Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.15642 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915867715960832 |
|---|---|
| author | Mody, Pearl Panchal, Mihir Kar, Rishit Bhowmick, Kiran Karani, Ruhina |
| author_facet | Mody, Pearl Panchal, Mihir Kar, Rishit Bhowmick, Kiran Karani, Ruhina |
| contents | Large language model (LLM) agents are increasingly deployed in long running workflows, where they must preserve user and task state across many turns. Many existing agent memory systems behave like external databases with ad hoc read/write rules, which can yield unstable retention, limited consolidation, and vulnerability to distractor content. We present CraniMem, a neurocognitively motivated, gated and bounded multi-stage memory design for agentic systems. CraniMem couples goal conditioned gating and utility tagging with a bounded episodic buffer for near term continuity and a structured long-term knowledge graph for durable semantic recall. A scheduled consolidation loop replays high utility traces into the graph while pruning low utility items, keeping memory growth in check and reducing interference. On long horizon benchmarks evaluated under both clean inputs and injected noise, CraniMem is more robust than a Vanilla RAG and Mem0 baseline and exhibits smaller performance drops under distraction. Our code is available at https://github.com/PearlMody05/Cranimem and the accompanying PyPI package at https://pypi.org/project/cranimem. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_15642 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CraniMem: Cranial Inspired Gated and Bounded Memory for Agentic Systems Mody, Pearl Panchal, Mihir Kar, Rishit Bhowmick, Kiran Karani, Ruhina Artificial Intelligence Large language model (LLM) agents are increasingly deployed in long running workflows, where they must preserve user and task state across many turns. Many existing agent memory systems behave like external databases with ad hoc read/write rules, which can yield unstable retention, limited consolidation, and vulnerability to distractor content. We present CraniMem, a neurocognitively motivated, gated and bounded multi-stage memory design for agentic systems. CraniMem couples goal conditioned gating and utility tagging with a bounded episodic buffer for near term continuity and a structured long-term knowledge graph for durable semantic recall. A scheduled consolidation loop replays high utility traces into the graph while pruning low utility items, keeping memory growth in check and reducing interference. On long horizon benchmarks evaluated under both clean inputs and injected noise, CraniMem is more robust than a Vanilla RAG and Mem0 baseline and exhibits smaller performance drops under distraction. Our code is available at https://github.com/PearlMody05/Cranimem and the accompanying PyPI package at https://pypi.org/project/cranimem. |
| title | CraniMem: Cranial Inspired Gated and Bounded Memory for Agentic Systems |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2603.15642 |