❌

Normal view

Received — 27 May 2026 ⏭

Distilling Game Code World Model Generation into Lightweight Large Language Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Tyrone Serapio · Arjun Prakash · Haoyang Xu · Kevin Wang · Amy Greenwald
26 May 2026 at 12:00
arXiv:2605.24375v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown great ability in generating executable code from natural language, opening the possibility of automatically constructing environments for AI agents. Recent work on Code World Models (CWMs) demonstrates that LLMs can translate game rules into Python implementations compatible with solvers like Monte Carlo Tree Search. We study this problem in game settings, where generated environments must implement rules, legal actions, state transitions, observations, and rewards. We refer to these game-specific executable models as Game Code World Models (GameCWMs). However, current approaches to generating code world models rely on frontier models and inference-time refinement loops, limiting accessibility and scalability. This work investigates whether GameCWM generation capabilities can be distilled into smaller models through post-training. We introduce: (1) a curated dataset of 30 games spanning perfect and imperfect information games, (2) a verification framework that evaluates generated code against structural and semantic game properties, and (3) a post-training pipeline combining Supervised Fine-Tuning (SFT) with Reinforcement Learning with Verifiable Rewards (RLVR). We experiment with Qwen2.5-3B-Instruct and find that SFT can increase syntactic correctness, while RLVR can improve execution-level adherence to game rules, thereby improving Qwen's ability to generate valid GameCWMs in both perfect and imperfect information games. Overall, our pipeline makes Qwen2.5-3B-Instruct more capable of generating valid GameCWMs, thereby offering a scalable path toward automatic environment generation from natural language.

GPNMB Drives Brain Metastasis by Sculpting a Pathological Endothelial-Immune Interactome

✇Omics In Lung
By: Xuefei Liu · Jun Tan · Chun Wu · Guanyin Huang · Yixin Cheng · Jianyang Hu · Binyu Zhang · Mao Zhao · Boxi Zhao · Jingru Lian · Shuqian Zheng · Lin Zeng · Meng Xu · Yang Xu · Shan Zeng · Hao Yu · Hui Yang · Zhixiang Zuo · Chuanyu Liu · Weineng Feng · Weinan Guo · Chunying Li · Sai-Lan Liu · Qing Liu · Feiqiu Wen · Xin Hong
13 April 2026 at 18:00

Cancer Discov. 2026 Apr 15. doi: 10.1158/2159-8290.CD-25-1663. Online ahead of print.

ABSTRACT

Brain metastases (BM) remain a devastating disease with dismal prognosis. How circulating tumor cells (CTCs) penetrate the blood brain barrier (BBB) and reprogram the brain microenvironment remain unclear. Using spatially resolved multi-omic profiling of CTCs and brain metastases, integrated with experimental and clinical analyses, we identified Glycoprotein Non-Metastatic Melanoma Protein B (GPNMB) as a CTC-secreted driver of vascular disruption and brain colonization. CBX3 upregulation induced GPNMB expression, which bound endothelial EGFR, triggering CBL-mediated ubiquitination and degradation. Attenuated EGFR signaling suppressed FTO and disrupted endothelial junctions via YTHDF2-dependent TJP1 m6A methylation. Remarkably, GPNMB-induced BBB remodeling promoted immune infiltration via CXCL12-CXCR4 axis, and induced time course-dependent T cell exhaustion within the brain microenvironment. Clinically, elevated CBX3⁺GPNMB⁺ CTCs and plasma CXCL12 were significantly associated with BM progression in lung cancer and melanoma. Therapeutically, dual blockade of GPNMB and PD1 enhanced anti-BM efficacy in mice, unveiling GPNMB as a promising target for precision immunotherapy.

PMID:41973996 | DOI:10.1158/2159-8290.CD-25-1663

Received — 13 April 2026 ⏭

Engineered immunosuppressive dendritic cells protect against cardiac remodelling

✇Nature - Issue - nature.com science feeds
By: Xiaoying Li · Jiamin Li · Guohua Li · Lisheng Zhu · Guo Cheng · Huanqiang Li · Hao Lin · Ningqing Jia · Xiaoqian Hong · Ye Liu · Zhiwei Zhong · Yize Chen · Biqing Wang · Jing Zhao · Zhenqi Hua · Lingjun Wang · Qiming Chen · Peijie Zheng · Shuyuan Sheng · Songting Gu · Cheng Ni · Shuchang Ye · Changle Ke · Feimu Zhang · Mo Li · Shaohui Shi · Junhua He · Yan Wu · Yinghui Xu · Minjian Kong · Qi Chen · Huajun Li · Yu Zhang · Jianzhong Sun · Guanhua Hu · Chengchen Zhao · Yiping Dong · Lili Yu · Yang Xu · Xinyang Hu
8 April 2026 at 08:00

Nature, Published online: 08 April 2026; doi:10.1038/s41586-026-10346-5

Lesion-targeted immune modulation is a feasible strategy to control cardiac fibrosis, and engineered dendritic cells are a promising therapeutic platform for treating cardiac remodelling and heart failure.
Received — 8 April 2026 ⏭

MoltNet: Understanding Social Behavior of AI Agents in the Agent-Native MoltBook

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yi Feng · Chen Huang · Zhibo Man · Ryner Tan · Long P. Hoang · Shaoyang Xu · Wenxuan Zhang
7 April 2026 at 12:00
arXiv:2602.13458v2 Announce Type: replace-cross Abstract: Large-scale communities of AI agents are becoming increasingly prevalent, creating new environments for agent-agent social interaction. Prior work has examined multi-agent behavior primarily in controlled or small-scale settings, limiting our understanding of emergent social dynamics at scale. The recent emergence of MoltBook, a social networking platform designed explicitly for AI agents, presents a unique opportunity to study whether and how these interactions reproduce core human social mechanisms. We present MoltNet, a dataset tracking the full one-month activity trajectories of 148K AI agents on MoltBook (Jan.-Feb., 2026), and analyze their social interaction along four theory-grounded dimensions: \textit{intent and motivation}, \textit{norms and templates}, \textit{incentives and drift}, \textit{emotion and contagion}. Our analysis reveals that agents respond strongly to social rewards, converge on community-specific norms, and actively enforce them across community boundaries -- resembling human incentive sensitivity and normative conformity. However, they exhibit weak alignment with declared personas and display limited emotional reciprocity and dialogic engagement, diverging systematically from human online communities. These findings establish a first empirical portrait of agent social behavior at scale, with direct implications for the design and governance of AI-populated communities.
Received — 4 April 2026 ⏭

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.
Received — 2 April 2026 ⏭

RAAP: Retrieval-Augmented Affordance Prediction with Cross-Image Action Alignment

✇cs.AI, q-bio.NC updates on arXiv.org
By: Qiyuan Zhuang · He-Yang Xu · Yijun Wang · Xin-Yang Zhao · Yang-Yang Li · Xiu-Shen Wei
1 April 2026 at 12:00
arXiv:2603.29419v1 Announce Type: cross Abstract: Understanding object affordances is essential for enabling robots to perform purposeful and fine-grained interactions in diverse and unstructured environments. However, existing approaches either rely on retrieval, which is fragile due to sparsity and coverage gaps, or on large-scale models, which frequently mislocalize contact points and mispredict post-contact actions when applied to unseen categories, thereby hindering robust generalization. We introduce Retrieval-Augmented Affordance Prediction (RAAP), a framework that unifies affordance retrieval with alignment-based learning. By decoupling static contact localization and dynamic action direction, RAAP transfers contact points via dense correspondence and predicts action directions through a retrieval-augmented alignment model that consolidates multiple references with dual-weighted attention. Trained on compact subsets of DROID and HOI4D with as few as tens of samples per task, RAAP achieves consistent performance across unseen objects and categories, and enables zero-shot robotic manipulation in both simulation and the real world. Project website: https://github.com/SEU-VIPGroup/RAAP.

DNA damage burden causes selective CUX2 neuron loss in neuroinflammation

✇Nature - Issue - nature.com science feeds
By: Laura Morcom · Wenlong Xia · Zhaoyang Xu · Yashika Awasthi · Celine Geywitz · Matthew O. Ellis · Tomas Noli · Amel Zulji · Daniel Yamamoto · Gemma C. Girdler · Li Kai · Keying Zhu · Mingming Wei · Xiao-Yan Tang · Kimberly K. Hoi · Julio Gonzalez-Maya · Greg J. Duncan · Adrien M. Vaquie · Diana Gold Diaz · Riki Kawaguchi · Erdong Liu · Yu Sun · Denny Yang · Gregory D. Jordan · I-Ling Lu · Staffan Holmqvist · Theresa Bartels · Katherine Ridley · Jennifer Ja-Yoon Choi · Santos J. Franco · Eric J. Huang · Ben Emery · Daniel Geschwind · Lucas Schirmer · Gabriel Balmus · Brian Popko · Stephen P. J. Fancy · David H. Rowitch
1 April 2026 at 08:00

Nature, Published online: 01 April 2026; doi:10.1038/s41586-026-10310-3

DNA damage burden and inadequate repair in CUX2+ cortical layer 2/3 excitatory neurons contributes to selective vulnerability in neuroinflammatory injury.

Expansion of outer cortical CUX2 neurons requires adaptations for DNA repair

✇Nature - Issue - nature.com science feeds
By: Wenlong Xia · Laura Morcom · Zhaoyang Xu · I-Ling Lu · Qing Wang · Kimberly K. Hoi · Mingming Wei · Keying Zhu · Gregory Jordan · Xiao-Yan Tang · Julio Gonzalez-Maya · Vanesa S. Mattera · Sophia M. Panigrahi · Riki Kawaguchi · Ben Emery · Santos J. Franco · Daniel H. Geschwind · Brian Popko · David H. Rowitch · Stephen P. J. Fancy
1 April 2026 at 08:00

Nature, Published online: 01 April 2026; doi:10.1038/s41586-026-10290-4

The transcription factor ATF4 is shown to regulate double-stranded DNA repair within vulnerable CUX2+ upper-layer 2/3 cortical neurons, enabling their survival during development.

Robust transcriptomic hallmarks targeting intratumor heterogeneity in intrahepatic cholangiocarcinoma

✇(Multiomics OR Omics) AND (Pancreatic)
By: Youpei Lin · Lihua Peng · Haichao Zhao · Penghui Lin · Lv Chen · Zunyun Gong · Jian Lin · Dongbing Liu · Xupeng Yang · Xiangze Song · Mao Zhang · Shuyi Ji · Junhua Rao · Huijuan Luo · Yifei Cheng · Xiaofang Chen · Guohe Song · Hao Hou · Dongning Rao · Tiancheng Zhang · Weiren Liu · Shu Zhang · Gaoyang Xu · Juan Zhang · Liyun Xiao · Yan Liang · Yang Liu · Yuhan Chen · Zhirou Cui · Xiaoying Wang · Jian Zhou · Qiang Gao · Kui Wu · Jia Fan
31 March 2026 at 18:00

Cell Rep Med. 2026 Mar 30:102708. doi: 10.1016/j.xcrm.2026.102708. Online ahead of print.

ABSTRACT

Intratumor heterogeneity (ITH) undermines transcriptome-based stratification in intrahepatic cholangiocarcinoma (iCCA). Here, we integrate multi-omics data from multi-region, single-region, and single-cell RNA sequencing cohorts to systematically characterize gene expression ITH. We uncover that immune and stromal heterogeneity are primary drivers of ITH, leading to misclassification of a median 27.8% of tumors by existing subtyping systems. To overcome this, we identify a low-intratumor-heterogeneity/high-intertumor-variability (LIHV) gene set and develop an ITH-insensitive classification system defining five subgroups: inflammatory (SI), metabolic (SII), atypical (SIII-1), immune-silent (SIII-2), and neurodegenerative (SIII-3). These subgroups exhibit distinct clinical outcomes, molecular features, immune landscapes, and therapeutic vulnerabilities. GPRC5A and VTCN1 serve as robust immunohistochemical biomarkers for SI and SIII tumors, while serum CEA and CA19-9 identify inflammatory iCCA. Therapeutically, HSP90 inhibition synergizes with anti-PD1 in inflammatory iCCA, whereas combined anti-PD1 and anti-TIM3 suppresses neurodegenerative iCCA. Collectively, our study provides a robust molecular framework and actionable therapeutic strategies for iCCA.

PMID:41916296 | DOI:10.1016/j.xcrm.2026.102708

Received — 26 March 2026 ⏭

Trem1 regulates neutrophil metabolism and recruitment in lung ischemia-reperfusion injury

✇Omics In Lung
By: Fengjing Yang · Song Tong · Junhao Wan · Yixing Li · Jiani Gao · Yan Sun · Xiangfu Sun · Huikang Fu · Wenzhuo Luo · Jiayang Xu · Ting Zhou · Sowe Babou · Junqi Wu · Guangjian Zhang · Chang Chen · Sihua Wang
20 March 2026 at 18:00

Redox Biol. 2026 Jan 14;92:104026. doi: 10.1016/j.redox.2026.104026. Online ahead of print.

ABSTRACT

Primary graft dysfunction (PGD) caused by ischemia-reperfusion injury (IRI) is a major complication after lung transplantation, yet its underlying mechanisms remain unclear. Triggering receptor expressed on myeloid cells 1 (Trem1) is an important mediator of inflammation, but its role in neutrophil function and metabolic reprogramming during lung IRI is not well understood. In this study, we used a murine orthotopic lung transplantation model with cold ischemia and reperfusion, and Trem1 knockout (Trem1-/-) and myeloid-specific Trem1 conditional knockout mice (LysmCreTrem1fl) to explore the role of Trem1 in neutrophil recruitment, neutrophil extracellular trap (NET) formation, and metabolism. Our results show that Trem1 expression increases in both mouse and human lungs after reperfusion and correlates with neutrophil infiltration and lung injury. Trem1 deficiency significantly reduced neutrophil and macrophage recruitment, NET formation, and tissue damage. Multi-omics analysis revealed that Trem1 deletion suppressed oxidative phosphorylation (OXPHOS) and induced a metabolic shift in neutrophils toward glycolysis. In clinical samples, the abundance of TREM1+ neutrophils was correlated with PGD severity and OXPHOS activity. These findings identify Trem1 as a key regulator of neutrophil metabolism and recruitment in lung IRI, and suggest that targeting Trem1 may provide a novel therapeutic strategy to mitigate PGD and improve lung transplant outcomes.

PMID:41861599 | DOI:10.1016/j.redox.2026.104026

Received — 17 March 2026 ⏭

Delta1 with LLM: symbolic and neural integration for credible and explainable reasoning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yang Xu · Jun Liu · Shuwei Chen · Chris Nugent · Hailing Guo
16 March 2026 at 12:00
arXiv:2603.12953v1 Announce Type: cross Abstract: Neuro-symbolic reasoning increasingly demands frameworks that unite the formal rigor of logic with the interpretability of large language models (LLMs). We introduce an end to end explainability by construction pipeline integrating the Automated Theorem Generator Delta1 based on the full triangular standard contradiction (FTSC) with LLMs. Delta1 deterministically constructs minimal unsatisfiable clause sets and complete theorems in polynomial time, ensuring both soundness and minimality by construction. The LLM layer verbalizes each theorem and proof trace into coherent natural language explanations and actionable insights. Empirical studies across health care, compliance, and regulatory domains show that Delta1 and LLM enables interpretable, auditable, and domain aligned reasoning. This work advances the convergence of logic, language, and learning, positioning constructive theorem generation as a principled foundation for neuro-symbolic explainable AI.
Received — 11 March 2026 ⏭

Don't Freeze, Don't Crash: Extending the Safe Operating Range of Neural Navigation in Dense Crowds

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jiefu Zhang · Yang Xu · Vaneet Aggarwal
10 March 2026 at 12:00
arXiv:2603.06729v1 Announce Type: cross Abstract: Navigating safely through dense crowds requires collision avoidance that generalizes beyond the densities seen during training. Learning-based crowd navigation can break under out-of-distribution crowd sizes due to density-sensitive observation normalization and social-cost scaling, while analytical solvers often remain safe but freeze in tight interactions. We propose a reinforcement learning approach for dense, variable-density navigation that attains zero-shot density generalization using a density-invariant observation encoding with density-randomized training and physics-informed proxemic reward shaping with density-adaptive scaling. The encoding represents the distance-sorted $K$ nearest pedestrians plus bounded crowd summaries, keeping input statistics stable as crowd size grows. Trained with $N\!\in\![11,16]$ pedestrians in a $3\mathrm{m}\times3\mathrm{m}$ arena and evaluated up to $N\!=\!21$ pedestrians ($1.3\times$ denser), our policy reaches the goal in $>99\%$ of episodes and achieves $86\%$ collision-free success in random crowds, with markedly less freezing than analytical methods and a $>\!60$-point collision-free margin over learning-based benchmark methods. Codes are available at \href{https://github.com/jznmsl/PSS-Social}{https://github.com/jznmsl/PSS-Social}.

Cross-Modal Taxonomic Generalization in (Vision-) Language Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Tianyang Xu · Marcelo Sandoval-Castaneda · Karen Livescu · Greg Shakhnarovich · Kanishka Misra
10 March 2026 at 12:00
arXiv:2603.07474v1 Announce Type: cross Abstract: What is the interplay between semantic representations learned by language models (LM) from surface form alone to those learned from more grounded evidence? We study this question for a scenario where part of the input comes from a different modality -- in our case, in a vision-language model (VLM), where a pretrained LM is aligned with a pretrained image encoder. As a case study, we focus on the task of predicting hypernyms of objects represented in images. We do so in a VLM setup where the image encoder and LM are kept frozen, and only the intermediate mappings are learned. We progressively deprive the VLM of explicit evidence for hypernyms, and test whether knowledge of hypernyms is recoverable from the LM. We find that the LMs we study can recover this knowledge and generalize even in the most extreme version of this experiment (when the model receives no evidence of a hypernym during training). Additional experiments suggest that this cross-modal taxonomic generalization persists under counterfactual image-label mappings only when the counterfactual data have high visual similarity within each category. Taken together, these findings suggest that cross-modal generalization in LMs arises as a result of both coherence in the extralinguistic input and knowledge derived from language cues.
Received — 5 March 2026 ⏭

LifeBench: A Benchmark for Long-Horizon Multi-Source Memory

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zihao Cheng · Weixin Wang · Yu Zhao · Ziyang Ren · Jiaxuan Chen · Ruiyang Xu · Shuai Huang · Yang Chen · Guowei Li · Mengshi Wang · Yi Xie · Ren Zhu · Zeren Jiang · Keda Lu · Yihong Li · Xiaoliang Wang · Liwei Liu · Cam-Tu Nguyen
5 March 2026 at 13:00
arXiv:2603.03781v1 Announce Type: new Abstract: Long-term memory is fundamental for personalized agents capable of accumulating knowledge, reasoning over user experiences, and adapting across time. However, existing memory benchmarks primarily target declarative memory, specifically semantic and episodic types, where all information is explicitly presented in dialogues. In contrast, real-world actions are also governed by non-declarative memory, including habitual and procedural types, and need to be inferred from diverse digital traces. To bridge this gap, we introduce Lifebench, which features densely connected, long-horizon event simulation. It pushes AI agents beyond simple recall, requiring the integration of declarative and non-declarative memory reasoning across diverse and temporally extended contexts. Building such a benchmark presents two key challenges: ensuring data quality and scalability. We maintain data quality by employing real-world priors, including anonymized social surveys, map APIs, and holiday-integrated calendars, thus enforcing fidelity, diversity and behavioral rationality within the dataset. Towards scalability, we draw inspiration from cognitive science and structure events according to their partonomic hierarchy; enabling efficient parallel generation while maintaining global coherence. Performance results show that top-tier, state-of-the-art memory systems reach just 55.2\% accuracy, highlighting the inherent difficulty of long-horizon retrieval and multi-source integration within our proposed benchmark. The dataset and data synthesis code are available at https://github.com/1754955896/LifeBench.

Dynamic Manifold Hopfield Networks for Context-Dependent Associative Memory

✇cs.AI, q-bio.NC updates on arXiv.org
By: Chong Li · Taiping Zeng · Xiangyang Xue · Jianfeng Feng
4 March 2026 at 13:00
arXiv:2506.01303v3 Announce Type: replace-cross Abstract: Neural population activity in cortical and hippocampal circuits can be flexibly reorganized by context, suggesting that cognition relies on dynamic manifolds rather than static representations. However, how such dynamic organization can be realized mechanistically within a unified dynamical system remains unclear. Continuous Hopfield networks provide a classical attractor framework in which neural dynamics follow gradient descent on a fixed energy landscape, constraining retrieval within a static attractor manifold geometry. Extending this approach, we introduce Dynamic Manifold Hopfield Networks (DMHN), continuous dynamical models in which contextual modulation dynamically reshapes attractor geometry, transforming a static attractor manifold into a context-dependent family of neural manifolds. In DMHN, network interactions are learned in a data-driven manner, to intrinsically deform the geometry of its attractor manifold across cues without explicit context-specific parameterization. As a result, in associative retrieval, DMHN achieve substantially higher capacity and robustness than classical and modern Hopfield networks: when storing $2N$ patterns in a network of $N$ neurons, DMHN attain reliable retrieval with an average accuracy of 64%, compared with 1% and 13% for classical and modern variants, respectively. Together, these results establish dynamic reorganization of attractor manifold geometry as a principled mechanism for context-dependent remapping in neural associative memory.
Received — 17 February 2026 ⏭

MoltNet: Understanding Social Behavior of AI Agents in the Agent-Native MoltBook

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yi Feng · Chen Huang · Zhibo Man · Ryner Tan · Long P. Hoang · Shaoyang Xu · Wenxuan Zhang
17 February 2026 at 13:00
arXiv:2602.13458v1 Announce Type: cross Abstract: Large-scale communities of AI agents are becoming increasingly prevalent, creating new environments for agent-agent social interaction. Prior work has examined multi-agent behavior primarily in controlled or small-scale settings, limiting our understanding of emergent social dynamics at scale. The recent emergence of MoltBook, a social networking platform designed explicitly for AI agents, presents a unique opportunity to study whether and how these interactions reproduce core human social mechanisms. We present MoltNet, a large-scale empirical analysis of agent interaction on MoltBook using data collected in early 2026. Grounded in sociological and social-psychological theory, we examine behavior along four dimensions: intent and motivation, norms and templates, incentives and behavioral drift, emotion and contagion. Our analysis revealed that agents strongly respond to social rewards and rapidly converge on community-specific interaction templates, resembling human patterns of incentive sensitivity and normative conformity. However, they are predominantly knowledge-driven rather than persona-aligned, and display limited emotional reciprocity along with weak dialogic engagement, which diverges systematically from human online communities. Together, these results reveal both similarities and differences between artificial and human social systems and provide an empirical foundation for understanding, designing, and governing large-scale agent communities.

InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problem

✇cs.AI, q-bio.NC updates on arXiv.org
By: Shuofei Qiao · Yunxiang Wei · Xuehai Wang · Bin Wu · Boyang Xue · Ningyu Zhang · Hossein A. Rahmani · Yanshan Wang · Qiang Zhang · Keyan Ding · Jeff Z. Pan · Huajun Chen · Emine Yilmaz
17 February 2026 at 13:00
arXiv:2602.14367v1 Announce Type: cross Abstract: The rapid evolution of Large Language Models has catalyzed a surge in scientific idea production, yet this leap has not been accompanied by a matching advance in idea evaluation. The fundamental nature of scientific evaluation needs knowledgeable grounding, collective deliberation, and multi-criteria decision-making. However, existing idea evaluation methods often suffer from narrow knowledge horizons, flattened evaluation dimensions, and the inherent bias in LLM-as-a-Judge. To address these, we regard idea evaluation as a knowledge-grounded, multi-perspective reasoning problem and introduce InnoEval, a deep innovation evaluation framework designed to emulate human-level idea assessment. We apply a heterogeneous deep knowledge search engine that retrieves and grounds dynamic evidence from diverse online sources. We further achieve review consensus with an innovation review board containing reviewers with distinct academic backgrounds, enabling a multi-dimensional decoupled evaluation across multiple metrics. We construct comprehensive datasets derived from authoritative peer-reviewed submissions to benchmark InnoEval. Experiments demonstrate that InnoEval can consistently outperform baselines in point-wise, pair-wise, and group-wise evaluation tasks, exhibiting judgment patterns and consensus highly aligned with human experts.
There are no more articles
❌