❌

Normal view

Received β€” 15 September 2026 ⏭

GraphAHA: Graph-Based Adaptive Search with Heterogeneous Actions for Test-Time Code Generation

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Xitao Li Β· Haijun Wang Β· Gege Yuan Β· Qiyuan Wu Β· Jiali Wei Β· Ming Fan Β· Xiaofei Xie
14 September 2026 at 12:00
arXiv:2609.12757v1 Announce Type: cross Abstract: Test-time scaling improves code generation by spending additional inference budget (e.g., calls or tokens) on direct sampling, feedback-conditioned repair, and reasoning-guided implementation. Search-based methods can allocate this budget adaptively, but two challenges remain. First, tree-structured search treats each generation history as a separate state even when trajectories converge to the same program, duplicating evaluation and preventing statistics from being shared. Second, sampling, repair, and reasoning have complementary and state-dependent payoffs, making online allocation among them difficult under a finite budget. To address these challenges, we propose an adaptive graph search method with heterogeneous actions (GraphAHA). GraphAHA organizes the test-time code generation in a typed directed acyclic graph. Equivalent programs are merged into a single code node, allowing their downstream search statistics to be reused across all discovery paths. Hierarchical Thompson sampling then selects whether to generate a new state or follow an existing successor and, for generation, chooses among the type-valid sampling, reasoning, implementation, and repair operations. Evaluated on LiveCodeBench and CodeContests with Qwen2.5-Coder and DeepSeek-Coder, GraphAHA achieves the best score in 18 of 20 cases. For Pass@1 measured using visible tests, it outperforms the strongest baseline for both models on both benchmarks by 4.1 percentage points on average, demonstrating more effective use of a fixed inference budget.
Received β€” 27 May 2026 ⏭

Mendelian Randomization Analysis of the Relationship between Neurotransmitter-related Genes and Cancer: Insights from Multi-omics Data

βœ‡(Multiomics OR Omics) AND (Pancreatic)
By: Quan Yuan Β· Yuli Xi Β· Hao Yu Β· Rongjie Ye Β· Neng Wang Β· Ge Yu Β· Ming Niu
21 May 2026 at 18:00

Curr Top Med Chem. 2026 May 18. doi: 10.2174/0115680266436608260406113212. Online ahead of print.

ABSTRACT

INTRODUCTION: Epidemiological studies indicate a potential link between mental disorders and cancer; however, the role of neurotransmitter-related genes (NRGs) in carcinogenesis remains unclear. In this study, we employed Mendelian randomization utilizing multi-omics data to investigate the causal effects and mechanisms of NRGs in cancer.

METHODS: We assessed the causal relationships between ten mental disorders and fourteen cancer types. NRGs were sourced from GeneCards, and transcriptome data for breast cancer (BC) were obtained from the Gene Expression Omnibus (GEO). Summary-data-based Mendelian Randomization (SMR) integrated genome-wide association study (GWAS) data with expression quantitative trait loci (eQTLs), DNA methylation QTLs (mQTLs), intestinal eQTLs, and fecal microbiota QTLs (mbQTLs). Colocalization analyses were conducted to explore the relationships between host genes and gut microbiota, with sensitivity assessments performed using two additional Mendelian randomization methods.

RESULTS: Mendelian randomization confirmed a causal association between mental disorders and BC. A meta-analysis of five BC datasets identified 821 differentially expressed genes (DEGs) among 829 non-redundant genes. SMR highlighted KRTCAP2 as a potential causal gene in blood, and cg24674445 as a significant methylation site. The expression of KRTCAP2 was found to be inversely correlated with BC, while methylation at cg24674445 downregulated KRTCAP2, suggesting that cg24674445 may promote BC progression.

DISCUSSION: This study advances beyond established epidemiological correlations by providing genetically validated evidence for a causal link between mental disorders and breast cancer. Its primary significance lies in delineating a plausible biological pathway-epigenetic regulation of neurotransmitter-related genes-that may mechanistically elucidate this connection. By integrating multi-omics data, we transition from mere association to a testable model of disease etiology, where genetic predispositions to mental illness and cancer converge upon shared regulatory mechanisms within the genome.

CONCLUSION: Multi-omics Mendelian randomization demonstrates that DNA methylation modulates the association between neurotransmitter-related genes and breast cancer.

PMID:42163732 | DOI:10.2174/0115680266436608260406113212

Received β€” 4 April 2026 ⏭
Received β€” 25 February 2026 ⏭

AdaWorldPolicy: World-Model-Driven Diffusion Policy with Online Adaptive Learning for Robotic Manipulation

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Ge Yuan Β· Qiyuan Qiao Β· Jing Zhang Β· Dong Xu
24 February 2026 at 13:00
arXiv:2602.20057v1 Announce Type: cross Abstract: Effective robotic manipulation requires policies that can anticipate physical outcomes and adapt to real-world environments. Effective robotic manipulation requires policies that can anticipate physical outcomes and adapt to real-world environments. In this work, we introduce a unified framework, World-Model-Driven Diffusion Policy with Online Adaptive Learning (AdaWorldPolicy) to enhance robotic manipulation under dynamic conditions with minimal human involvement. Our core insight is that world models provide strong supervision signals, enabling online adaptive learning in dynamic environments, which can be complemented by force-torque feedback to mitigate dynamic force shifts. Our AdaWorldPolicy integrates a world model, an action expert, and a force predictor-all implemented as interconnected Flow Matching Diffusion Transformers (DiT). They are interconnected via the multi-modal self-attention layers, enabling deep feature exchange for joint learning while preserving their distinct modularity characteristics. We further propose a novel Online Adaptive Learning (AdaOL) strategy that dynamically switches between an Action Generation mode and a Future Imagination mode to drive reactive updates across all three modules. This creates a powerful closed-loop mechanism that adapts to both visual and physical domain shifts with minimal overhead. Across a suite of simulated and real-robot benchmarks, our AdaWorldPolicy achieves state-of-the-art performance, with dynamical adaptive capacity to out-of-distribution scenarios.
There are no more articles
❌