❌

Normal view

Received — 15 September 2026 ⏭

GTA: Graph Theory Agent and Benchmark for Algorithmic Graph Reasoning with LLMs

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zixiang Xu · Yanbo Wang · Chenxi Wang · Lang Gao · Zirui Song · Yue Huang · Zhaorun Chen · Xiangliang Zhang · Xiuying Chen
14 September 2026 at 12:00
arXiv:2609.12265v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly asked to reason over structured data such as graphs, yet how reliably they can carry out multi-step graph algorithms in language remains unclear. Existing evaluations tend to use simple tasks on small graphs, to score code generation rather than reasoning over the graph itself, or to fix a single input format. We introduce Graph Theory Bench (GT Bench), a benchmark covering 24 classical graph problems in 44 task-structure settings, with over 100,000 examples across four representations: natural language, structured language, adjacency list, and adjacency matrix. Evaluating eight LLMs on GT Bench shows that accuracy is strongly tied to the input representation, that the best representation shifts with graph density, size, and topology as well as with the model, and that this sensitivity persists, attenuated, in the strongest reasoning models. Building on these observations, we propose the Graph Theory Agent (GTA), which pairs a preference-trained representation selector with plan-and-decompose scaffolding around a frozen executor LLM. GTA lifts Phi-4 from 53.5% to 69.1% on the benchmark's easy split and from 33.0% to 41.5% on its hard split, outperforming eight prompting and agent baselines, and transfers without retraining to GraCoRe and NLGraph. Code for benchmark generation and evaluation: https://github.com/xzx34/GTA. The project homepage is available at https://xzx34.github.io/gta/.

AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhenyu Han · Ansheng You · Haibo Wang · Kui Luo · Guang Yang · Wenqi Shi · Menglong Chen · Sicheng Zhang · Zeshun Lan · Chunshi Deng · Huazhong Ji · Wenjie Liu · Yu Huang · Yixiang Zhang · Chenyi Pan · Jing Wang · Xin Huang · Chunsheng Li · Jianping Wu
14 September 2026 at 12:00
arXiv:2507.01663v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become a pivotal technology in the post-training phase of large language models (LLMs). Traditional task-collocated RL frameworks suffer from significant scalability bottlenecks, while task-separated RL frameworks face challenges in managing complex dataflows and resolving resource idling. Furthermore, most existing frameworks are tightly coupled with LLM training or inference engines, making them difficult to support custom-designed engines. To address these challenges, we propose AsyncFlow, an asynchronous streaming RL framework tailored for efficient post-training. Specifically, we introduce a distributed data storage and transfer module that provides panoramic data management and fine-grained scheduling capabilities in a fully streamed manner. This architecture inherently enables automated pipeline overlapping among RL tasks and dynamic load-balancing. Moreover, we propose an asynchronous producer-consumer workflow, which is engineered to minimize computational idleness by strategically deferring the parameter update process within staleness thresholds. Finally, the core capabilities of AsyncFlow are architecturally decoupled from underlying training and inference engines and encapsulated by service-oriented user interfaces, offering a modular and customizable user experience. Extensive experiments demonstrate an average throughput of 1.59x compared to the state-of-the-art baseline. The architecture presented in this work provides actionable insights for designing next-generation RL training systems.

Propionyl-CoA catabolism is a metabolic gatekeeper for fatty acid oxidation in pancreatic cancer

✇Oncogene - Issue - nature.com science feeds
By: Weidong Yu · Bo Wang · Fanhao Meng · Xiaojun Ren · Danyi Zhou · Huanxin Wei · Zhengquan Yang · Hongwei Sun · Minghua Jiang · Tao Xia · Wei Cui · Hezhi Fang
11 September 2026 at 08:00

Oncogene, Published online: 11 September 2026; doi:10.1038/s41388-026-03979-3

Propionyl-CoA catabolism is a metabolic gatekeeper for fatty acid oxidation in pancreatic cancer
Received — 13 September 2026 ⏭

Joint impact of pathological burden and cognitive resilience on Alzheimer’s disease risk

✇Nature Medicine
By: Zhibo Wang · Shuheng Wang · Yumei Liang · Xinlei Chen · Simiao Wang · Wei Qin · Qi Wang · Yan Li · Tan Zhao · Yue Wang · Fang Li · Guoguang Zhao · Jianping Jia
11 September 2026 at 08:00

Nature Medicine, Published online: 11 September 2026; doi:10.1038/s41591-026-04635-9

A 15-year cohort study shows that Alzheimer’s dementia risk is jointly shaped by Alzheimer’s pathology and cognitive resilience, with high resilience linked to lower risk, even under greater pathology.
Received — 10 September 2026 ⏭

MITF-SCD1 Lipid Metabolic Axis Prevents Ouabain-Induced Spiral Ganglion Neuron Ferroptosis and Hearing Loss

✇Molecular Therapy
By: Xue Wang · Fang Chen · Ziji Zhang · Man Zhang · Man Wang · Lei Chen · Anqi Suo · Xugang Zhuang · Tenghan Ling · Renjie Chai · Haibo Wang · Bo Chu · Lei Xu · Wenwen Liu
31 August 2026 at 08:00
Ouabain triggers cochlear spiral ganglion neuron (SGN) ferroptosis and hearing loss via SCD1 downregulation. MITF directly activates Scd1 transcription, and the MITF–SCD1 axis mitigates SGN ferroptosis and hearing impairment in ototoxic ouabain and cisplatin models, revealing a lipid metabolic vulnerability and therapeutic target for sensorineural hearing loss.
Received — 27 May 2026 ⏭

OrpQuant: Geometric Orthogonal Residual Projection for Multiplier-Free Power-of-Two Transformer Quantization

✇cs.AI, q-bio.NC updates on arXiv.org
By: Maoyang Xiang · Bo Wang · Tao Luo
26 May 2026 at 12:00
arXiv:2605.26092v1 Announce Type: cross Abstract: The deployment of Large Language Models (LLMs) and Vision Transformers (ViTs) on edge devices is significantly constrained by memory limitations and the critical timing bottlenecks introduced by dense Multiply-Accumulate (MAC) arrays. In the ultra-low bit regime, logarithmic Power-of-Two (PoT) quantization provides a hardware-efficient alternative by replacing MAC operations with bit-shifts. However, the non-uniform exponential lattice is inherently limited by a \textbf{Low Angular Resolution Regime}, a structural flaw that becomes particularly pronounced at sub-4-bit thresholds, leading to a notable degradation of high-dimensional feature manifolds. To address this geometric limitation, we propose Orthogonal Residual Projection (ORP), an algorithm-hardware co-design framework. By formulating quantization as a dual-basis geometric projection, ORP adaptively synthesizes a higher-resolution residual lattice using strictly shift-and-add operations. Furthermore, ORP's analytical solver offers a practical alternative to computationally intensive gradient-based optimization, reducing the full-model calibration time for LLaMA-2-7B to approximately \textbf{15 minutes}. Extensive evaluations demonstrate ORP's applicability across modalities and its hardware efficiency. Under the 3-bit (W3/A16) constraint, ORP achieves a perplexity of 6.10 on LLaMA-2-7B, comparing favorably to conventional MAC-intensive baselines like AWQ without relying on asymmetric scaling, while maintaining competitive accuracy in 4-bit scenarios. At the silicon level, standard-cell RTL synthesis at a 28nm node indicates that ORP effectively mitigates the timing bottlenecks associated with dense multiplier trees.

Rethinking the Comparison Unit in Sequence-Level Reinforcement Learning: An Equal-Length Paired Training Framework from Loss Correction to Sample Construction

✇cs.AI, q-bio.NC updates on arXiv.org
By: Fei Ding · Yongkang Zhang · Runhao Liu · Yuhao Liao · Zijian Zeng · Huiming Yang · Sibo wang · Linglin Liao
26 May 2026 at 12:00
arXiv:2604.17328v2 Announce Type: replace-cross Abstract: This paper investigates the length problem in sequence-level relative reinforcement learning. We observe that, although existing methods partially alleviate length-related phenomena, a more fundamental issue remains insufficiently characterized: the comparison units used during training lack inherent comparability. Building on this observation, we propose a new perspective: the length problem should not be viewed merely as a loss-scaling or normalization bias, but rather as a \emph{comparison unit construction} problem. We further establish a sample-construction-based training framework that, instead of applying post-hoc corrections to unequal-length responses, proactively constructs equal-length, alignable, and comparable training segments during generation. Within this framework, we propose EqLen, a concrete method applicable to group-relative comparison algorithms such as GRPO, GSPO, and RLOO. Through dual-track synchronous generation, prefix inheritance, and segment masking, EqLen efficiently collects effective equal-length training segments and enables stable

Internalizing Outcome Supervision into Process Supervision: A New Paradigm for Reinforcement Learning for Reasoning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Fei Ding · Yongkang Zhang · Runhao Liu · Yuhao Liao · Zijian Zeng · Sibo wang · Huiming Yang
26 May 2026 at 12:00
arXiv:2605.05226v2 Announce Type: replace-cross Abstract: The central challenge of reinforcement learning for reasoning lies not only in the sparsity of outcome-level supervision, but more fundamentally in how to transform feedback provided only at the end of a sequence into fine-grained learning signals that can guide intermediate reasoning steps. Existing approaches either rely on outcome-level rewards for sequence-level optimization, which makes precise credit assignment difficult, or depend on externally constructed process supervision, which is costly and difficult to scale sustainably. To address this, we propose a new perspective: reinforcement learning for reasoning can be understood as the problem of internalizing outcome supervision into process supervision. From this perspective, we introduce a supervision-internalization method for reinforcement learning for reasoning, enabling the model to automatically extract process-level learning signals through identifying, correcting, and reusing failed reasoning trajectories, thereby achieving finer-grained policy optimization under outcome-only supervision. We further abstract this idea into a new training paradigm, in which the model continually generates and refines its own internal process supervision during reinforcement learning, opening a new path for fine-grained credit assignment in reinforcement learning for reasoning that differs from externally provided process supervision.

Activation of methionine metabolism mediated by HNF4α confers ferroptosis resistance in hepatocellular carcinoma

✇Cell Death Discovery nature.com science feeds
By: Xiaolei Zhou · Zhenzhen Li · Libo Wang · Yongdeng Xu · Pinsheng Han · TianYu Zhao · Sen Liu · Liuyang Zhu · Miao Zhang · Chenglong Chu · Xiulin Yi · Fengying Yan · Tao Cui · Xiaoliang Wang · Ze Wang
26 May 2026 at 08:00

Cell Death Discovery, Published online: 26 May 2026; doi:10.1038/s41420-026-03165-0

Activation of methionine metabolism mediated by HNF4α confers ferroptosis resistance in hepatocellular carcinoma

Integrated single-cell and bulk RNA sequencing reveals novel biomarkers of invasive adenocarcinoma subtypes in lung adenocarcinoma

✇Pulmonary nodule
By: Xiaoming Wu · Xuxia Ye · Bo Wang · Zhoule Li · Chengnan Fang · Jian Xu · Mengli Wu
25 May 2026 at 18:00

Transl Cancer Res. 2026 Apr 30;15(4):314. doi: 10.21037/tcr-2025-aw-2503. Epub 2026 Mar 20.

ABSTRACT

BACKGROUND: Lung adenocarcinoma (LUAD) is one of the most common lung cancer subtypes worldwide, and its aggressive subtype invasive adenocarcinoma (IAC) has low survival rates. The precise identification of IAC is vital for the clinical diagnosis and treatment. The purpose of this study is to identify novel biomarkers for LUAD using single-cell and bulk RNA sequencing, so as to provide theoretical basis and practical support for the diagnosis, treatment and prognosis evaluation of lung invasive adenocarcinoma.

METHODS: We employed a combination of transcriptomic analysis and single-cell analysis to investigate the molecular characteristics and immune microenvironment of four subtypes of LUAD, including atypical adenomatous hyperplasia (AAH), adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), and IAC, with the aim of screening for biomarkers to differentiate pre-invasive lesions from invasive lesions.

RESULTS: Transcriptomic and single-cell analyses revealed that IAC subtypes demonstrated the most substantial molecular differences, particularly in immune cell infiltration and immune-related gene expression. Three genes-CD27, TIGIT, and TNFRSF18-that were significantly upregulated in IAC, predominantly expressed in immune cells and closely linked to immune regulatory pathways. We further analyzed T cell subpopulations in the IAC subtype and explored the expression of transcription factors (TFs) corresponding to these three genes, revealing their critical roles in immune cell function. Additionally, communication between T cells and other cells showed significantly enhanced signaling pathways, particularly those related to immune co-stimulatory molecules and inflammation pathways. Immunohistochemical validation of clinical samples showed that these three genes have high diagnostic value in IAC subtypes. These findings establish a crucial biological foundation for diagnosis, classification, and immunotherapy of LUAD, which contributes to the development of individualized treatment strategies.

CONCLUSIONS: This study identifies a three-gene signature (CD27, TIGIT, and TNFRSF18) that not only distinguishes invasive from pre-invasive LUAD with high precision by capturing the immune checkpoint disequilibrium characteristic of IAC, but also provides a clinically actionable biomarker panel for preoperative diagnosis and personalized immunotherapy strategies.

PMID:42180871 | PMC:PMC13190665 | DOI:10.21037/tcr-2025-aw-2503

Can China’s Great Green Wall shape efforts to keep the world’s deserts at bay?

✇Nature - Issue - nature.com science feeds
By: Lilin Zheng · Annah Lake Zhu · Qiuxia Dong · Michael E. Meadows · David S. G. Thomas · Xin Gao · Jiaojun Zhu · Xiaobo Wang · Zilong Xia · Alex De Sherbinin · Ruishan Chen
15 April 2026 at 08:00

Nature, Published online: 15 April 2026; doi:10.1038/d41586-026-01102-w

Grand anti-desertification schemes often fail when trees die and funding dries up — yet one project has broken the mould.
Received — 8 April 2026 ⏭

Can LLMs Learn to Reason Robustly under Noisy Supervision?

✇cs.AI, q-bio.NC updates on arXiv.org
By: Shenzhi Yang · Guangcheng Zhu · Bowen Song · Sharon Li · Haobo Wang · Xing Zheng · Yingfan Ma · Zhongqi Chen · Weiqiang Wang · Gang Chen
7 April 2026 at 12:00
arXiv:2604.03993v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) effectively trains reasoning models that rely on abundant perfect labels, but its vulnerability to unavoidable noisy labels due to expert scarcity remains critically underexplored. In this work, we take the first step toward a systematic analysis of noisy label mechanisms in RLVR. In contrast to supervised classification, most RLVR algorithms incorporate a rollout-based condition: a label's influence on training is contingent on whether the current policy can generate rollouts that realize it, a property that naturally extends to noisy labels. Based on this observation, we distinguish two types of noise: inactive noisy labels, which reduce data efficiency, and active noisy labels, which are reinforced and risk skewing the model toward incorrect distributions. From experiments on training with noisy samples, we identify an Early Correctness Coherence phenomenon: although noisy samples begin to lag behind in later stages, accuracy on both clean and noisy samples increases similarly in early training. Motivated by this dynamic, we propose Online Label Refinement (OLR), which progressively corrects potentially noisy labels with majority-voted answers when two conditions hold: a positive slope in the majority answer's rollout pass rate and stable historical consistency across updates, enabling gradual self-correction as the policy improves. We evaluate OLR on six in-distribution mathematical reasoning benchmarks (AIME24/25, AMC, MATH-500, Minerva, and Olympiad) and three out-of-distribution tasks (ARC-c, GPQA-diamond, and MMLU-pro). Across noise ratios from 0.1 to 0.9, OLR consistently improves robustness under both inactive and active noisy-label settings, achieving average gains of 3.6% to 3.9% on in-distribution benchmarks and 3.3% to 4.6% on out-of-distribution evaluations.

VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model

✇cs.AI, q-bio.NC updates on arXiv.org
By: Sibo Wang · Xiangkui Cao · Jie Zhang · Zheng Yuan · Shiguang Shan · Xilin Chen · Wen Gao
7 April 2026 at 12:00
arXiv:2406.14194v3 Announce Type: replace-cross Abstract: The emergence of Large Vision-Language Models (LVLMs) marks significant strides towards achieving general artificial intelligence. However, these advancements are accompanied by concerns about biased outputs, a challenge that has yet to be thoroughly explored. Existing benchmarks are not sufficiently comprehensive in evaluating biases due to their limited data scale, single questioning format and narrow sources of bias. To address this problem, we introduce VLBiasBench, a comprehensive benchmark designed to evaluate biases in LVLMs. VLBiasBench, features a dataset that covers nine distinct categories of social biases, including age, disability status, gender, nationality, physical appearance, race, religion, profession, social economic status, as well as two intersectional bias categories: race x gender and race x social economic status. To build a large-scale dataset, we use Stable Diffusion XL model to generate 46,848 high-quality images, which are combined with various questions to creat 128,342 samples. These questions are divided into open-ended and close-ended types, ensuring thorough consideration of bias sources and a comprehensive evaluation of LVLM biases from multiple perspectives. We conduct extensive evaluations on 15 open-source models as well as two advanced closed-source models, yielding new insights into the biases present in these models. Our benchmark is available at https://github.com/Xiangkui-Cao/VLBiasBench.
Received — 4 April 2026 ⏭

TRACE-Bot: Detecting Emerging LLM-Driven Social Bots via Implicit Semantic Representations and AIGC-Enhanced Behavioral Patterns

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhongbo Wang · Zhiyu Lin · Zhu Wang · Haizhou Wang
3 April 2026 at 12:00
arXiv:2604.02147v1 Announce Type: new Abstract: Large Language Model-driven (LLM-driven) social bots pose a growing threat to online discourse by generating human-like content that evades conventional detection. Existing methods suffer from limited detection accuracy due to overreliance on single-modality signals, insufficient sensitivity to the specific generative patterns of Artificial Intelligence-Generated Content (AIGC), and a failure to adequately model the interplay between linguistic patterns and behavioral dynamics. To address these limitations, we propose TRACE-Bot, a unified dual-channel framework that jointly models implicit semantic representations and AIGC-enhanced behavioral patterns. TRACE-Bot constructs fine-grained representations from heterogeneous sources, including personal information data, interaction behavior data and tweet data. A dual-channel architecture captures linguistic representations via a pretrained language model and behavioral irregularities via multidimensional activity features augmented with signals from state-of-the-art (SOTA) AIGC detectors. The fused representations are then classified through a lightweight prediction head. Experiments on two public LLM-driven social bot datasets demonstrate SOTA performance, achieving accuracies of 98.46% and 97.50%, respectively. The results further indicate strong robustness against advanced bot strategies, highlighting the effectiveness of jointly leveraging implicit semantic representations and AIGC-enhanced behavioral patterns for emerging LLM-driven social bot detection.

SHOE: Semantic HOI Open-Vocabulary Evaluation Metric

✇cs.AI, q-bio.NC updates on arXiv.org
By: Maja Noack · Qinqian Lei · Taipeng Tian · Bihan Dong · Robby T. Tan · Yixin Chen · John Young · Saijun Zhang · Bo Wang
3 April 2026 at 12:00
arXiv:2604.01586v1 Announce Type: cross Abstract: Open-vocabulary human-object interaction (HOI) detection is a step towards building scalable systems that generalize to unseen interactions in real-world scenarios and support grounded multimodal systems that reason about human-object relationships. However, standard evaluation metrics, such as mean Average Precision (mAP), treat HOI classes as discrete categorical labels and fail to credit semantically valid but lexically different predictions (e.g., "lean on couch" vs. "sit on couch"), limiting their applicability for evaluating open-vocabulary predictions that go beyond any predefined set of HOI labels. We introduce SHOE (Semantic HOI Open-Vocabulary Evaluation), a new evaluation framework that incorporates semantic similarity between predicted and ground-truth HOI labels. SHOE decomposes each HOI prediction into its verb and object components, estimates their semantic similarity using the average of multiple large language models (LLMs), and combines them into a similarity score to evaluate alignment beyond exact string match. This enables a flexible and scalable evaluation of both existing HOI detection methods and open-ended generative models using standard benchmarks such as HICO-DET. Experimental results show that SHOE scores align more closely with human judgments than existing metrics, including LLM-based and embedding-based baselines, achieving an agreement of 85.73% with the average human ratings. Our work underscores the need for semantically grounded HOI evaluation that better mirrors human understanding of interactions. We will release our evaluation metric to the public to facilitate future research.

Think, Act, Build: An Agentic Framework with Vision Language Models for Zero-Shot 3D Visual Grounding

✇cs.AI, q-bio.NC updates on arXiv.org
By: Haibo Wang · Zihao Lin · Zhiyang Xu · Lifu Huang
3 April 2026 at 12:00
arXiv:2604.00528v2 Announce Type: replace-cross Abstract: 3D Visual Grounding (3D-VG) aims to localize objects in 3D scenes via natural language descriptions. While recent advancements leveraging Vision-Language Models (VLMs) have explored zero-shot possibilities, they typically suffer from a static workflow relying on preprocessed 3D point clouds, essentially degrading grounding into proposal matching. To bypass this reliance, our core motivation is to decouple the task: leveraging 2D VLMs to resolve complex spatial semantics, while relying on deterministic multi-view geometry to instantiate the 3D structure. Driven by this insight, we propose "Think, Act, Build (TAB)", a dynamic agentic framework that reformulates 3D-VG tasks as a generative 2D-to-3D reconstruction paradigm operating directly on raw RGB-D streams. Specifically, guided by a specialized 3D-VG skill, our VLM agent dynamically invokes visual tools to track and reconstruct the target across 2D frames. Crucially, to overcome the multi-view coverage deficit caused by strict VLM semantic tracking, we introduce the Semantic-Anchored Geometric Expansion, a mechanism that first anchors the target in a reference video clip and then leverages multi-view geometry to propagate its spatial location across unobserved frames. This enables the agent to "Build" the target's 3D representation by aggregating these multi-view features via camera parameters, directly mapping 2D visual cues to 3D coordinates. Furthermore, to ensure rigorous assessment, we identify flaws such as reference ambiguity and category errors in existing benchmarks and manually refine the incorrect queries. Extensive experiments on ScanRefer and Nr3D demonstrate that our framework, relying entirely on open-source models, significantly outperforms previous zero-shot methods and even surpasses fully supervised baselines.

Do Phone-Use Agents Respect Your Privacy?

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhengyang Tang · Ke Ji · Xidong Wang · Zihan Ye · Xinyuan Wang · Yiduo Guo · Ziniu Li · Chenxin Li · Jingyuan Hu · Shunian Chen · Tongxu Luo · Jiaxi Bi · Zeyu Qin · Shaobo Wang · Xin Lai · Pengyuan Lyu · Junyi Li · Can Xu · Chengquan Zhang · Han Hu · Ming Yan · Benyou Wang
3 April 2026 at 12:00
arXiv:2604.00986v2 Announce Type: replace-cross Abstract: We study whether phone-use agents respect privacy while completing benign mobile tasks. This question has remained hard to answer because privacy-compliant behavior is not operationalized for phone-use agents, and ordinary apps do not reveal exactly what data agents type into which form entries during execution. To make this question measurable, we introduce MyPhoneBench, a verifiable evaluation framework for privacy behavior in mobile agents. We operationalize privacy-respecting phone use as permissioned access, minimal disclosure, and user-controlled memory through a minimal privacy contract, iMy, and pair it with instrumented mock apps plus rule-based auditing that make unnecessary permission requests, deceptive re-disclosure, and unnecessary form filling observable and reproducible. Across five frontier models on 10 mobile apps and 300 tasks, we find that task success, privacy-compliant task completion, and later-session use of saved preferences are distinct capabilities, and no single model dominates all three. Evaluating success and privacy jointly reshuffles the model ordering relative to either metric alone. The most persistent failure mode across models is simple data minimization: agents still fill optional personal entries that the task does not require. These results show that privacy failures arise from over-helpful execution of benign tasks, and that success-only evaluation overestimates the deployment readiness of current phone-use agents. All code, mock apps, and agent trajectories are publicly available at~ https://github.com/FreedomIntelligence/MyPhoneBench.
Received — 2 April 2026 ⏭

FlowPIE: Test-Time Scientific Idea Evolution with Flow-Guided Literature Exploration

✇cs.AI, q-bio.NC updates on arXiv.org
By: Qiyao Wang · Hongbo Wang · Longze Chen · Zhihao Yang · Guhong Chen · Hamid Alinejad-Rokny · Hui Li · Yuan Lin · Min Yang
1 April 2026 at 12:00
arXiv:2603.29557v1 Announce Type: new Abstract: Scientific idea generation (SIG) is critical to AI-driven autonomous research, yet existing approaches are often constrained by a static retrieval-then-generation paradigm, leading to homogeneous and insufficiently divergent ideas. In this work, we propose FlowPIE, a tightly coupled retrieval-generation framework that treats literature exploration and idea generation as a co-evolving process. FlowPIE expands literature trajectories via a flow-guided Monte Carlo Tree Search (MCTS) inspired by GFlowNets, using the quality of current ideas assessed by an LLM-based generative reward model (GRM) as a supervised signal to guide adaptive retrieval and construct a diverse, high-quality initial population. Based on this population, FlowPIE models idea generation as a test-time idea evolution process, applying selection, crossover, and mutation with the isolation island paradigm and GRM-based fitness computation to incorporate cross-domain knowledge. It effectively mitigates the information cocoons arising from over-reliance on parametric knowledge and static literature. Extensive evaluations demonstrate that FlowPIE consistently produces ideas with higher novelty, feasibility and diversity compared to strong LLM-based and agent-based frameworks, while enabling reward scaling during test time.

Owl-AuraID 1.0: An Intelligent System for Autonomous Scientific Instrumentation and Scientific Data Analysis

✇cs.AI, q-bio.NC updates on arXiv.org
By: Han Deng · Anqi Zou · Hanling Zhang · Ben Fei · Chengyu Zhang · Haobo Wang · Xinru Guo · Zhenyu Li · Xuzhu Wang · Peng Yang · Fujian Zhang · Weiyu Guo · Xiaohong Shao · Zhaoyang Liu · Shixiang Tang · Zhihui Wang · Wanli Ouyang
1 April 2026 at 12:00
arXiv:2603.29828v1 Announce Type: new Abstract: Scientific discovery increasingly depends on high-throughput characterization, yet automation is hindered by proprietary GUIs and the limited generalizability of existing API-based systems. We present Owl-AuraID, a software-hardware collaborative embodied agent system that adopts a GUI-native paradigm to operate instruments through the same interfaces as human experts. Its skill-centric framework integrates Type-1 (GUI operation) and Type-2 (data analysis) skills into end-to-end workflows, connecting physical sample handling with scientific interpretation. Owl-AuraID demonstrates broad coverage across ten categories of precision instruments and diverse workflows, including multimodal spectral analysis, microscopic imaging, and crystallographic analysis, supporting modalities such as FTIR, NMR, AFM, and TGA. Overall, Owl-AuraID provides a practical, extensible foundation for autonomous laboratories and illustrates a path toward evolving laboratory intelligence through reusable operational and analytical skills. The code are available at https://github.com/OpenOwlab/AuraID.
❌