[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85283-en":3,"doc-seo-85283-105":29,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},85283,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Flout at Your Own Risk: LLMs Struggle with Pragmatic Cooperativity Under Epistemic Asymmetry","Fruitful collaboration depends on cooperative communication, including appropriate use of contextual cues in reasoning. With the growing deployment of LLMs in collaborative and agentic pipelines, it becomes crucial to test whether they exhibit pragmatic cooperativity when collaborators possess different knowledge. This paper studies multi-party collaborative reasoning under partial information, formalizes collaborative epistemic asymmetry linking task success to Grice’s cooperative principle, and evaluates LLM speaker/listener behavior via prompting and post-training. Results reveal pragmatic abilities plus persistent failures when information is incomplete.","arXiv :2607 . 1 1053v 1 [ cs .CL] 13 Jul 2026  \nFlout at Your Own Risk: LLMs Struggle with Pragmatic Cooperativity Under Epistemic Asymmetry  \nHannah VanderHoeven, Abhijnan Nath & Nikhil Krishnaswamy  \nSituated Grounding and Natural Language (SIGNAL) Lab Department of Computer Science  \nColorado State University Fort Collins, CO 80523, USA  \n{hannah.vanderhoeven,[nkrishna](nkrishna}@colostate.edu)[}](nkrishna}@colostate.edu)[@colostate.edu](nkrishna}@colostate.edu)  \nAbstract  \nFruitful collaborations rely on cooperative communications, including of contextual cues to incorporate into reasoning. The increasing use of LLMs in collaborative and agentic pipelines raises questions about the extent to which they exhibit these pragmatic capabilities, especially in scenarios where they may not have access to the same information as their collaborators. In this paper, we perform a novel investigation into the pragmatic reasoning capabilities of LLMs in a multi-party collaborative task under partial information conditions. We formalize a notion of collaborative epistemic asymmetry that explicitly connects objective task success to Grice’s cooperative principle and empirically assess various LLMs’ abilities to act cooperatively as both speakers and listeners, including both prompting and post-training strategies. Our results show that while LLMs exhibit certain pragmatic capabilities in collaborative settings, and these can be elicited through prompting and post-training, they still face challenges in pragmatic communication with incomplete information, and that certain failure modes do correlate with floutings of Grice’s maxims that go unrecognized.  \n1 Introduction  \nSuccessful collaboration rests on establishing common ground (Clark & Brennan, 1991; Clark, 1996). Collaborative groups can achieve outcomes exceeding the abilities and understanding of any individual member (Boyd, 2021), but only if they can effectively share perspectives. Inherent in this is the adjustment of communications to be cooperative—expressing no more or less than the needed information, at the right time, in the appropriate way (Grice, 1975) .  \nThe dialogue capabilities of large language models (LLMs) have led them to be incorporated into workflows across many domains, often as “collaborators” with humans, or with other AI systems in “agentic” pipelines (Butler et al., 2025; Maslej et al., 2025) . In large part this has come about because they appear to be fluent, cooperative communicators; the implicit assumption is that LLMs and agentic systems driven by them will exchange information and interpret collaborator needs and instructions in a way that is roughly equivalent to the cooperativity exhibited by humans (Zarrieß & Schlangen, 2019; Guo et al., 2026) . However, evidence regarding the pragmatic competence of LLMs is mixed at best (Nguyen, 2023; Jian & Siddharth, 2024; Park et al., 2024; Sravanthi et al., 2024; Ma et al., 2025a;b; Eisenstein et al., 2026; Nath et al., 2026) . This calls into question whether current LLMs truly possess the pragmatic capabilities required to be good collaborators, or if their apparent demonstrations of pragmatic competence are illusory. This question is particularly relevant in multiparty collaborations with more than 2 agents (human or AI), because each agent may labor under”false assumptions” about other agents and how they communicate.  \nThis paper presents a first of its kind examination of common LLMs’ cooperative communication capabilities in a challenging multi-agent, partially-observable collaborative reasoning task. Fig. 1 shows an overview of our approach. Through a focus on agentagent collaborations, we address the following research questions. RQ1: In multiagent  \nCRAFT Environment  \nLiteral Builder prompt  \nPragmatic Builder prompt  \nDirector Model  \nActionable Progress  \nD1  \nD2  \nD3  \nBuilder Model  \nSFT  \nDPO  \nIPO  \nFigure 1: High level overview of our experimental pipeline.  \ncollaborations, do common LLMs","cbCainRFpLFESpzy","https://ap.wps.com/l/cbCainRFpLFESpzy","pdf",10511652,1,32,"English","en",105,"# Introduction\n# Related Work","[{\"question\":\"What problem does the paper investigate about LLM collaboration?\",\"answer\":\"It investigates how well common LLMs cooperate pragmatically in multi-party collaborative tasks when agents do not have access to the same information.\"},{\"question\":\"How does the paper formalize the collaboration setting and connect it to communication theory?\",\"answer\":\"It introduces collaborative epistemic asymmetry and explicitly links objective task success to Grice’s cooperative principle and conversational maxims.\"},{\"question\":\"What do the results show about LLM pragmatic behavior under incomplete information?\",\"answer\":\"LLMs can exhibit some pragmatic speaking and listening capabilities that improve with prompting and post-training, but they still struggle to cooperate when information is incomplete, with failure modes correlating to unrecognized floutings of Gricean maxims.\"}]",1784202251,81,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"flout-at-your-own-risk-llms-struggle-with-pragmatic-cooperativity-under-epistemic-asymmetry","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/flout-at-your-own-risk-llms-struggle-with-pragmatic-cooperativity-under-epistemic-asymmetry/85283/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What problem does the paper investigate about LLM collaboration?","Question",{"text":74,"@type":75},"It investigates how well common LLMs cooperate pragmatically in multi-party collaborative tasks when agents do not have access to the same information.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does the paper formalize the collaboration setting and connect it to communication theory?",{"text":79,"@type":75},"It introduces collaborative epistemic asymmetry and explicitly links objective task success to Grice’s cooperative principle and conversational maxims.",{"name":81,"@type":72,"acceptedAnswer":82},"What do the results show about LLM pragmatic behavior under incomplete information?",{"text":83,"@type":75},"LLMs can exhibit some pragmatic speaking and listening capabilities that improve with prompting and post-training, but they still struggle to cooperate when information is incomplete, with failure modes correlating to unrecognized floutings of Gricean maxims.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]