❌

Normal view

Received — 10 September 2026 ⏭

Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Lin Shi (Audrey) · Haowei Lin (Audrey) · Zixuan Zhu (Audrey) · Xiaoyue Zhou (Audrey) · Xiang Li (Audrey) · Xiangning Lin (Audrey) · Yaxuan Deng (Audrey) · Han Xu (Audrey) · Yuangang Li (Audrey) · Shanda Li (Audrey) · Zizhao Chen (Audrey) · Hanwen Xing (Audrey) · Harsh Raj (Audrey) · Bo Chen (Audrey) · Quan Shi (Audrey) · Steven Dillmann (Audrey) · Yipeng Gao (Audrey) · Puneesh Khanna (Audrey) · Ruofan Lu (Audrey) · Chao Beyond Zhou (Audrey) · Michael Yang (Audrey) · Robert Zhang (Audrey) · Siyuan Chai (Audrey) · Jiayu Chang (Audrey) · Yizhao Chen (Audrey) · Xiaokun Chen (Audrey) · Yiwei Dai (Audrey) · Wenting Yang (Audrey) · Hange Liu (Audrey) · Minghao Liu (Audrey) · Zihan Wang (Audrey) · Adnan El Assadi (Audrey) · Benedikt Stroebl (Audrey) · E. Kelly Buchanan (Audrey) · Han Meng (Audrey) · Junwei He (Audrey) · Longxuan Yu (Audrey) · Radin Shayanfar (Audrey) · Yukyung Lee (Audrey) · Zhikang Dong (Audrey) · Allen G Hart (Audrey) · Anjiang Wei (Audrey) · Anurag Kashyap (Audrey) · Arpandeep Khatua (Audrey) · Audrey Jixin Zheng (Audrey) · Chengrui Ma (Aud
10 September 2026 at 12:00
arXiv:2609.04298v2 Announce Type: replace Abstract: Evaluating agents on the growing number of agentic benchmarks is challenging because they often require complex environments and agent integrations. We introduce Harbor Adapters, a unified evaluation infrastructure for agentic benchmarks. Our work makes three contributions. First, we develop benchmark adapters that port more than 80 benchmarks to evaluate arbitrary agents, and validate them through rigorous code review and parity experiments. Second, we conduct a large-scale evaluation of 8 models spanning capability tiers across 54 benchmarks; every model is run with Terminus-2 and with one of 3 native harnesses. This enables a broader analysis of agent capabilities and failure modes than was previously possible. Third, we introduce Harbor-Index, a curated set of 82 difficult, diverse, and high-quality tasks spanning 29 benchmarks, refined from the adapted suite through difficulty filtering, AI and human audit, and an audit-and-fix loop. Harbor-Index preserves the challenge and breadth of large-scale agentic evaluations while being affordable to run; no evaluated model-harness configuration exceeds 30% pass rate, and the strongest (GPT-5.5 with Codex) reaches 28.0%. We release the adapters, evaluation results, in-depth analysis, and Harbor-Index as open-source artifacts to support more reliable and comprehensive evaluation of language-model agents.
Received — 27 May 2026 ⏭
Received — 8 April 2026 ⏭

FeynmanBench: Benchmarking Multimodal LLMs on Diagrammatic Physics Reasoning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zeyu Wang · Xiaogang Li · Peiyao Xiao · Qinhao Kong · Ben Wang · Chengliang Xu · Zichao Chen · Bing Zhao · Hu Wei
7 April 2026 at 12:00
arXiv:2604.03893v1 Announce Type: new Abstract: Breakthroughs in frontier theory often depend on the combination of concrete diagrammatic notations with rigorous logic. While multimodal large language models (MLLMs) show promise in general scientific tasks, current benchmarks often focus on local information extraction rather than the global structural logic inherent in formal scientific notations. In this work, we introduce FeynmanBench, the first benchmark centered on Feynman diagram tasks. It is designed to evaluate AI's capacity for multistep diagrammatic reasoning, which requires satisfying conservation laws and symmetry constraints, identifying graph topology, converting between diagrammatic and algebraic representations, and constructing scattering amplitudes under specific conventions and gauges. To support large-scale and reproducible evaluation, we developed an automated pipeline producing diverse Feynman diagrams along with verifiable topological annotations and amplitude results. Our database spans the electromagnetic, weak, and strong interactions of the Standard Model, encompasses over 100 distinct types and includes more than 2000 tasks. Experiments on state-of-the-art MLLMs reveal systematic failure modes, including unstable enforcement of physical constraints and violations of global topological conditions, highlighting the need for physics-grounded benchmarks for visual reasoning over scientific notation. FeynmanBench provides a logically rigorous test of whether AI can effectively engage in scientific discovery, particularly within theoretical physics.

Unveiling Language Routing Isolation in Multilingual MoE Models for Interpretable Subnetwork Adaptation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Kening Zheng · Wei-Chieh Huang · Jiahao Huo · Zhonghao Li · Henry Peng Zou · Yibo Yan · Xin Zou · Jungang Li · Junzhuo Li · Hanrong Zhang · Xuming Hu · Philip S. Yu
7 April 2026 at 12:00
arXiv:2604.03592v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models exhibit striking performance disparities across languages, yet the internal mechanisms driving these gaps remain poorly understood. In this work, we conduct a systematic analysis of expert routing patterns in MoE models, revealing a phenomenon we term Language Routing Isolation, in which high- and low-resource languages tend to activate largely disjoint expert sets. Through layer-stratified analysis, we further show that routing patterns exhibit a layer-wise convergence-divergence pattern across model depth. Building on these findings, we propose RISE (Routing Isolation-guided Subnetwork Enhancement), a framework that exploits routing isolation to identify and adapt language-specific expert subnetworks. RISE applies a tripartite selection strategy, using specificity scores to identify language-specific experts in shallow and deep layers and overlap scores to select universal experts in middle layers. By training only the selected subnetwork while freezing all other parameters, RISE substantially improves low-resource language performance while preserving capabilities in other languages. Experiments on 10 languages demonstrate that RISE achieves target-language F1 gains of up to 10.85% with minimal cross-lingual degradation.
Received — 2 April 2026 ⏭

Route-Induced Density and Stability (RIDE): Controlled Intervention and Mechanism Analysis of Routing-Style Meta Prompts on LLM Internal States

✇cs.AI, q-bio.NC updates on arXiv.org
By: Dianxing Zhang · Gang Li · Sheng Li
1 April 2026 at 12:00
arXiv:2603.29206v1 Announce Type: new Abstract: Routing is widely used to scale large language models, from Mixture-of-Experts gating to multi-model/tool selection. A common belief is that routing to a task ``expert'' activates sparser internal computation and thus yields more certain and stable outputs (the Sparsity--Certainty Hypothesis). We test this belief by injecting routing-style meta prompts as a textual proxy for routing signals in front of frozen instruction-tuned LLMs. We quantify (C1) internal density via activation sparsity, (C2) domain-keyword attention, and (C3) output stability via predictive entropy and semantic variation. On a RouterEval subset with three instruction-tuned models (Qwen3-8B, Llama-3.1-8B-Instruct, and Mistral-7B-Instruct-v0.2), meta prompts consistently densify early/middle-layer representations rather than increasing sparsity; natural-language expert instructions are often stronger than structured tags. Attention responses are heterogeneous: Qwen/Llama reduce keyword attention, while Mistral reinforces it. Finally, the densification--stability link is weak and appears only in Qwen, with near-zero correlations in Llama and Mistral. We present RIDE as a diagnostic probe for calibrating routing design and uncertainty estimation.

Correction: The multifunctional RNA helicase DDX39A drives glioblastoma progression by modulating WISP1 alternative splicing that induces an immunosuppressive macrophage polarization

✇Oncogene - Issue - nature.com science feeds
By: Yan Zhang · Zhiwei Xue · Naibin Zhang · Yuehua Zhu · YanZhao Wu · Meilin Lv · Zhihan Zhang · Feiyu Mu · Wenchen Xing · Ziyi Tang · Chunjie Wang · Zhiyi Xue · Wenjing Zhou · Xiaofei Liu · Xingang Li · Rolf Bjerkvig · Bin Huang · Mingzhi Han · Jian Wang · Donghai Wang
1 April 2026 at 08:00

Oncogene, Published online: 01 April 2026; doi:10.1038/s41388-026-03756-2

Correction: The multifunctional RNA helicase DDX39A drives glioblastoma progression by modulating WISP1 alternative splicing that induces an immunosuppressive macrophage polarization
Received — 26 March 2026 ⏭

Inactivating <i>SnRK1β1A</i> promotes broad-spectrum disease resistance in rice

✇Nature - Issue - nature.com science feeds
By: Guixin Yuan · Xunli Lu · Xingbin Wang · Mengfei Li · Shiwei Wang · Zhaoxiang Huang · Zhigang Li · Fengrui Zhang · Xin Zhang · Jun Yang · Hailong Guo · Vijai Bhadauria · Wang-Sheng Zhu · Wensheng Zhao · Meng Yuan · Jian-Min Zhou · You-Liang Peng
25 March 2026 at 08:00

Nature, Published online: 25 March 2026; doi:10.1038/s41586-026-10273-5

SnRK1β1A in rice promotes susceptibility to multiple fungal diseases, and disrupting this infection-inducible gene confers broad-spectrum resistance without compromising growth or yield under normal field conditions.

PAK4 functions as an immune suppressor by reprogramming the phosphatidylcholine metabolism of CD8 + T cells within the glioblastoma tumor microenvironment

✇Oncogene - Issue - nature.com science feeds
By: Lin Yao · Heyang Gao · Zuopeng Su · Guozheng Zhao · Liyan Tang · Shuo Feng · Yuting Ma · Xiao Zhang · Ming Feng · Jialiang Qian · Yanyan Li · Ting Sun · Jiangang Liu · Hao Wang · Youxin Zhou
23 March 2026 at 08:00

Oncogene, Published online: 23 March 2026; doi:10.1038/s41388-026-03734-8

PAK4 functions as an immune suppressor by reprogramming the phosphatidylcholine metabolism of CD8 + T cells within the glioblastoma tumor microenvironment

SIRT3 deacetylates STEAP4 to modulate cuproptosis sensitivity via mitochondrial metabolic reprogramming in HBV-related HCC

✇Omics in Hepatocellular
By: Ze-Bang Du · Xin-Mou Wu · Jia-Ming Lei · Yu-Xin Cai · Jie He · Bo Qian · Xin-Xin He · Wen-Hao Han · Yuan Lu · Xiao-Gang Xia · Han-Ying Zheng · Dong-Bei Guo · You-Liang Yao · Wen-Gang Li · Yu-Chun Lin · Zhong-Ning Lin
17 March 2026 at 18:00

Cell Death Differ. 2026 Mar 16. doi: 10.1038/s41418-026-01713-w. Online ahead of print.

ABSTRACT

Hepatitis B virus (HBV) infection remains a leading etiological driver of hepatocellular carcinoma (HCC). Cuproptosis is a recently defined copper-dependent form of regulated cell death that selectively eliminates mitochondria-dependent cells; whether HBV rewires this vulnerability remains unknown. Here we unveil a novel HBV X protein (HBx)-driven mechanism of cuproptosis evasion. Integrative analysis of clinical specimens, HBx-transgenic (HBx-Tg) mice, and multi-omics datasets revealed marked downregulation of STEAP4 (six-transmembrane epithelial antigen of prostate 4), a metalloreductase essential for cuproptosis sensitivity, in HBV-positive HCC. Mechanistically, HBx attenuates sirtuin 3 (SIRT3), impairing deacetylation of STEAP4 at lysine 404 and abolishing its mitochondrial targeting. Consequently, cells switch from the tricarboxylic acid (TCA) cycle respiration to glycolysis, reducing sensitivity to the copper ionophore elesclomol (ES). Restoring STEAP4 expression or pharmacological activation of SIRT3 with honokiol (HKL) re-instated mitochondrial STEAP4 localization and re-sensitized HBV-related HCC cells to cuproptosis; combination with ES produced synergistic tumor suppression in vitro and in orthotopic models. Collectively, our findings establish the SIRT3-STEAP4 axis as a novel regulator of cuproptosis resistance in HBV-related HCC. HBx-mediated repression of SIRT3 disrupts STEAP4 deacetylation and mitochondrial targeting, fostering metabolic reprogramming and evasion of copper-induced cell death. The results provide a pre-clinical rationale for copper-directed combination strategies in HBV-associated HCC.

PMID:41840161 | DOI:10.1038/s41418-026-01713-w

Received — 11 March 2026 ⏭

LycheeCluster: Efficient Long-Context Inference with Structure-Aware Chunking and Hierarchical KV Indexing

✇cs.AI, q-bio.NC updates on arXiv.org
By: Dongfang Li · Zixuan Liu · Gang Lin · Baotian Hu · Min Zhang
10 March 2026 at 12:00
arXiv:2603.08453v1 Announce Type: cross Abstract: The quadratic complexity of the attention mechanism and the substantial memory footprint of the Key-Value (KV) cache present severe computational and memory challenges for Large Language Models (LLMs) processing long contexts. Existing retrieval-based methods often compromise semantic integrity through fixed-size chunking and suffer from inefficient linear scanning. In this paper, we propose LycheeCluster, a novel method for efficient KV cache management. LycheeCluster preserves local semantic coherence via boundary-aware chunking and constructs a recursive hierarchical index rooted in the triangle inequality. This design transforms cache retrieval from a linear scan into a theoretically bounded, logarithmic-time pruning process, while a lazy update strategy supports efficient streaming generation. Experiments demonstrate that LycheeCluster achieves up to a 3.6x end-to-end inference speedup with negligible degradation in model performance, outperforming state-of-the-art KV cache management methods (e.g., Quest, ClusterKV). We will release our code and kernels after publication.

Unveiling Downstream Performance Scaling of LLMs: A Clustering-Based Perspective

✇cs.AI, q-bio.NC updates on arXiv.org
By: Chengyin Xu · Kaiyuan Chen · Xiao Li · Ke Shen · Chenggang Li
10 March 2026 at 12:00
arXiv:2502.17262v4 Announce Type: replace-cross Abstract: The escalating scale and cost of Large Language Models (LLMs) training necessitate accurate pre-training prediction of downstream task performance for comprehensive understanding of scaling properties. This is challenged by: 1) the emergence phenomenon, where unpredictable capabilities appearing suddenly at critical model scales; and 2) uneven task difficulty and inconsistent performance scaling patterns, leading to high metric variability. Current prediction methods lack accuracy and reliability. We propose a Clustering-On-Difficulty (COD) framework for downstream performance prediction. The COD framework clusters tasks by their difficulty scaling features, thereby constructing a more stable and predictable task subset that exhibits well-behaved scaling characteristics with the increase of compute budget. We adopt a performance scaling law to predict cluster-wise performance with theoretical support. Predictable subset performance acts as an intermediate predictor for the full evaluation set. We further derive a mapping function to accurately extrapolate the performance of the subset to the full set. Applied to an LLM with 70B parameters, COD achieved a 1.55\% average prediction error across eight key LLM benchmarks, thus providing actionable insights for scaling properties and training monitoring during LLM pre-training.

PMM2 interacts with TRIM28 to recruit E2F4 and promote KIFC3-mediated tumor glycolysis and colorectal cancer progression

✇Oncogene - Issue - nature.com science feeds
By: Zheng Peng · Bing Ma · Zhou Song · Yunshan Zhao · Yang Yang · Yong Liu · Chenggang Li · Yong Zhang
6 March 2026 at 08:00

Oncogene, Published online: 06 March 2026; doi:10.1038/s41388-026-03707-x

PMM2 interacts with TRIM28 to recruit E2F4 and promote KIFC3-mediated tumor glycolysis and colorectal cancer progression
Received — 17 February 2026 ⏭

RRPO: Robust Reward Policy Optimization for LLM-based Emotional TTS

✇cs.AI, q-bio.NC updates on arXiv.org
By: Cong Wang · Changfeng Gao · Yang Xiang · Zhihao Du · Keyu An · Han Zhao · Qian Chen · Xiangang Li · Yingming Gao · Ya Li
17 February 2026 at 13:00
arXiv:2512.04552v3 Announce Type: replace-cross Abstract: Differentiable reinforcement learning (RL) frameworks like DiffRO offer a powerful approach for controllable text-to-speech (TTS), but are vulnerable to reward hacking, particularly for nuanced tasks like emotion control. The policy model can exploit a vanilla Reward Model (RM) by generating acoustic artifacts to achieve spurious rewards, but at the cost of degrading perceptual quality. To address this, we propose Robust Reward Policy Optimization (RRPO), a novel framework that employs a hybrid regularization scheme. This scheme develops a robust RM whose reward signal is more reliably aligned with human perception, compelling the policy to abandon detrimental shortcuts and instead learn the complex features of genuine emotions. Our ablation study confirms the enhanced robustness of our RM, as evidenced by its strong cross-lingual generalization. The subjective evaluation demonstrates that this robust RM effectively mitigates reward hacking, leading to significant improvements in both emotional expressiveness and naturalness over all baselines. Demo page: https://lrwinr.github.io/RRPO-CosyVoice.
There are no more articles
❌