CodeMem: Architecting Reproducible Agents via Dynamic MCP and Procedural Memory
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909968372858880 |
|---|---|
| author | Gaurav, Nishant Akarsh, Adit Ravishankar, Tejas Bajaj, Manoj |
| author_facet | Gaurav, Nishant Akarsh, Adit Ravishankar, Tejas Bajaj, Manoj |
| contents | Current tool-using AI agents suffer from limited action space, context inefficiency, and probabilistic instability that makes them unsuitable for handling repetitive tasks which are otherwise reliably and efficiently tackled by agentic workflows built on platforms like n8n and Zapier. Earlier works like CodeAct, DynaSaur, Code Mode have tried to tackle the first two issues by using the whole Python language as its action space: The number of tools that the agent can call becomes infinite. Python code blocks can execute complex actions into a single step and print only relevant results which helps in keeping the context lean. However, the probabilistic instability issue still remains, as for the same task in the same environment, the agent can follow different trajectories due to the probabilistic nature of LLMs. Therefore, we need procedural memory for consistency and reliability. This paper proposes CodeMem, an architecture to implement procedural memory via code which can be used to build and run reusable agentic workflows with deterministic reliability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_15813 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CodeMem: Architecting Reproducible Agents via Dynamic MCP and Procedural Memory Gaurav, Nishant Akarsh, Adit Ravishankar, Tejas Bajaj, Manoj Software Engineering Artificial Intelligence Current tool-using AI agents suffer from limited action space, context inefficiency, and probabilistic instability that makes them unsuitable for handling repetitive tasks which are otherwise reliably and efficiently tackled by agentic workflows built on platforms like n8n and Zapier. Earlier works like CodeAct, DynaSaur, Code Mode have tried to tackle the first two issues by using the whole Python language as its action space: The number of tools that the agent can call becomes infinite. Python code blocks can execute complex actions into a single step and print only relevant results which helps in keeping the context lean. However, the probabilistic instability issue still remains, as for the same task in the same environment, the agent can follow different trajectories due to the probabilistic nature of LLMs. Therefore, we need procedural memory for consistency and reliability. This paper proposes CodeMem, an architecture to implement procedural memory via code which can be used to build and run reusable agentic workflows with deterministic reliability. |
| title | CodeMem: Architecting Reproducible Agents via Dynamic MCP and Procedural Memory |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2512.15813 |