❌

Normal view

Received β€” 26 October 2025 ⏭ Favourites

Decoding the tumor immune microenvironment in lung squamous cell carcinoma: characteristics, regulatory mechanisms, and future directions in immunotherapy

βœ‡Omics In Lung
By: Yunfeng Tong Β· Yuxia Wang Β· Yunfei Chen Β· Yun Fan Β· Hui Li
24 October 2025 at 18:00

Transl Lung Cancer Res. 2025 Sep 30;14(9):4112-4130. doi: 10.21037/tlcr-2025-350. Epub 2025 Sep 18.

ABSTRACT

Lung squamous cell carcinoma (LUSC), a predominant type of lung cancer, is marked by an unfavorable prognosis and limited therapeutic options. Unlike lung adenocarcinoma (LUAD), LUSC exhibits few driver mutations, resulting in minimal benefits from targeted therapies for these patients. Despite the transformative effects of immunotherapy on patient outcomes, only a subset of patients achieving durable responses. This heterogeneity in treatment outcomes is increasingly attributed to the complex feature of the tumor immune microenvironment (TIME) in LUSC. The TIME of LUSC is a highly dynamic ecosystem composed of diverse immune cell populations and stromal components that collectively foster an immune-evasive niche. Recent breakthroughs in multi-omics technologies, particularly single-cell RNA sequencing (scRNA-seq) and spatial omics, have provided unprecedented resolution in dissecting the cellular and molecular architecture of the TIME in LUSC. These technologies have enabled the identification of distinct immune cells and their spatial interactions with the tumor, shedding light on the mechanisms underlying immune evasion and resistance to immunotherapy. Building on these advancements, this review establishes a new classification of the TIME which may guide patient stratification and personalized immunotherapy. And we comprehensively offer a detailed examination of the principal characteristics and regulatory mechanisms of the TIME, highlighting potential immunotherapeutic strategies tailored to this distinct immunological context.

PMID:41133013 | PMC:PMC12541881 | DOI:10.21037/tlcr-2025-350

Biomarkers for non-small cell lung cancer risk using multi-omics approaches: a nested case-control study

βœ‡Omics In Lung
By: Youngmin Han Β· Keum Ji Jung Β· Seong Gyu Choi Β· Yeun Soo Yang Β· Kwangbae Lee Β· Sun Ha Jee
24 October 2025 at 18:00

Transl Lung Cancer Res. 2025 Sep 30;14(9):3645-3658. doi: 10.21037/tlcr-2025-603. Epub 2025 Sep 25.

ABSTRACT

BACKGROUND: Lung cancer poses a major public health challenge, accounting for the highest cancer-related mortality worldwide. This study aimed to identify non-invasive biomarkers for the early detection of non-small cell lung cancer (NSCLC) risk.

METHODS: We randomly selected 150 incident NSCLC cases during follow-up from the Korean Cancer Prevention Study-II. Controls (n=150) were matched to cases by age, gender, and the time of blood collection. Non-targeted metabolite screening by ultra-high-performance liquid chromatography (UHPLC)/mass spectrometry (MS) was conducted on the pre-diagnostic biological samples. The 11 reported lung cancer-associated single-nucleotide polymorphisms (SNPs) in Koreans were extracted from DNA genotyping data of the study population. Metabolite markers related to NSCLC risk were identified through clustering using hierarchical density-based spatial clustering of applications with noise. The associations between smoking, dietary factors, and NSCLC were also examined.

RESULTS: Six discriminative serum metabolites were identified as having an association with NSCLC incidence. Notably, the relationship between specific metabolite levels and NSCLC risk differed by rs7086803 genotype. Smoking status and occupational exposures appear to influence specific metabolite profiles, while dietary vegetable intake may modulate the risk of NSCLC among smokers.

CONCLUSIONS: The meaningful biomarkers revealed in the current research could be used to enhance the predictive ability for NSCLC risk. Furthermore, we suggest that the protective role of dietary vegetables against NSCLC may be attenuated or absent in smokers.

PMID:41133005 | PMC:PMC12541849 | DOI:10.21037/tlcr-2025-603

AI-powered vaccine breakthroughs: Targeting pancreatic cancer with neoantigens and combination therapies

βœ‡(Multiomics OR Omics) AND (Pancreatic)
By: Jiaxin Zhang Β· Lin Xiao Β· Yueshui Zhang Β· Gang Jin Β· Kailian Zheng
25 October 2025 at 18:00

Biochim Biophys Acta Rev Cancer. 2025 Oct 23:189484. doi: 10.1016/j.bbcan.2025.189484. Online ahead of print.

ABSTRACT

The five-year survival rate for Pancreatic Ductal Adenocarcinoma (PDAC) remains below 10 %, primarily due to the limited efficacy of conventional chemotherapy and immune checkpoint inhibitors against its triple-immune-sequestered, low-TMB tumor microenvironment(TME). This situation has been furter exacerbated by the stagnation of traditional vaccine development, driven by inefficient antigen screening and high tumor heterogeneity. Artificial intelligence (AI) exhibits remarkable advantages in the design of pancreatic ductal adenocarcinoma (PDAC) vaccines. It can integrate multi - omics data to efficiently unearth cryptic neoantigens from low - tumor mutation burden (TMB) samples, significantly enhancing the screening efficiency. Through dynamic modeling, AI can rationally plan the timing of combined vaccine therapies, effectively reducing the degree of T - cell exhaustion. By leveraging the digital twin model, AI can remarkably improve the matching accuracy between antigens and human leukocyte antigen (HLA). Additionally, it can construct a monitoring system to provide early warnings of antigen loss risks, thus gaining adjustment time for clinical treatments.This review aims to accomplish three primary objectives: demonstrate AI's potential in breaking the therapeutic impasse to overcome manufacturing-related treatment delays for 25-30 % of patients; further delineates the logical progression of AI from concept to clinical application; thereby provides a translational framework to bridge the gap between research and patient benefit.

PMID:41138796 | DOI:10.1016/j.bbcan.2025.189484

Best Practices for Data Modernization Across the United States Public Health System: Scoping Review

βœ‡Journal of Medical Internet Research
By: Zebunnesa Zeba Β· Stella T Lartey Β· Polina Durneva Β· Shongkour Roy Β· Niharika Jha Β· Michael Arthur Ofori Β· Nidhi Mittal Β· Stella Dockery Β· Nichole Saulsberry Scarboro Β· Michelle Taylor Β· Ashish Joshi
25 October 2025 at 04:00
Background: The adoption of new technologies and data modernization approaches in public health aims to enhance the use of health data to inform decision-making and improve population health. However, public health departments struggle with legacy systems, siloed data, and privacy concerns, hampering new technology adoption and data sharing with stakeholders. This paper maps how to address these shortcomings by identifying data modernization challenges, initiatives, and progress. Objective: To characterize the evidence for data modernization associated gaps and best practices in public health. Methods: This scoping review was conducted using the five-stage framework developed by Arksey and O’Malley and was reported according to the PRISMA-ScR guidelines. A structured search was performed in databases PubMed, Scopus, CINAHL, PsycINFO, and was complemented by a further search in the Google Scholar search engine, covering publications from January 1, 2019, to April 30, 2024. Eligible studies were peer-reviewed, published in English, and focused on data modernization initiatives within U.S. public health and reported on best practices, challenges, and outcomes. Search terms combined concepts such as β€œData Modernization,” β€œInteroperability,” and β€œPublic Health” using Boolean operators. Two reviewers independently screened titles, abstracts, and full texts using Rayyan QCRI, with conflicts resolved through consultation with a third reviewer. Data was extracted into Microsoft Excel and thematically analyzed. Results: This review analyzed 22 studies focused on public health data modernization. Across the literature, common components included transitioning to cloud-based systems, consolidating fragmented data into unified platforms, applying governance frameworks, and implementing analytics tools to support decision-making. Primary data sources were electronic health records, insurance claims, and disease surveillance registries. Key challenges identified across studies involved data quality issues, lack of interoperability, and limited resources, particularly in underfunded settings. Notable benefits included more timely and accessible data, improved integration across systems, and enhanced analytical capabilities, which collectively support more responsive and effective public health interventions when guided by clear standards and policy alignment. Conclusions: Progress hinges on balancing local adaptability with national coordination, improving data governance practices, and enhancing collaboration across institutions. These steps are vital to ensure public health systems can deliver timely, accurate, and actionable information to support effective public health efforts.

The glaring security risks with AI browser agents

βœ‡TechCrunch
By: Maxwell Zeff
25 October 2025 at 20:00
New AI browsers from OpenAI and Perplexity promise to increase user productivity, but they also come with increased security risks.

Anthropic Introduces Skills for Custom Claude Tasks

βœ‡InfoQ
By: Daniel Dominguez
25 October 2025 at 18:05

Anthropic has unveiled a new feature called Skills, designed to let developers extend Claude with modular, reusable task components.

By Daniel Dominguez
  • βœ‡TechCrunch
  • The browser wars are back, and this time they’re powered by AI Theresa Loconsolo
    The browser wars are heating up again, this time with AI in the driver’s seat.Β  OpenAI just launched Atlas, a ChatGPT-powered browser that lets users surf the web using natural language, and even includes an β€œagent mode” that can complete tasks autonomously. It’s one of the biggest browser launches in recent memory, but it’s debuting […]
     
  • 🏷️
  • ↗️

The browser wars are back, and this time they’re powered by AI

βœ‡TechCrunch
By: Theresa Loconsolo
25 October 2025 at 03:00
The browser wars are heating up again, this time with AI in the driver’s seat.Β  OpenAI just launched Atlas, a ChatGPT-powered browser that lets users surf the web using natural language, and even includes an β€œagent mode” that can complete tasks autonomously. It’s one of the biggest browser launches in recent memory, but it’s debuting […]
Received β€” 24 October 2025 ⏭ Favourites

AI PB: A Grounded Generative Agent for Personalized Investment Insights

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Daewoo Park Β· Suho Park Β· Inseok Hong Β· Hanwool Lee Β· Junkyu Park Β· Sangjun Lee Β· Jeongman An Β· Hyunbin Loh
24 October 2025 at 12:00
arXiv:2510.20099v1 Announce Type: new Abstract: We present AI PB, a production-scale generative agent deployed in real retail finance. Unlike reactive chatbots that answer queries passively, AI PB proactively generates grounded, compliant, and user-specific investment insights. It integrates (i) a component-based orchestration layer that deterministically routes between internal and external LLMs based on data sensitivity, (ii) a hybrid retrieval pipeline using OpenSearch and the finance-domain embedding model, and (iii) a multi-stage recommendation mechanism combining rule heuristics, sequential behavioral modeling, and contextual bandits. Operating fully on-premises under Korean financial regulations, the system employs Docker Swarm and vLLM across 24 X NVIDIA H100 GPUs. Through human QA and system metrics, we demonstrate that grounded generation with explicit routing and layered safety can deliver trustworthy AI insights in high-stakes finance.

Bias by Design? How Data Practices Shape Fairness in AI Healthcare Systems

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Anna Arias-Duart Β· Maria Eugenia Cardello Β· Atia Cort\'es
24 October 2025 at 12:00
arXiv:2510.20332v1 Announce Type: new Abstract: Artificial intelligence (AI) holds great promise for transforming healthcare. However, despite significant advances, the integration of AI solutions into real-world clinical practice remains limited. A major barrier is the quality and fairness of training data, which is often compromised by biased data collection practices. This paper draws on insights from the AI4HealthyAging project, part of Spain's national R&D initiative, where our task was to detect biases during clinical data collection. We identify several types of bias across multiple use cases, including historical, representation, and measurement biases. These biases manifest in variables such as sex, gender, age, habitat, socioeconomic status, equipment, and labeling. We conclude with practical recommendations for improving the fairness and robustness of clinical problem design and data collection. We hope that our findings and experience contribute to guiding future projects in the development of fairer AI systems in healthcare.
  • βœ‡cs.AI, q-bio.NC updates on arXiv.org
  • LLM-empowered knowledge graph construction: A survey Haonan Bian
    arXiv:2510.20345v1 Announce Type: new Abstract: Knowledge Graphs (KGs) have long served as a fundamental infrastructure for structured knowledge representation and reasoning. With the advent of Large Language Models (LLMs), the construction of KGs has entered a new paradigm-shifting from rule-based and statistical pipelines to language-driven and generative frameworks. This survey provides a comprehensive overview of recent progress in LLM-empowered knowledge graph construction, systematically
     
  • 🏷️
  • ↗️

LLM-empowered knowledge graph construction: A survey

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Haonan Bian
24 October 2025 at 12:00
arXiv:2510.20345v1 Announce Type: new Abstract: Knowledge Graphs (KGs) have long served as a fundamental infrastructure for structured knowledge representation and reasoning. With the advent of Large Language Models (LLMs), the construction of KGs has entered a new paradigm-shifting from rule-based and statistical pipelines to language-driven and generative frameworks. This survey provides a comprehensive overview of recent progress in LLM-empowered knowledge graph construction, systematically analyzing how LLMs reshape the classical three-layered pipeline of ontology engineering, knowledge extraction, and knowledge fusion. We first revisit traditional KG methodologies to establish conceptual foundations, and then review emerging LLM-driven approaches from two complementary perspectives: schema-based paradigms, which emphasize structure, normalization, and consistency; and schema-free paradigms, which highlight flexibility, adaptability, and open discovery. Across each stage, we synthesize representative frameworks, analyze their technical mechanisms, and identify their limitations. Finally, the survey outlines key trends and future research directions, including KG-based reasoning for LLMs, dynamic knowledge memory for agentic systems, and multimodal KG construction. Through this systematic review, we aim to clarify the evolving interplay between LLMs and knowledge graphs, bridging symbolic knowledge engineering and neural semantic understanding toward the development of adaptive, explainable, and intelligent knowledge systems.

FLORA: Unsupervised Knowledge Graph Alignment by Fuzzy Logic

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Yiwen Peng (IP Paris) Β· Thomas Bonald (IP Paris) Β· Fabian M. Suchanek (IP Paris)
24 October 2025 at 12:00
arXiv:2510.20467v1 Announce Type: new Abstract: Knowledge graph alignment is the task of matching equivalent entities (that is, instances and classes) and relations across two knowledge graphs. Most existing methods focus on pure entity-level alignment, computing the similarity of entities in some embedding space. They lack interpretable reasoning and need training data to work. In this paper, we propose FLORA, a simple yet effective method that (1) is unsupervised, i.e., does not require training data, (2) provides a holistic alignment for entities and relations iteratively, (3) is based on fuzzy logic and thus delivers interpretable results, (4) provably converges, (5) allows dangling entities, i.e., entities without a counterpart in the other KG, and (6) achieves state-of-the-art results on major benchmarks.

Lost in Translation: Policymakers are not really listening to Citizen Concerns about AI

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Susan Ariel Aaronson Β· Michael Moreno
24 October 2025 at 12:00
arXiv:2510.20568v1 Announce Type: new Abstract: The worlds people have strong opinions about artificial intelligence (AI), and they want policymakers to listen. Governments are inviting public comment on AI, but as they translate input into policy, much of what citizens say is lost. Policymakers are missing a critical opportunity to build trust in AI and its governance. This paper compares three countries, Australia, Colombia, and the United States, that invited citizens to comment on AI risks and policies. Using a landscape analysis, the authors examined how each government solicited feedback and whether that input shaped governance. Yet in none of the three cases did citizens and policymakers establish a meaningful dialogue. Governments did little to attract diverse voices or publicize calls for comment, leaving most citizens unaware or unprepared to respond. In each nation, fewer than one percent of the population participated. Moreover, officials showed limited responsiveness to the feedback they received, failing to create an effective feedback loop. The study finds a persistent gap between the promise and practice of participatory AI governance. The authors conclude that current approaches are unlikely to build trust or legitimacy in AI because policymakers are not adequately listening or responding to public concerns. They offer eight recommendations: promote AI literacy; monitor public feedback; broaden outreach; hold regular online forums; use innovative engagement methods; include underrepresented groups; respond publicly to input; and make participation easier.
  • βœ‡cs.AI, q-bio.NC updates on arXiv.org
  • Fluidity Index: Next-Generation Super-intelligence Benchmarks Eric Ngoiya Β· Tianshu Bao
    arXiv:2510.20636v1 Announce Type: new Abstract: This paper introduces the Fluidity Index (FI) to quantify model adaptability in dynamic, scaling environments. The benchmark evaluates response accuracy based on deviations in initial, current, and future environment states, assessing context switching and continuity. We distinguish between closed-ended and open-ended benchmarks, prioritizing closed-loop open-ended real-world benchmarks to test adaptability. The approach measures a model's ability
     
  • 🏷️
  • ↗️

Fluidity Index: Next-Generation Super-intelligence Benchmarks

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Eric Ngoiya Β· Tianshu Bao
24 October 2025 at 12:00
arXiv:2510.20636v1 Announce Type: new Abstract: This paper introduces the Fluidity Index (FI) to quantify model adaptability in dynamic, scaling environments. The benchmark evaluates response accuracy based on deviations in initial, current, and future environment states, assessing context switching and continuity. We distinguish between closed-ended and open-ended benchmarks, prioritizing closed-loop open-ended real-world benchmarks to test adaptability. The approach measures a model's ability to understand, predict, and adjust to state changes in scaling environments. A truly super-intelligent model should exhibit at least second-order adaptability, enabling self-sustained computation through digital replenishment for optimal fluidity.

MolBridge: Atom-Level Joint Graph Refinement for Robust Drug-Drug Interaction Event Prediction

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Xuan Lin Β· Aocheng Ding Β· Tengfei Ma Β· Hua Liang Β· Zhe Quan
24 October 2025 at 12:00
arXiv:2510.20448v1 Announce Type: cross Abstract: Drug combinations offer therapeutic benefits but also carry the risk of adverse drug-drug interactions (DDIs), especially under complex molecular structures. Accurate DDI event prediction requires capturing fine-grained inter-drug relationships, which are critical for modeling metabolic mechanisms such as enzyme-mediated competition. However, existing approaches typically rely on isolated drug representations and fail to explicitly model atom-level cross-molecular interactions, limiting their effectiveness across diverse molecular complexities and DDI type distributions. To address these limitations, we propose MolBridge, a novel atom-level joint graph refinement framework for robust DDI event prediction. MolBridge constructs a joint graph that integrates atomic structures of drug pairs, enabling direct modeling of inter-drug associations. A central challenge in such joint graph settings is the potential loss of information caused by over-smoothing when modeling long-range atomic dependencies. To overcome this, we introduce a structure consistency module that iteratively refines node features while preserving the global structural context. This joint design allows MolBridge to effectively learn both local and global interaction outperforms state-of-the-art baselines, achieving superior performance across long-tail and inductive scenarios. patterns, yielding robust representations across both frequent and rare DDI types. Extensive experiments on two benchmark datasets show that MolBridge consistently. These results demonstrate the advantages of fine-grained graph refinement in improving the accuracy, robustness, and mechanistic interpretability of DDI event prediction.This work contributes to Web Mining and Content Analysis by developing graph-based methods for mining and analyzing drug-drug interaction networks.

Exploring Large Language Models for Access Control Policy Synthesis and Summarization

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Adarsh Vatsa Β· Bethel Hall Β· William Eiers
24 October 2025 at 12:00
arXiv:2510.20692v1 Announce Type: cross Abstract: Cloud computing is ubiquitous, with a growing number of services being hosted on the cloud every day. Typical cloud compute systems allow administrators to write policies implementing access control rules which specify how access to private data is governed. These policies must be manually written, and due to their complexity can often be error prone. Moreover, existing policies often implement complex access control specifications and thus can be difficult to precisely analyze in determining their behavior works exactly as intended. Recently, Large Language Models (LLMs) have shown great success in automated code synthesis and summarization. Given this success, they could potentially be used for automatically generating access control policies or aid in understanding existing policies. In this paper, we explore the effectiveness of LLMs for access control policy synthesis and summarization. Specifically, we first investigate diverse LLMs for access control policy synthesis, finding that: although LLMs can effectively generate syntactically correct policies, they have permissiveness issues, generating policies equivalent to the given specification 45.8% of the time for non-reasoning LLMs, and 93.7% of the time for reasoning LLMs. We then investigate how LLMs can be used to analyze policies by introducing a novel semantic-based request summarization approach which leverages LLMs to generate a precise characterization of the requests allowed by a policy. Our results show that while there are significant hurdles in leveraging LLMs for automated policy generation, LLMs show promising results when combined with symbolic approaches in analyzing existing policies.

User Perceptions of Privacy and Helpfulness in LLM Responses to Privacy-Sensitive Scenarios

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Xiaoyuan Wu Β· Roshni Kaushik Β· Wenkai Li Β· Lujo Bauer Β· Koichi Onoue
24 October 2025 at 12:00
arXiv:2510.20721v1 Announce Type: cross Abstract: Large language models (LLMs) have seen rapid adoption for tasks such as drafting emails, summarizing meetings, and answering health questions. In such uses, users may need to share private information (e.g., health records, contact details). To evaluate LLMs' ability to identify and redact such private information, prior work developed benchmarks (e.g., ConfAIde, PrivacyLens) with real-life scenarios. Using these benchmarks, researchers have found that LLMs sometimes fail to keep secrets private when responding to complex tasks (e.g., leaking employee salaries in meeting summaries). However, these evaluations rely on LLMs (proxy LLMs) to gauge compliance with privacy norms, overlooking real users' perceptions. Moreover, prior work primarily focused on the privacy-preservation quality of responses, without investigating nuanced differences in helpfulness. To understand how users perceive the privacy-preservation quality and helpfulness of LLM responses to privacy-sensitive scenarios, we conducted a user study with 94 participants using 90 scenarios from PrivacyLens. We found that, when evaluating identical responses to the same scenario, users showed low agreement with each other on the privacy-preservation quality and helpfulness of the LLM response. Further, we found high agreement among five proxy LLMs, while each individual LLM had low correlation with users' evaluations. These results indicate that the privacy and helpfulness of LLM responses are often specific to individuals, and proxy LLMs are poor estimates of how real users would perceive these responses in privacy-sensitive scenarios. Our results suggest the need to conduct user-centered studies on measuring LLMs' ability to help users while preserving privacy. Additionally, future research could investigate ways to improve the alignment between proxy LLMs and users for better estimation of users' perceived privacy and utility.

Automated Extraction of Fluoropyrimidine Treatment and Treatment-Related Toxicities from Clinical Notes Using Natural Language Processing

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Xizhi Wu Β· Madeline S. Kreider Β· Philip E. Empey Β· Chenyu Li Β· Yanshan Wang
24 October 2025 at 12:00
arXiv:2510.20727v1 Announce Type: cross Abstract: Objective: Fluoropyrimidines are widely prescribed for colorectal and breast cancers, but are associated with toxicities such as hand-foot syndrome and cardiotoxicity. Since toxicity documentation is often embedded in clinical notes, we aimed to develop and evaluate natural language processing (NLP) methods to extract treatment and toxicity information. Materials and Methods: We constructed a gold-standard dataset of 236 clinical notes from 204,165 adult oncology patients. Domain experts annotated categories related to treatment regimens and toxicities. We developed rule-based, machine learning-based (Random Forest, Support Vector Machine [SVM], Logistic Regression [LR]), deep learning-based (BERT, ClinicalBERT), and large language models (LLM)-based NLP approaches (zero-shot and error-analysis prompting). Models used an 80:20 train-test split. Results: Sufficient data existed to train and evaluate 5 annotated categories. Error-analysis prompting achieved optimal precision, recall, and F1 scores (F1=1.000) for treatment and toxicities extraction, whereas zero-shot prompting reached F1=1.000 for treatment and F1=0.876 for toxicities extraction.LR and SVM ranked second for toxicities (F1=0.937). Deep learning underperformed, with BERT (F1=0.873 treatment; F1= 0.839 toxicities) and ClinicalBERT (F1=0.873 treatment; F1 = 0.886 toxicities). Rule-based methods served as our baseline with F1 scores of 0.857 in treatment and 0.858 in toxicities. Discussion: LMM-based approaches outperformed all others, followed by machine learning methods. Machine and deep learning approaches were limited by small training data and showed limited generalizability, particularly for rare categories. Conclusion: LLM-based NLP most effectively extracted fluoropyrimidine treatment and toxicity information from clinical notes, and has strong potential to support oncology research and pharmacovigilance.

Thought Communication in Multiagent Collaboration

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Yujia Zheng Β· Zhuokai Zhao Β· Zijian Li Β· Yaqi Xie Β· Mingze Gao Β· Lizhu Zhang Β· Kun Zhang
24 October 2025 at 12:00
arXiv:2510.20733v1 Announce Type: cross Abstract: Natural language has long enabled human cooperation, but its lossy, ambiguous, and indirect nature limits the potential of collective intelligence. While machines are not subject to these constraints, most LLM-based multi-agent systems still rely solely on natural language, exchanging tokens or their embeddings. To go beyond language, we introduce a new paradigm, thought communication, which enables agents to interact directly mind-to-mind, akin to telepathy. To uncover these latent thoughts in a principled way, we formalize the process as a general latent variable model, where agent states are generated by an unknown function of underlying thoughts. We prove that, in a nonparametric setting without auxiliary information, both shared and private latent thoughts between any pair of agents can be identified. Moreover, the global structure of thought sharing, including which agents share which thoughts and how these relationships are structured, can also be recovered with theoretical guarantees. Guided by the established theory, we develop a framework that extracts latent thoughts from all agents prior to communication and assigns each agent the relevant thoughts, along with their sharing patterns. This paradigm naturally extends beyond LLMs to all modalities, as most observational data arise from hidden generative processes. Experiments on both synthetic and real-world benchmarks validate the theory and demonstrate the collaborative advantages of thought communication. We hope this work illuminates the potential of leveraging the hidden world, as many challenges remain unsolvable through surface-level observation alone, regardless of compute or data scale.
❌