Saved in:
Bibliographic Details
Main Authors: Bi, Dasheng, Hu, Yubin, Nasir, Mohammed N.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.22074
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913056040157184
author Bi, Dasheng
Hu, Yubin
Nasir, Mohammed N.
author_facet Bi, Dasheng
Hu, Yubin
Nasir, Mohammed N.
contents Learning how to do things from trial and error in real time is a hallmark of biological intelligence, yet most LLM-based agents lack mechanisms to acquire procedural knowledge after deployment. We propose Procedural Recall for Agents with eXperiences Indexed by State (PRAXIS), a lightweight post-training learning mechanism that stores the consequences of actions and retrieves them by jointly matching environmental and internal states of past episodes to the current state. PRAXIS augments agentic action selection with retrieved state-action-result exemplars that are generated in real time. When evaluated on the REAL web browsing benchmark, PRAXIS improves task completion accuracy, reliability, and cost efficiency across different foundation model backbones, and shows preliminary generalization to unseen tasks in similar environments. These results demonstrate that PRAXIS enables the practical adoption of AI agents in fast-evolving stateful environments by helping them learn new procedures effectively.
format Preprint
id arxiv_https___arxiv_org_abs_2511_22074
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Real-Time Procedural Learning From Experience for AI Agents
Bi, Dasheng
Hu, Yubin
Nasir, Mohammed N.
Artificial Intelligence
Information Retrieval
Learning how to do things from trial and error in real time is a hallmark of biological intelligence, yet most LLM-based agents lack mechanisms to acquire procedural knowledge after deployment. We propose Procedural Recall for Agents with eXperiences Indexed by State (PRAXIS), a lightweight post-training learning mechanism that stores the consequences of actions and retrieves them by jointly matching environmental and internal states of past episodes to the current state. PRAXIS augments agentic action selection with retrieved state-action-result exemplars that are generated in real time. When evaluated on the REAL web browsing benchmark, PRAXIS improves task completion accuracy, reliability, and cost efficiency across different foundation model backbones, and shows preliminary generalization to unseen tasks in similar environments. These results demonstrate that PRAXIS enables the practical adoption of AI agents in fast-evolving stateful environments by helping them learn new procedures effectively.
title Real-Time Procedural Learning From Experience for AI Agents
topic Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2511.22074