# A Benchmark for Procedural Memory Retrieval in Language Agents

arXiv: https://arxiv.org/abs/2511.21730 · HTML: https://mlsanity.com/paper/2511.21730/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 18 references that are in the map.
- First posted on arXiv 21 Nov 2025.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 14 of 14)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [MIRIX: Multi-Agent Memory System for LLM-Based Agents](https://mlsanity.com/paper/2507.07957/) (2025)
- [ACON: Optimizing Context Compression for Long-horizon LLM Agents](https://mlsanity.com/paper/2510.00615/) (2025)
- [LEGOMem: Modular Procedural Memory for Multi-agent LLM Systems for Workflow Automation](https://mlsanity.com/paper/2510.04851/) (2025)
- [Trajectory Prediction Meets Large Language Models: A Survey](https://mlsanity.com/paper/2506.03408/) (2025)
- [PAL-UI: Planning with Active Look-back for Vision-Based GUI Agents](https://mlsanity.com/paper/2510.00413/) (2025)
- [Procedural Memory Is Not All You Need: Bridging Cognitive Gaps in LLM-Based Agents](https://mlsanity.com/paper/2505.03434/) (2025)
- [TRACE: Grounding Time Series in Context for Multimodal Embedding and Retrieval](https://mlsanity.com/paper/2506.09114/) (2025)
- [TrajAgent: An LLM-Agent Framework for Trajectory Modeling via Large-and-Small Model Collaboration](https://mlsanity.com/paper/2410.20445/) (2024)

## Built on by (most cited first, 4 of 4)

- [A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents](https://mlsanity.com/paper/2602.06052/) (2026)
- [AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents](https://mlsanity.com/paper/2512.23343/) (2025)
- [LMEB: Long-horizon Memory Embedding Benchmark](https://mlsanity.com/paper/2603.12572/) (2026)
- [Retrieved but not ranked: surface-form bias in structural retrieval, from mathematics to agent trajectories](https://mlsanity.com/paper/2609.01556/) (2026)

## Abstract (arXiv)

Current AI agents excel in familiar settings, but fail sharply when faced with novel tasks with unseen vocabularies -- a core limitation of procedural memory systems. We present the first benchmark that isolates procedural memory retrieval from task execution, evaluating whether agents can recognize functionally equivalent procedures that span different object instantiations. Using ALFWorld, we construct dual corpora of expert and LLM-generated trajectories and evaluate six retrieval methods using systematically stratified queries. Our results expose a clear generalization cliff: embedding-based methods perform strongly on familiar contexts, yet degrade considerably on novel ones, while LLM-generated procedural abstractions demonstrate reliable cross-context transfer. Controlled ablations show that although embeddings capture some lexical-level abstraction, they fundamentally treat procedures as unordered bags of words, discarding temporal structure necessary for cross-context transfer. Corpus scale delivers far larger gains than representation enrichment, revealing an architectural ceiling in current encoders. Our benchmark offers the first diagnostic framework separating genuine procedural understanding from surface-level memorization and gives tools for developing retrieval systems capable of dependable generalization. Resources available at our GitHub repository (https://github.com/qpiai/Proced_mem_bench).