❌

Normal view

Received today — 7 October 2026 ⏭

Two-dimensional materials for advanced back-end-of-line and wafer backside technologies

✇Nature Nanotechnology
By: Zhengpeng Wang · Jiechen Wang · Yue Cao · Hang-Ming Zhang · Yan Zeng · Sishuo Liu · Songqi Wang · Hehe Gong · Yuhao Zhang · Pingfan Wu · Liang Peng · Han Wang
17 September 2026 at 08:00

Nature Nanotechnology, Published online: 17 September 2026; doi:10.1038/s41565-026-02274-2

Two-dimensional materials offer low resistivity, strong thermal management and back-end-of-line compatibility, making them promising for advanced interconnects, backside power delivery and boosting efficiency in next-generation semiconductor chips.
Received — 10 September 2026 ⏭

Structured light–matter interaction in semiconductor cavity quantum electrodynamics

✇Nature Nanotechnology
By: Shunfa Liu · Jiantao Ma · Hanqing Liu · Yangpeng Wang · Xueshi Li · Haiqiao Ni · Zhichuan Niu · Kai Zou · Yun Meng · Xiaolong Hu · Xuehua Wang · Jin Liu
8 September 2026 at 08:00

Nature Nanotechnology, Published online: 08 September 2026; doi:10.1038/s41565-026-02275-1

Structured light–matter interaction at the single-photon level is demonstrated in a coupled quantum-dot–micropillar system, enabling cavity-enhanced single-photon emission with spin-locked orbital angular momentum and tunable spin–orbit entanglement.

From Monolithic Blending to Agentic Orchestration: Dynamic Response for Conversational Assistants at Scale

✇cs.AI, q-bio.NC updates on arXiv.org
By: Cen Mia Zhao · Peng Wang · Chuan Shi · Yufeng Zhang · Ying Lyu · Wanmeng Ren · Robert Xue · Claire Na Cheng · Yashar Mehdad
10 September 2026 at 12:00
arXiv:2609.05758v2 Announce Type: replace Abstract: Conversational assistants can blend retrieval, action selection, escalation, and wording in a single model path, or separate those roles. We report a production migration of a customer-support assistant at a large accommodation marketplace (millions of conversations per month, 11 languages, 10-second P90). Dynamic Response (DR) replaces a single Qwen3-235B-A22B blended responder with a bounded ReAct orchestrator over typed tools plus a smaller generator that writes from a backend-validated context contract. Because the migration also changed prompts, alignment, and serving, we attribute each effect to its cause and claim as architecture effects only those measured on identical replayed turns: typed entity selection moves the reservation selector to a precision-first operating point (precision 8.3% to 89.1%, recall 75.2% to 67.3%), and typed action IDs with a membership check remove observed structured-action hallucination (2.14% to 0.0%). A low-ramp A/B test reproduces the replay escalation reductions: hard-escalation responses fall from 5.60% to 3.08% and soft-escalation responses from 9.56% to 2.49%, while production handoff volume holds roughly steady; self-solve is directional (+5.1 points, 95% CI [-2, +12]). Serving optimizations cut orchestrator P90 latency from 3.87s to 2.24s on a GPU footprint reduced by roughly one-third, and self-hosting reduces estimated annual model-serving cost by more than an order of magnitude.
Received — 27 May 2026 ⏭

Low-Cost Labels, Reliable Choices: Rollout-Calibrated Hyper-Heuristics for Job Shop Scheduling

✇cs.AI, q-bio.NC updates on arXiv.org
By: Junhao Wei · Yanxiao Li · Yifu Zhao · Zhenhong Peng · Baili Lu · Dexing Yao · Haochen Li · Qinbin He · Sio-Kei Im · Yapeng Wang · Xu Yang
26 May 2026 at 12:00
arXiv:2605.23957v1 Announce Type: new Abstract: Learning-assisted hyper-heuristics can select among dispatching rules while preserving the feasibility and interpretability of constructive Job Shop Scheduling Problem (JSSP) heuristics. Their main computational cost lies in label generation rather than model fitting, since each supervised label usually requires rolling out candidate rules from a partial schedule. We study this label-cost problem together with a reliability problem: a learned selector should not switch away from a strong default rule unless the predicted gain is credible. The proposed selector uses regret-normalized rollout labels, a contextual KNN uncertainty estimate, and a gate that acts only when the predicted improvement exceeds an uncertainty-adjusted margin. We also vary rollout depth and breadth to measure the cost-quality trade-off. On synthetic JSSP instances, the gated selector achieves the lowest mean RPD among learned selectors, remains close to the best fixed dispatching rule, and reduces Random-HH mean RPD by more than an order of magnitude.

Iterative Refinement Neural Operators are Learned Fixed-Point Solvers: A Principled Approach to Spectral Bias Mitigation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xiaotian Liu · Shuyuan Shang · Xiaopeng Wang · Pu Ren · Yaoqing Yang
26 May 2026 at 12:00
arXiv:2605.24041v2 Announce Type: cross Abstract: Neural operators serve as fast, data-driven surrogates for scientific modeling but typically rely on a monolithic, single-pass inference procedure that struggles to resolve high-frequency details, a limitation known as spectral bias. We introduce the Iterative Refinement Neural Operator (IRNO), which augments pre-trained operators with a learned refinement module iteratively applied via fixed-point iteration. IRNO decomposes the prediction into a coarse initialization followed by successive residual corrections, paralleling classical numerical solvers. Under local assumptions, we establish contraction of the induced operator, ensuring convergence to a unique fixed point. To explicitly target high-frequency errors, we propose a progressive spectral loss that adaptively increases penalty on high-frequency components over refinement steps during training. Across physical systems, IRNO consistently lowers error, with up to 56.05% improvement on turbulent flow. On Active Matter, spectral analysis reveals that, relative to base operator, the normalized error ratios decrease to 27.72-36.10% in low-, 5.07-6.68% in mid-, and 1.48-2.04% in high-frequencies, remaining stable beyond the trained iteration count. Code is available at https://github.com/xiaotianliu-dartmouth/Iterative_Refinement_Neural_Operator

Copper depletion boosts CNS leukemia therapy by inhibiting nucleotide synthesis through impairment of mitochondrial complex IV activity

✇Nature Cancer
By: Alan Y. L. Wong · Jacob W. Myers · Gyan Prakash · Alice Ma · Jeannette R. Brook · Boryana Petrova · Baran Bulut · Ralph White III · Catherine Merz · Maeve de Souza · Adam G. Maynard · Peng Wang · Amy Yu · Nancy K. Pohl · Michal Weitman · Lewis B. Silverman · Kimberly Stegmaier · L. Stirling Churchman · Peter D. Cole · Donita C. Brady · Naama Kanarek
25 May 2026 at 08:00

Nature Cancer, Published online: 25 May 2026; doi:10.1038/s43018-026-01177-4

Wong et al. uncover a nutritional dependency for acute lymphoblastic leukemia cells that spread to the central nervous system and propose using copper restriction to impair leukemia progression by disrupting nucleotide synthesis through the inhibition of electron transport chain activity.
Received — 2 April 2026 ⏭

PromptForge-350k: A Large-Scale Dataset and Contrastive Framework for Prompt-Based AI Image Forgery Localization

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jianpeng Wang · Haoyu Wang · Baoying Chen · Jishen Zeng · Yiming Qin · Yiqi Yang · Zhongjie Ba
1 April 2026 at 12:00
arXiv:2603.29386v1 Announce Type: cross Abstract: The rapid democratization of prompt-based AI image editing has recently exacerbated the risks associated with malicious content fabrication and misinformation. However, forgery localization methods targeting these emerging editing techniques remain significantly under-explored. To bridge this gap, we first introduce a fully automated mask annotating framework that leverages keypoint alignment and semantic space similarity to generate precise ground-truth masks for edited regions. Based on this framework, we construct PromptForge-350k, a large-scale forgery localization dataset covering four state-of-the-art prompt-based AI image editing models, thereby mitigating the data scarcity in this domain. Furthermore, we propose ICL-Net, an effective forgery localization network featuring a triple-stream backbone and intra-image contrastive learning. This design enables the model to capture highly robust and generalizable forensic features. Extensive experiments demonstrate that our method achieves an IoU of 62.5% on PromptForge-350k, outperforming SOTA methods by 5.1%. Additionally, it exhibits strong robustness against common degradations with an IoU drop of less than 1%, and shows promising generalization capabilities on unseen editing models, achieving an average IoU of 41.5%.

Hallucination-aware intermediate representation edit in large vision-language models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Wei Suo · Hanzu Zhang · Lijun Zhang · Ji Ma · Peng Wang · Yanning Zhang
1 April 2026 at 12:00
arXiv:2603.29405v1 Announce Type: cross Abstract: Large Vision-Language Models have demonstrated exceptional performance in multimodal reasoning and complex scene understanding. However, these models still face significant hallucination issues, where outputs contradict visual facts. Recent research on hallucination mitigation has focused on retraining methods and Contrastive Decoding (CD) methods. While both methods perform well, retraining methods require substantial training resources, and CD methods introduce dual inference overhead. These factors hinder their practical applicability. To address the above issue, we propose a framework for dynamically detecting hallucination representations and performing hallucination-eliminating edits on these representations. With minimal additional computational cost, we achieve state-of-the-art performance on existing benchmarks. Extensive experiments demonstrate the effectiveness of our approach, highlighting its efficient and robust hallucination elimination capability and its powerful controllability over hallucinations. Code is available at https://github.com/ASGO-MM/HIRE
Received — 26 March 2026 ⏭

Low-dose intestinal irradiation enhances the efficacy and prognosis of PD-1 blockade in metastatic non-small cell lung cancer

✇Omics In Lung
By: Baiyang Huang · Jiarui Zhao · Jingyu Zhu · Xingpeng Wang · Min Li · Jing Xu · Kaiyue Wang · Xiaohan Wang · Weiqing Wang · Cong Bo · Jinquan Yao · Menglin Bai · Bo Cheng · Jinming Yu · Guoxin Cai · Xue Meng
18 March 2026 at 18:00

Clin Cancer Res. 2026 Mar 18. doi: 10.1158/1078-0432.CCR-25-4153. Online ahead of print.

ABSTRACT

PURPOSE: Intestinal low-dose irradiation (ILDR) may enhance immunotherapy efficacy by modulating the gut microbiota and metabolism; however, its role in metastatic non-small cell lung cancer (mNSCLC), particularly in the first-line setting, remains unclear.

EXPERIMENTAL DESIGN: This multicenter retrospective and prospective study included mNSCLC patients receiving first- and second-line programmed cell death protein 1 (PD-1) inhibitors along with abdominopelvic radiotherapy between 2018 and 2025. Patients were stratified by the mean intestinal radiation dose into <1 Gy, 1-3 Gy, and >3 Gy groups and treatment outcomes were compared. The blood and fecal samples were subjected to multi-omics profiling.

RESULTS: g>309 patients were included in the retrospective analysis. Optimal efficacy was observed with a small intestinal mean radiation dose (SIMRD) of 1-3 Gy, showing longer progression-free survival (PFS, 10.2 months) and overall survival (OS, 22.8 months) (P < 0.01), which was consistent across subgroups. Compared with 1-3 Gy, SIMRD >3 Gy (Hazard ratio [HR] = 4.87, P < 0.001) and <1 Gy (HR = 1.85, P < 0.001) independently predicted worse OS. Prospective results confirmed the best disease control rate (P = 0.041) and PFS (P = 0.046) with SIMRD of 1-3 Gy. Responders were enriched in Bacillota, Clostridia, and indole derivatives, particularly indole-3-carboxylic acid. Moreover, the 1-3 Gy group exhibited increased circulating macrophage inflammatory protein-3α and reduced circulating α4β7+ regulatory T cells.

CONCLUSIONS: ILDR influences the efficacy of PD-1 blockade in patients with mNSCLC, particularly when SIMRD is maintained within the 1-3 Gy range, likely through modulation of the gut microbiota-metabolite-immune axis.

PMID:41849236 | DOI:10.1158/1078-0432.CCR-25-4153

Received — 17 March 2026 ⏭

Efficient and Interpretable Multi-Agent LLM Routing via Ant Colony Optimization

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xudong Wang · Chaoning Zhang · Jiaquan Zhang · Chenghao Li · Qigan Sun · Sung-Ho Bae · Peng Wang · Ning Xie · Jie Zou · Yang Yang · Hengtao Shen
16 March 2026 at 12:00
arXiv:2603.12933v1 Announce Type: new Abstract: Large Language Model (LLM)-driven Multi-Agent Systems (MAS) have demonstrated strong capability in complex reasoning and tool use, and heterogeneous agent pools further broaden the quality--cost trade-off space. Despite these advances, real-world deployment is often constrained by high inference cost, latency, and limited transparency, which hinders scalable and efficient routing. Existing routing strategies typically rely on expensive LLM-based selectors or static policies, and offer limited controllability for semantic-aware routing under dynamic loads and mixed intents, often resulting in unstable performance and inefficient resource utilization. To address these limitations, we propose AMRO-S, an efficient and interpretable routing framework for Multi-Agent Systems (MAS). AMRO-S models MAS routing as a semantic-conditioned path selection problem, enhancing routing performance through three key mechanisms: First, it leverages a supervised fine-tuned (SFT) small language model for intent inference, providing a low-overhead semantic interface for each query; second, it decomposes routing memory into task-specific pheromone specialists, reducing cross-task interference and optimizing path selection under mixed workloads; finally, it employs a quality-gated asynchronous update mechanism to decouple inference from learning, optimizing routing without increasing latency. Extensive experiments on five public benchmarks and high-concurrency stress tests demonstrate that AMRO-S consistently improves the quality--cost trade-off over strong routing baselines, while providing traceable routing evidence through structured pheromone patterns.
Received — 11 March 2026 ⏭

Not all tokens are needed(NAT): token efficient reinforcement learning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Hejian Sang · Yuanda Xu · Zhengze Zhou · Ran He · Zhipeng Wang
10 March 2026 at 12:00
arXiv:2603.06619v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a key driver of progress in large language models, but scaling RL to long chain-of-thought (CoT) trajectories is increasingly constrained by backpropagation over every generated token. Even with optimized rollout engines, full-token updates can consume a large fraction of total training cost, turning token length into a hidden tax on RL. We introduce Not All Tokens Are Needed (NAT), a unified framework that makes the token budget a first-class optimization primitive. NAT updates the policy using only a selected subset of generated tokens while preserving the learning signal of full-sequence RL. The core idea is an unbiased partial-token policy-gradient estimator via Horvitz-Thompson reweighting, which ensures statistically correct gradients despite subsampling. We instantiate NAT with two simple, plug-and-play token selection schemes: Uniform Random Sampling (URS) and Random Prefix Cutting (RPC), both of which reduce forward and backward compute and memory without modifying the reward computation or rollout pipeline. Across mathematical reasoning benchmarks, NAT matches full-token GRPO performance while using as few as 50% of tokens, providing an efficient and orthogonal pathway to scaling RL beyond the limits imposed by long trajectories. In our experiments, RPC saves 18% peak GPU memory and 29% forward and backward RL training time for Qwen3-8B.

Arginine methylation-dependent stabilization of SUV39H1 promotes breast cancer growth

✇Oncogene - Issue - nature.com science feeds
By: Wei Zhao · Ge Wang · Peng Wang · Bo Ma · Bo Liu · Yenan Fu · Youzhi Tang · Xinwei Duan · Kunhao Zhou · Jing Zhang · Wei-Guo Zhu · Hongquan Zhang · Yu Yu
7 March 2026 at 08:00

Oncogene, Published online: 07 March 2026; doi:10.1038/s41388-026-03712-0

Arginine methylation-dependent stabilization of SUV39H1 promotes breast cancer growth
Received — 5 March 2026 ⏭

AriadneMem: Threading the Maze of Lifelong Memory for LLM Agents

✇cs.AI, q-bio.NC updates on arXiv.org
By: Wenhui Zhu · Xiwen Chen · Zhipeng Wang · Jingjing Wang · Xuanzhao Dong · Minzhou Huang · Rui Cai · Hejian Sang · Hao Wang · Peijie Qiu · Yueyue Deng · Prayag Tiwari · Brendan Hogan Rappazzo · Yalin Wang
5 March 2026 at 13:00
arXiv:2603.03290v1 Announce Type: cross Abstract: Long-horizon LLM agents require memory systems that remain accurate under fixed context budgets. However, existing systems struggle with two persistent challenges in long-term dialogue: (i) \textbf{disconnected evidence}, where multi-hop answers require linking facts distributed across time, and (ii) \textbf{state updates}, where evolving information (e.g., schedule changes) creates conflicts with older static logs. We propose AriadneMem, a structured memory system that addresses these failure modes via a decoupled two-phase pipeline. In the \textbf{offline construction phase}, AriadneMem employs \emph{entropy-aware gating} to filter noise and low-information message before LLM extraction and applies \emph{conflict-aware coarsening} to merge static duplicates while preserving state transitions as temporal edges. In the \textbf{online reasoning phase}, rather than relying on expensive iterative planning, AriadneMem executes \emph{algorithmic bridge discovery} to reconstruct missing logical paths between retrieved facts, followed by \emph{single-call topology-aware synthesis}. On LoCoMo experiments with GPT-4o, AriadneMem improves \textbf{Multi-Hop F1 by 15.2\%} and \textbf{Average F1 by 9.0\%} over strong baselines. Crucially, by offloading reasoning to the graph layer, AriadneMem reduces \textbf{total runtime by 77.8\%} using only \textbf{497} context tokens. The code is available at https://github.com/LLM-VLM-GSL/AriadneMem.

From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Ruilin Luo · Chufan Shi · Yizhen Zhang · Cheng Yang · Songtao Jiang · Tongkun Guan · Ruizhe Chen · Ruihang Chu · Peng Wang · Mingkun Yang · Yujiu Yang · Junyang Lin · Zhibo Yang
5 March 2026 at 13:00
arXiv:2603.03825v1 Announce Type: cross Abstract: The cold-start initialization stage plays a pivotal role in training Multimodal Large Reasoning Models (MLRMs), yet its mechanisms remain insufficiently understood. To analyze this stage, we introduce the Visual Attention Score (VAS), an attention-based metric that quantifies how much a model attends to visual tokens. We find that reasoning performance is strongly correlated with VAS (r=0.9616): models with higher VAS achieve substantially stronger multimodal reasoning. Surprisingly, multimodal cold-start fails to elevate VAS, resulting in attention distributions close to the base model, whereas text-only cold-start leads to a clear increase. We term this counter-intuitive phenomenon Lazy Attention Localization. To validate its causal role, we design training-free interventions that directly modulate attention allocation during inference, performance gains of 1$-$2% without any retraining. Building on these insights, we further propose Attention-Guided Visual Anchoring and Reflection (AVAR), a comprehensive cold-start framework that integrates visual-anchored data synthesis, attention-guided objectives, and visual-anchored reward shaping. Applied to Qwen2.5-VL-7B, AVAR achieves an average gain of 7.0% across 7 multimodal reasoning benchmarks. Ablation studies further confirm that each component of AVAR contributes step-wise to the overall gains. The code, data, and models are available at https://github.com/lrlbbzl/Qwen-AVAR.

SpotIt+: Verification-based Text-to-SQL Evaluation with Database Constraints

✇cs.AI, q-bio.NC updates on arXiv.org
By: Rocky Klopfenstein · Yang He · Andrew Tremante · Yuepeng Wang · Nina Narodytska · Haoze Wu
5 March 2026 at 13:00
arXiv:2603.04334v1 Announce Type: cross Abstract: We present SpotIt+, an open-source tool for evaluating Text-to-SQL systems via bounded equivalence verification. Given a generated SQL query and the ground truth, SpotIt+ actively searches for database instances that differentiate the two queries. To ensure that the generated counterexamples reflect practically relevant discrepancies, we introduce a constraint-mining pipeline that combines rule-based specification mining over example databases with LLM-based validation. Experimental results on the BIRD dataset show that the mined constraints enable SpotIt+ to generate more realistic differentiating databases, while preserving its ability to efficiently uncover numerous discrepancies between generated and gold SQL queries that are missed by standard test-based evaluation.

SpotIt: Evaluating Text-to-SQL Evaluation with Formal Verification

✇cs.AI, q-bio.NC updates on arXiv.org
By: Rocky Klopfenstein · Yang He · Andrew Tremante · Yuepeng Wang · Nina Narodytska · Haoze Wu
5 March 2026 at 13:00
arXiv:2510.26840v2 Announce Type: replace-cross Abstract: Community-driven Text-to-SQL evaluation platforms play a pivotal role in tracking the state of the art of Text-to-SQL performance. The reliability of the evaluation process is critical for driving progress in the field. Current evaluation methods are largely test-based, which involves comparing the execution results of a generated SQL query and a human-labeled ground-truth on a static test database. Such an evaluation is optimistic, as two queries can coincidentally produce the same output on the test database while actually being different. In this work, we propose a new alternative evaluation pipeline, called SpotIt, where a formal bounded equivalence verification engine actively searches for a database that differentiates the generated and ground-truth SQL queries. We develop techniques to extend existing verifiers to support a richer SQL subset relevant to Text-to-SQL. A performance evaluation of ten Text-to-SQL methods on the high-profile BIRD dataset suggests that test-based methods can often overlook differences between the generated query and the ground-truth. Further analysis of the verification results reveals a more complex picture of the current Text-to-SQL evaluation.
Received — 25 February 2026 ⏭

FUSAR-GPT : A Spatiotemporal Feature-Embedded and Two-Stage Decoupled Visual Language Model for SAR Imagery

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xiaokun Zhang · Yi Yang · Ziqi Ye · Baiyun · Xiaorong Guo · Qingchen Fang · Ruyi Zhang · Xinpeng Zhou · Haipeng Wang
24 February 2026 at 13:00
arXiv:2602.19190v1 Announce Type: cross Abstract: Research on the intelligent interpretation of all-weather, all-time Synthetic Aperture Radar (SAR) is crucial for advancing remote sensing applications. In recent years, although Visual Language Models (VLMs) have demonstrated strong open-world understanding capabilities on RGB images, their performance is severely limited when directly applied to the SAR field due to the complexity of the imaging mechanism, sensitivity to scattering features, and the scarcity of high-quality text corpora. To systematically address this issue, we constructed the inaugural SAR Image-Text-AlphaEarth feature triplet dataset and developed FUSAR-GPT, a VLM specifically for SAR. FUSAR-GPT innovatively introduces a geospatial baseline model as a 'world knowledge' prior and embeds multi-source remote-sensing temporal features into the model's visual backbone via 'spatiotemporal anchors', enabling dynamic compensation for the sparse representation of targets in SAR images. Furthermore, we designed a two-stage SFT strategy to decouple the knowledge injection and task execution of large models. The spatiotemporal feature embedding and the two-stage decoupling paradigm enable FUSAR-GPT to achieve state-of-the-art performance across several typical remote sensing visual-language benchmark tests, significantly outperforming mainstream baseline models by over 12%.

Evaluating LLMs' Divergent Thinking Capabilities for Scientific Idea Generation with Minimal Context

✇cs.AI, q-bio.NC updates on arXiv.org
By: Kai Ruan · Xuan Wang · Jixiang Hong · Peng Wang · Yang Liu · Hao Sun
24 February 2026 at 13:00
arXiv:2412.17596v4 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) demonstrate remarkable capabilities in scientific tasks such as literature analysis and experimental design (e.g., accurately extracting key findings from papers or generating coherent experimental procedures), existing evaluation benchmarks primarily assess performance using rich contextual inputs. We introduce LiveIdeaBench, a comprehensive benchmark evaluating LLMs' scientific idea generation by assessing divergent thinking capabilities using single-keyword prompts. Drawing from Guilford's creativity theory, our benchmark employs a dynamic panel of state-of-the-art LLMs to assess generated ideas across five key dimensions: originality, feasibility, fluency, flexibility, and clarity. Through extensive experimentation with over 40 leading models across 1,180 keywords spanning 22 scientific domains, we reveal that the scientific idea generation capabilities measured by our benchmark, are poorly predicted by standard metrics of general intelligence. Our results demonstrate that models like QwQ-32B-preview achieve creative performance comparable to top-tier models such as claude-3.7-sonnet:thinking, despite significant gaps in their general intelligence scores. These findings highlight the need for specialized evaluation benchmarks for scientific idea generation and suggest that enhancing these idea generation capabilities in LLMs may require different training strategies than those used for improving general problem-solving abilities, potentially enabling a wider range of AI tools tailored for different stages of the scientific process.
Received — 17 February 2026 ⏭

RV-Syn: Rational and Verifiable Mathematical Reasoning Data Synthesis based on Structured Function Library

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jiapeng Wang · Jinhao Jiang · Zhiqiang Zhang · Jun Zhou · Wayne Xin Zhao
17 February 2026 at 13:00
arXiv:2504.20426v3 Announce Type: replace Abstract: The advancement of reasoning capabilities in Large Language Models (LLMs) requires substantial amounts of high-quality reasoning data, particularly in mathematics. Existing data synthesis methods, such as data augmentation from annotated training sets or direct question generation based on relevant knowledge points and documents, have expanded datasets but face challenges in mastering the inner logic of the problem during generation and ensuring the verifiability of the solutions. To address these issues, we propose RV-Syn, a novel Rational and Verifiable mathematical Synthesis approach. RV-Syn constructs a structured mathematical operation function library based on initial seed problems and generates computational graphs as solutions by combining Python-formatted functions from this library. These graphs are then back-translated into complex problems. Based on the constructed computation graph, we achieve solution-guided logic-aware problem generation. Furthermore, the executability of the computational graph ensures the verifiability of the solving process. Experimental results show that RV-Syn surpasses existing synthesis methods, including those involving human-generated problems, achieving greater efficient data scaling. This approach provides a scalable framework for generating high-quality reasoning datasets.
There are no more articles
❌