arXiv:2604.20987  (cs)
 



 

  Authors:  Xiyang Wu ,  Zongxia Li ,  Guangyao Shi ,  Alexander Duffy ,  Tyler Marques ,  Matthew Lyle Olson ,  Tianyi Zhou ,  Dinesh Manocha               View a PDF of the paper titled Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks, by Xiyang Wu and 7 other authors 
 View PDF 

 
         Abstract: Long horizon interactive environments are a testbed for evaluating agents skill usage abilities. These environments demand multi step reasoning, the chaining of multiple skills over many timesteps, and robust decision making under delayed rewards and partial observability. Games are a good testbed for evaluating agent skill usage in environments. Large Language Models (LLMs) offer a promising alternative as game playing agents, but they often struggle with consistent long horizon decision making because they lack a mechanism to discover, retain, and reuse structured skills across episodes. We present COSPLAY, a co evolution framework in which an LLM decision agent retrieves skills from a learnable skill bank to guide action taking, while an agent managed skill pipeline discovers reusable skills from the agents unlabeled rollouts to form a skill bank. Our framework improves both the decision agent to learn better skill retrieval and action generation, while the skill bank agent continually extracts, refines, and updates skills together with their contracts. Experiments across six game environments show that COSPLAY with an 8B base model achieves over 25.1 percent average reward improvement against four frontier LLM baselines on single player game benchmarks while remaining competitive on multi player social reasoning games.
 

 
 
            
       Comments: 
       26 pages 
     

       Subjects: 
       
         Artificial Intelligence (cs.AI)  
      
       Cite as: 
         arXiv:2604.20987  [cs.AI]  
     
     
         
       (or  
           arXiv:2604.20987v1  [cs.AI]  for this version)
       
     
     
         
                      https://doi.org/10.48550/arXiv.2604.20987  
           
             Focus to learn more 
           
           
           
                                arXiv-issued DOI via DataCite (pending registration) 
         
       
      
 


 
  

   Full-text links: 
  

       view license 
      
 
      

 new 
  |  
 recent 
  |   2026-04 

Change to browse by:
 
     cs  
 


 
   
    

        NASA ADS    Google Scholar  
        Semantic Scholar  
     
      
   


 export BibTeX citation 
 Loading... 



 
     
        

         × 
     
     
         loading... 
     
     
         Data provided by:  
          
     
 

 Bibliographic Tools 
 
  

           Bibliographic Explorer Toggle 
         
       
       
         Bibliographic Explorer   ( What is the Explorer? ) 
       
     
     
       
         
           
            
           Connected Papers Toggle 
         
       
       
         Connected Papers   ( What is Connected Papers? ) 
       
      
       
         
           
            
           Litmaps Toggle 
         
       
       
         Litmaps   ( What is Litmaps? ) 
       
     
     
       
         
           
            
           scite.ai Toggle 
         
       
       
         scite Smart Citations   ( What are Smart Citations? ) 
       
     
   
      
      
      
      
 

 
 Code, Data, Media 
 
  

           alphaXiv Toggle 
         
       
       
         alphaXiv   ( What is alphaXiv? ) 
       
     

     
       
         
           
            
           Links to Code Toggle 
         
       
       
         CatalyzeX Code Finder for Papers   ( What is CatalyzeX? ) 
       
     

     
       
         
           
            
           DagsHub Toggle 
         
       
       
         DagsHub   ( What is DagsHub? ) 
       
     

     
       
         
           
            
           GotitPub Toggle 
         
       
       
         Gotit.pub   ( What is GotitPub? ) 
       
     

     
       
         
           
            
           Huggingface Toggle 
         
       
       
         Hugging Face   ( What is Huggingface? ) 
       
     

     
       
         
           
            
           ScienceCast Toggle 
         
       
       
         ScienceCast   ( What is ScienceCast? ) 
       
     
   

    
    
    
    
    
    
 

   
   Demos 
   
    

             Replicate Toggle 
           
         
         
           Replicate   ( What is Replicate? ) 
         
       
       
         
           
             
              
             Spaces Toggle 
           
         
         
           Hugging Face Spaces   ( What is Spaces? ) 
         
       
       
         
           
             
              
             Spaces Toggle 
           
         
         
           TXYZ.AI   ( What is TXYZ.AI? ) 
         
       
     
      
      
      
   
   
   Related Papers 
   
    

             Link to Influence Flower 
           
         
         
           Influence Flower   ( What are Influence Flowers? ) 
         
       
       
         
           
             
              
             Core recommender toggle 
           
         
         
           CORE Recommender   ( What is CORE? ) 
         
        
      
     
       
          Author  
          Venue  
          Institution  
          Topic  
       
       
            
            
            
            
       
     
      
      
   

   
   
    About arXivLabs
   
   
     
       
        

         arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

        Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

        Have an idea for a project that will add value for arXiv's community?   Learn more about arXivLabs  .

       
       
        

       
     
   

 



 Which authors of this paper are endorsers?  |
 Disable MathJax  ( What is MathJax? )