Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agents
Quick Answer
This paper shows that HORMA, a Hierarchical Organize-and-Retrieve Memory Agent, enhances long-horizon task performance in LLMs by organizing experiences hierarchically, achieving up to 22.17% of baseline token usage while improving efficiency and generalization across benchmarks like ALFWorld and LoCoMo.
Quick Take
HORMA, a Hierarchical Organize-and-Retrieve Memory Agent, enhances long-horizon task performance in LLMs by organizing experiences hierarchically, achieving up to 22.17% of baseline token usage while improving efficiency and generalization across benchmarks like ALFWorld and LoCoMo.
Key Points
- HORMA organizes experiences in a hierarchical structure for efficient memory retrieval.
- It reduces latency by using a lightweight agent trained with reinforcement learning.
- Achieves better efficiency-performance trade-offs compared to existing methods.
- Improves task performance under constrained context budgets across multiple benchmarks.
- Utilizes only 22.17% of baseline token usage in long conversation tasks.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 11680v1 Announce Type: new Abstract: Large language model (LLM) agents struggle with long-horizon tasks due to their inherent statelessness, requiring all task-relevant information to be encoded in growing input contexts. The resulting degraded reasoning quality, increased inference cost, and higher latency necessitate efficient working memory mechanisms.
However, existing approaches either rely on lossy compression or similarity-based retrieval, which often fail to capture temporal structure and causal dependencies required for multi-step agentic tasks. In this work, we present HORMA, a Hierarchical Organize-and-Retrieve Memory Agent that organizes experience into a file-system-like hierarchical structure, where summarized entities are linked to the corresponding raw trajectories, enabling efficient access without losing detailed information.
HORMA decomposes working memory into two stages: structured memory construction and navigation-based retrieval. The construction module iteratively refines how experiences are structured by distinguishing between failures caused by missing information and those caused by misleading or overloaded context.
The navigation module retrieves task-relevant context by traversing the hierarchy using a lightweight agent trained with reinforcement learning to select minimal yet sufficient context, thereby reducing latency along the critical execution path. Across ALFWorld, LoCoMo, and LongMemEval, HORMA improves task performance under constrained context budgets while requiring at most 22. 17% of the baseline token usage in long conversation tasks.
Compared to existing methods, it consistently achieves better efficiency-performance trade-offs and generalizes effectively to unseen tasks.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →Arbor: Tree Search as a Cognition Layer for Autonomous Agents
Arbor introduces a multi-agent framework utilizing structured tree search for optimizing LLM inference, achieving up to 193% throughput-latency improvement compared to vendor-optimized systems. It employs an Orchestrator and Critic agent for stability and coordination, demonstrating hardware-agnostic performance with minimal variance.