EVOQUANT: Self-Evolving Verifier-Guided Strategy Optimization for Robust Quantitative Trading

By: Jie Mao · Changlun Li · Xiang Li · Qiqi Duan · Jinhui Yuan · Xiang Liu · Yuyu Luo · Jing Tang · Xiaowen Chu · Nan Tang

10 September 2026 at 12:00

arXiv:2607.12455v2 Announce Type: replace Abstract: Quantitative strategy optimization remains largely manual, requiring domain experts to identify weak signals, tune risk-control rules, and repeatedly validate iterative revisions. Large language models can accelerate this process, but directly relying on them to rewrite trading strategies often introduces hallucinated edits, strategy drift, and backtest overfitting. We propose EVOQUANT, a self-Evolving Verifier-guided framework for strategy Optimization in Quantitative trading. Our method utilizes LLMs to deeply diagnose performance bottlenecks, generates semantically controlled candidate edits, selects the best strategy through a multi-stage verification pipeline, and distills optimization experience into reusable knowledge for continual self-improvement. We evaluate our method using seven representative strategies: four from the A-share market and three from the Crypto market. Experimental results show that our method significantly improves the Sharpe ratio across all tested strategies: the average test Sharpe increases from -0.298 to 0.538, and the best-performing strategy achieves a 199% relative improvement. Ablation studies and stress tests under stricter conditions further validate the effectiveness and robustness of the framework. Overall, this work transforms quantitative strategy optimization from costly manual trial and error into an automated and verifiable iterative paradigm, offering a new path for applying large language models to financial strategy research.

Test-Time Deep Thinking to Explore Implicit Rules

cs.AI, q-bio.NC updates on arXiv.org

By: Wentong Chen · Xin Cong · Zhong Zhang · Yaxi Lu · Siyuan Zhao · Yesai Wu · Qinyu Luo · Haotian Chen · Yankai Lin · Zhiyuan Liu · Maosong Sun

26 May 2026 at 12:00

arXiv:2605.24828v1 Announce Type: new Abstract: With the continuous advancement of Large Language Models (LLMs), intelligent agents are becoming increasingly vital. However, these agents often fail in environments governed by implicit rules--hidden constraints that cannot be observed directly and must be inferred through interaction. This causes agents to fall into repetitive trial-and-error loops, ultimately leading to task failure. To address this challenge, we propose Test-Time Exploration (TTExplore), a framework where a thinker component analyzes interaction history to infer these implicit rules and guide an actor. Effective exploration in this setting critically depends on the reasoning ability of the thinker. However, evaluating deep reasoning trajectories is inherently unstable and difficult, which poses a major obstacle to effective training. To overcome this issue, we introduce a novel and stable reinforcement learning pipeline. The core idea is to use accurate task-level scores as indirect rewards to bypass the difficulty of evaluating intermediate reasoning, and to retain only a single thinking node per trajectory to alleviate reward sparsity. Using this pipeline, we train a specialized 7B model, Exp-Thinker. Experiments on five text-based embodied tasks show that TTExplore equipped with Exp-Thinker improves baseline agent performance by an average of $14$-$19$ points, demonstrating the effectiveness of explicitly reasoning about implicit rules.

Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards

cs.AI, q-bio.NC updates on arXiv.org

By: Xiaodong Lu · Xiaohan Wang · Jiajun Chai · Guojun Yin · Wei Lin · Zhijun Chen · Yu Luo · Fuzhen Zhuang · Yikun Ban · Deqing Wang

26 May 2026 at 12:00

arXiv:2602.08499v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is an effective paradigm for improving the reasoning capabilities of large language models. However, existing RLVR methods utilize rollouts in an indiscriminate and short-horizon manner: responses of heterogeneous quality within each prompt are treated uniformly, and historical rollouts are discarded after a single use. This leads to noisy supervision, poor sample efficiency, and suboptimal policy updates. We address these issues by formulating rollout scheduling in RLVR as a contextual bandit problem and proposing a unified neural scheduling framework that adaptively selects high-value rollouts throughout training. Each rollout is treated as an arm whose reward is defined by the induced performance gain between consecutive optimization steps. The resulting scheduler supports both noise-aware intra-group selection and adaptive global reuse of historical rollouts within a single principled framework. We provide theoretical justification by deriving sublinear regret bounds and showing that enlarging the rollout buffer improves the achievable performance upper bound. Experiments on six mathematical reasoning benchmarks demonstrate consistent gains in performance and training efficiency across multiple RLVR optimization methods.

ATP2B4 driven chromatin compaction exacerbates pancreatic cancer radiotherapy resistance

Cell Death Discovery nature.com science feeds

By: Yuyu Luo · Wei Jiang · Yanfang Liu · Qinghua Li · Yuanfei Chen · Shiwan Lin · Hsiang-i Tsai · Lirong Zhang · Dongqing Wang · Xiang Liao · Haitao Zhu

25 May 2026 at 08:00

Cell Death Discovery, Published online: 25 May 2026; doi:10.1038/s41420-026-03142-7

ATP2B4 driven chromatin compaction exacerbates pancreatic cancer radiotherapy resistance

Metformin suppresses β-cell apoptosis under ER stress by inhibiting protein translation

(Multiomics OR Omics) AND (Pancreatic)

By: Ryota Inoue · Kazuki Tajima · Tomoko Okuyama · Chisato Sakai · Tamaki Kanno · Meng Zou · Mayu Kyohara · Kohichi Matsunaga · Takahiro Tsuno · Junyu Luo · Emi Ishida · Shin-Ichi Horike · Tohko Hirano · Noriaki Arakawa · Tatsuya Kin · A M James Shapiro · Yasuo Terauchi · Hideru Obinata · Hisashi Hirano · Jun Shirakawa

10 April 2026 at 18:00

Metabolism. 2026 Apr 8:156607. doi: 10.1016/j.metabol.2026.156607. Online ahead of print.

ABSTRACT

Endoplasmic reticulum (ER) stress is a critical driver of pancreatic β-cell dysfunction and apoptosis. Although metformin, a drug used to treat type 2 diabetes, primarily decreases blood glucose levels by improving insulin sensitivity, its direct effects on β-cell survival remain unclear. Here, we investigated the effect of metformin on β-cell stress responses under ER stress conditions. Thapsigargin (Tg)-induced ER stress increased β-cell apoptosis in mouse islets, which was prevented by metformin in a dose-dependent manner. Treatment with metformin for 24 h suppressed the Tg-induced upregulation of unfolded protein response (UPR)-related genes, as confirmed by transcriptomic and pathway analyses. Quantitative proteomics revealed that Tg inhibited eIF2 signaling and protein translation, both of which were partially restored by metformin. Enrichment analysis further indicated the attenuation of apoptotic pathways in metformin-treated islets. Polysome profiling and puromycin incorporation assays demonstrated that metformin reduced protein translation independently of ER stress. Metformin promoted the dephosphorylation of 4E-BP1, a key initiator of cap-dependent protein translation that is activated by phosphorylation, and the antiapoptotic effect of metformin was abolished by 4E-BP1 knockdown in MIN6 cells. Phosphoproteomic analysis indicated that the activation of mTOR signaling, a kinase of 4E-BP1, in Tg-treated islets was mitigated by metformin. Taken together, these findings reveal a cytoprotective mechanism of metformin in β-cells, in which metformin suppresses ER stress-induced apoptosis through 4E-BP1-mediated inhibition of mRNA translation and modulation of mTOR signaling. This study highlights a β-cell-intrinsic action of metformin that may contribute to its long-term therapeutic benefits in diabetes management.

PMID:41962652 | DOI:10.1016/j.metabol.2026.156607

ATBench: A Diverse and Realistic Trajectory Benchmark for Long-Horizon Agent Safety

cs.AI, q-bio.NC updates on arXiv.org

By: Yu Li · Haoyu Luo · Yuejin Xie · Yuqian Fu · Zhonghao Yang · Shuai Shao · Qihan Ren · Wanying Qu · Yanwei Fu · Yujiu Yang · Jing Shao · Xia Hu · Dongrui Liu

3 April 2026 at 12:00

arXiv:2604.02022v1 Announce Type: new Abstract: Evaluating the safety of LLM-based agents is increasingly important because risks in realistic deployments often emerge over multi-step interactions rather than isolated prompts or final responses. Existing trajectory-level benchmarks remain limited by insufficient interaction diversity, coarse observability of safety failures, and weak long-horizon realism. We introduce ATBench, a trajectory-level benchmark for structured, diverse, and realistic evaluation of agent safety. ATBench organizes agentic risk along three dimensions: risk source, failure mode, and real-world harm. Based on this taxonomy, we construct trajectories with heterogeneous tool pools and a long-context delayed-trigger protocol that captures realistic risk emergence across multiple stages. The benchmark contains 1,000 trajectories (503 safe and 497 unsafe), averaging 9.01 turns and 3.95k tokens, with 1,954 invoked tools drawn from pools spanning 2,084 available tools. Data quality is supported by rule-based and LLM-based filtering plus full human audit. Experiments on frontier LLMs, open-source models, and specialized guard systems show that ATBench is challenging even for strong evaluators, while enabling taxonomy-stratified analysis, cross-benchmark comparison, and diagnosis of long-horizon failure patterns.

A Comprehensive Graph Pooling Benchmark: Effectiveness, Robustness and Generalizability

cs.AI, q-bio.NC updates on arXiv.org

By: Pengyun Wang · Junyu Luo · Yanxin Shen · Ming Zhang · Shaoen Qin · Hanwen Xing · Siyu Heng · Xiao Luo

3 April 2026 at 12:00

arXiv:2406.09031v5 Announce Type: replace-cross Abstract: Graph pooling has gained attention for its ability to obtain effective node and graph representations for various downstream tasks. Despite the recent surge in graph pooling approaches, there is a lack of standardized experimental settings and fair benchmarks to evaluate their performance. To address this issue, we have constructed a comprehensive benchmark that includes 17 graph pooling methods and 28 different graph datasets. This benchmark systematically assesses the performance of graph pooling methods in three dimensions, i.e., effectiveness, robustness, and generalizability. We first evaluate the performance of these graph pooling approaches across different tasks including graph classification, graph regression and node classification. Then, we investigate their performance under potential noise attacks and out-of-distribution shifts in real-world scenarios. We also involve detailed efficiency analysis, backbone analysis, parameter analysis and visualization to provide more evidence. Extensive experiments validate the strong capability and applicability of graph pooling approaches in various scenarios, which can provide valuable insights and guidance for deep geometric learning research. The source code of our benchmark is available at https://github.com/goose315/Graph_Pooling_Benchmark.

Long-Document QA with Chain-of-Structured-Thought and Fine-Tuned SLMs

cs.AI, q-bio.NC updates on arXiv.org

By: Zhuowen Liang · Xiaotian Lin · Zhengxuan Zhang · Yuyu Luo · Haixun Wang · Nan Tang

1 April 2026 at 12:00

arXiv:2603.29232v1 Announce Type: cross Abstract: Large language models (LLMs) are widely applied to data analytics over documents, yet direct reasoning over long, noisy documents remains brittle and error-prone. Hence, we study document question answering (QA) that consolidates dispersed evidence into a structured output (e.g., a table, graph, or chunks) to support reliable, verifiable QA. We propose a two-pillar framework, LiteCoST, to achieve both high accuracy and low latency with small language models (SLMs). Pillar 1: Chain-of-Structured-Thought (CoST). We introduce a CoST template, a schema-aware instruction that guides a strong LLM to produce both a step-wise CoST trace and the corresponding structured output. The process induces a minimal structure, normalizes entities/units, aligns records, serializes the output, and verifies/refines it, yielding auditable supervision. Pillar 2: SLM fine-tuning. The compact models are trained on LLM-generated CoST data in two stages: Supervised Fine-Tuning for structural alignment, followed by Group Relative Policy Optimization (GRPO) incorporating triple rewards for answer/format quality and process consistency. By distilling structure-first behavior into SLMs, this approach achieves LLM-comparable quality on multi-domain long-document QA using 3B/7B SLMs, while delivering 2-4x lower latency than GPT-4o and DeepSeek-R1 (671B). The code is available at https://github.com/HKUSTDial/LiteCoST.

Nanoscale transfer-printed full-colour ultrahigh-resolution quantum dot LEDs

Nature - Issue - nature.com science feeds

By: Lihua Lin · Jie Wang · Hailong Hu · Haolin Luo · Yanbin Liu · Xingjie Yang · Jingnan Su · De’er Li · Zhongwei Xu · Chengyu Luo · Yongshen Yu · Tailiang Guo · Fushan Li

1 April 2026 at 08:00

Nature, Published online: 01 April 2026; doi:10.1038/s41586-026-10333-w

A dual-action force dynamics strategy using a hard silicon template as a nanoimprinting stamp combined with inverted transfer printing is described for the manufacture of high-performance full-colour ultrahigh-resolution quantum dot light-emitting diodes (LEDs) for active-matrix displays, while revealing electric-field reconstruction in nanoscale arrays and introducing dielectric matching to mitigate field concentration and performance degradation.

Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System

cs.AI, q-bio.NC updates on arXiv.org

By: Xiang Zhang · Hongming Xu · Le Zhou · Wei Zhou · Xuanhe Zhou · Guoliang Li · Yuyu Luo · Changdong Liu · Guorun Chen · Jiang Liao · Fan Wu

10 March 2026 at 12:00

arXiv:2603.07449v1 Announce Type: cross Abstract: Enterprises commonly deploy heterogeneous database systems, each of which owns a distinct SQL dialect with different syntax rules, built-in functions, and execution constraints. However, most existing NL2SQL methods assume a single dialect (e.g., SQLite) and struggle to produce queries that are both semantically correct and executable on target engines. Prompt-based approaches tightly couple intent reasoning with dialect syntax, rule-based translators often degrade native operators into generic constructs, and multi-dialect fine-tuning suffers from cross-dialect interference. In this paper, we present Dial, a knowledge-grounded framework for dialect-specific NL2SQL. Dial introduces: (1) a Dialect-Aware Logical Query Planning module that converts natural language into a dialect-aware logical query plan via operator-level intent decomposition and divergence-aware specification; (2) HINT-KB, a hierarchical intent-aware knowledge base that organizes dialect knowledge into (i) a canonical syntax reference, (ii) a declarative function repository, and (iii) a procedural constraint repository; and (3) an execution-driven debugging and semantic verification loop that separates syntactic recovery from logic auditing to prevent semantic drift. We construct DS-NL2SQL, a benchmark covering six major database systems with 2,218 dialect-specific test cases. Experimental results show that Dial consistently improves translation accuracy by 10.25% and dialect feature coverage by 15.77% over state-of-the-art baselines. The code is at https://github.com/weAIDB/Dial.

Reading view