversarial misuse. Here we present SafeMed-R1, trained with a traceable Clinical Trust Signals(CTS) pipeline that links each reasoning instance to clinician rubric scores and edit histories, and aligned through safety and ethics supervision and red team stress testing. SafeMed-R1 attains a macro-averaged accuracy of 79.6% across clinical benchmarks. Under adversarial safety testing, it shows the lowest aggregated risk and reduces unsafe outputs by about 3 to 5% relative to its baseline. In a paired expert study of 30 medication safety vignettes, SafeMed-R1 matches PGY1 and PGY2 residents on medical correctness and scores higher for medication safety, guideline consistency, and clinical usefulness. Collectively,

arXiv:2305.06426v2 Announce Type: replace Abstract: Diabetes is a global health priority, especially in low- and-middle-income countries, where over 50% of premature deaths are attributed to high blood glucose. Community Health Worker (CHW) programs can provide affordable and culturally tailored solutions for early detection and management of diabetes. We introduce an optimization framework to determine personalized CHW visits that maximize glycemic control at a community level. Our framework explicitly models the trade-off between screening new patients and providing management visits to individuals who are enrolled in treatment. We account for patients' motivational states, which affect their decisions to enroll or drop out of treatment and, therefore, the effectiveness of the intervention. By estimating patients' health and motivational states, our model builds visit plans accounting for patients' tradeoffs when deciding to enroll in treatment, leading to reduced dropout rates and i

arXiv:2605.27712v1 Announce Type: new Abstract: Long reasoning traces need reliability estimates before final answers are known. We study prefix-conditioned eventual-success estimation, $P(y=1 \mid o_{1:t})$, using prefix-safe observations. Sequential Bayesian Belief Tracking (SBBT) calibrates observation likelihoods and recursively updates a two-state belief, providing a common tracker for scalar scores, text and self-verification markers, hidden clusters, token-pooling probes, and latent-trajectory features. Across generated open-weight traces on MATH-500, GSM8K, AIME 2025, and RIMO-N, probability quality and ranking separate: score-only SBBT often improves Brier, while AUROC gains require structure-aware evidence beyond strong prefix-safe baselines. In the strongest hard math setting, structure-aware observations reach +0.110 AUROC against standard prefix-safe baselines. Under a same-prefix classifier audit, MATH-500 text markers and RIMO-N self-verification signals remain positive.

arXiv:2605.27610v1 Announce Type: cross Abstract: The rapid growth of scientific publishing has made it increasingly difficult to track how fast-moving areas evolve. Search engines and LLM-based assistants retrieve or summarize papers, but often hide how the corpus was selected, organized, or connected to temporal patterns. We present $\texttt{Eliot}$, a publicly deployed interactive system for traceable exploration of evolving scientific literature. Motivated by two studies on Large Language Models (LLMs) and Automated Planning and Scheduling (APS), $\texttt{Eliot}$ generalizes literature-evolution analysis beyond hand-built taxonomies and domain-specific scripts. Given explicit query terms and filters, it retrieves arXiv papers at query time, represents each paper by title and abstract, clusters the corpus into themes, assigns representative keywords, and visualizes each cluster's publication-year distribution. We evaluate $\texttt{Eliot}$ as both an applied system and an interactive

arXiv:2605.28742v1 Announce Type: new Abstract: Language models can use verifiable rewards to improve at a wide variety of reasoning tasks. However, both parametric (e.g. RLVR) and non-parametric (e.g. prompt optimization) approaches to doing so typically require hundreds of training samples and thousands of model rollouts, making them expensive in the best case and intractable in the worst. To address this challenge, we introduce Contrastive Reflection (CORE), a non-parametric learning algorithm that compares past reasoning traces to generate insights: short natural-language descriptions of reasoning strategies and constraints that capture differences between successful and unsuccessful problem attempts. Across four reasoning tasks, we demonstrate that CORE enables more rapid improvement than both parametric (GRPO) and non-parametric (GEPA, episodic RAG, and MemRL) methods, while using fewer rollouts. Under fixed rollout budgets with as few as five training samples, we then show that

arXiv:2605.28187v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as scholar recommenders, shaping who is seen as an expert in academia. Existing audits remain English-centric, single discipline, and persona-agnostic, leaving the source of output variability poorly understood. To this end, we propose a benchmark that disentangles the effects of model choice and prompt design on recommendations. We audit 43 LLMs by varying persona prompts (language, location, role-and-task) and context (field, seniority, k). Recommended scholars are compared against Semantic Scholar over six scientific disciplines to measure technical quality (factuality, coverage) and social representativeness (diversity, parity). Basic technical quality is driven by model choice, factuality and parity by context, and diversity by location. South Africa prompts yield less factual lists, while Japan prompts yield highly factual but homogeneous lists skewed toward highly productive scho

arXiv:2601.01616v2 Announce Type: replace Abstract: The textile industry in Bangladesh is one of the most energy-intensive sectors, yet its monitoring practices remain largely outdated, resulting in inefficient power usage and high operational costs. To address this, we propose a real-time Non-Intrusive Load Monitoring (NILM)-based framework tailored for industrial applications, with a focus on identical motor-driven loads representing textile cutting machines. A hardware setup comprising voltage and current sensors, Arduino Mega and ESP8266 was developed to capture aggregate and individual load data, which was stored and processed on cloud platforms. A new dataset was created from three identical induction motors and auxiliary loads, totaling over 180,000 samples, to evaluate the state-of-the-art MATNILM model under challenging industrial conditions. Results indicate that while aggregate energy estimation was reasonably accurate, per-appliance disaggregation faced difficulties, partic

arXiv:2603.12344v2 Announce Type: replace Abstract: Molecular Property Prediction (MPP) is a fundamental problem in drug discovery that has recently attracted growing attention. Large Language Models (LLMs), known for their impressive proficiency across domains, show promise as generalist models for MPP. However, their current performance remains below the threshold needed for practical adoption. To bridge this gap, we propose TreeKD for distilling the knowledge of tree-based specialist models into LLMs to complement the internal knowledge of LLMs and improve their predictive accuracy. For each property, we train a specialist decision tree using features derived from 40K functional groups in the input molecules. Then, the predictive rule learned by the decision tree, which encodes its knowledge, is verbalized and incorporated into the prompts for training LLMs. In addition, by replacing a single decision tree with a Random Forest, we introduce a test-time scaling technique called rule-

arXiv:2509.15848v2 Announce Type: replace Abstract: Industrial monitoring systems, especially when deployed in Industry 4.0 environments, are experiencing a shift in paradigm from traditional rule-based architectures to data-driven approaches leveraging machine learning and artificial intelligence. This study presents a comparison between these two methodologies, analyzing their respective strengths, limitations, and application scenarios, and proposes a basic framework to evaluate their key properties. Rule-based systems offer high interpretability, deterministic behavior, and ease of implementation in stable environments, making them ideal for regulated industries and safety-critical applications. However, they face challenges with scalability, adaptability, and performance in complex or evolving contexts. Conversely, data-driven systems excel in detecting hidden anomalies, enabling predictive maintenance and dynamic adaptation to new conditions. Despite their high accuracy, these mo

arXiv:2605.28091v1 Announce Type: new Abstract: Text-to-Image generation has evolved from basic image synthesis into a frequently used core capability in professional creative workflows, where simple text-image alignment can no longer satisfy users' pressing demands for faithful real-world reconstruction and genuine creative expression. Existing benchmarks, however, remain anchored in these foundational criteria and do not yet capture the nuanced capabilities that matter in authentic artistic practice, making it difficult to reliably distinguish state-of-the-art T2I models. To address the gap, we introduce Qwen-Image-Bench, a creator-centric benchmark co-designed with professional artists and grounded in real-world creation scenarios. Qwen-Image-Bench enriches conventional evaluation with two application-driven dimensions: Real-world Fidelity and Creative Generation. Drawing on the staged reasoning inherent in professional artistic workflows, we organize these five pillars into a top-d

arXiv:2601.16312v3 Announce Type: replace-cross Abstract: Research in AI4Science has shown promise in many science applications, including polymer design. However, current LLMs are ineffective in this problem space because: (i) most models lack polymer-specific knowledge, and (ii) existing aligned models have limited coverage of knowledge and capabilities relevant to polymer design. Addressing this, we introduce PolyBench, a large-scale training and test benchmark dataset of more than 125K polymer design-related tasks, leveraging a knowledge base of more than 13 million data points obtained from experimental and synthetic data sources to ensure broad coverage of polymers and their properties. For effective alignment using PolyBench, we introduce a knowledge-augmented reasoning distillation method that augments this dataset with structured CoT. Furthermore, tasks in PolyBench are organized from simple to complex analytical reasoning problems, enabling generalization tests and diagnostic

arXiv:2605.28162v1 Announce Type: cross Abstract: Logical operations are essential for quantum computation within quantum error-correcting codes. However, discovering their physical realizations is challenging, especially for non-additive codes that lack a stabilizer description. We present a general learning-based framework that, given only an encoding circuit, constructs physical implementations of logical operations while enforcing structural properties such as transversality or shallow depth. Our approach is validated by rediscovering known logical operations of standard stabilizer codes. We then extend it to a co-design procedure, dubbed variational early fault-tolerant quantum computing (VarEFTQC), which tailors non-additive encodings to a given noise model and enforces desired logical gate sets, such as transversal IQP-type families or low-depth universal sets. A software library implements the complete learning pipeline, including loss-function variants, ansatz families, and op

arXiv:2602.23602v2 Announce Type: replace-cross Abstract: Heteroscedasticity -- where the variance of a variable changes with other variables -- is pervasive in real data, and elucidating why it arises from the perspective of statistical moments is crucial in scientific knowledge discovery and decision-making. However, standard causal discovery does not reveal which causes act on the mean versus the variance, as it returns a single moment-agnostic graph, limiting interpretability and downstream intervention design. We propose a Bayesian, moment-driven causal discovery framework that infers separate \textit{mean} and \textit{variance} causal graphs from observational heteroscedastic data. We first derive the identification results by establishing sufficient conditions under which these two graphs are separately identifiable. Building on this theory, we develop a variational inference method that learns a posterior distribution over both graphs, enabling principled uncertainty quantifica

arXiv:2605.11544v2 Announce Type: replace Abstract: Strategy synthesis typically follows an all-or-nothing paradigm, returning unrealisable whenever a specification cannot be guaranteed in an uncertain environment. In this paper, we introduce optimal LTLf synthesis, where the goal is to realise as many objectives as possible from a given specification consisting of multiple objectives, especially for the case that they are not all jointly realisable. We first consider max-guarantee synthesis, which commits to a maximal set of objectives that we can a priori guarantee to realise. We then introduce max-observation synthesis, which maximises a posteriori realised objectives that may be incomparable on different executions. Finally, we present incremental max-observation synthesis, which further improves strategies by exploiting opportunities for stronger guarantees when they arise during an execution. Experimental results show that different variations of optimal synthesis scale broadly e