reflexion-agent-episodic-memory
IN premise — entries/2026/06/21/wiki-Large_language_model.md
Created 2026-06-21T09:50:09+00:00
The Reflexion agent method uses episodic 'lessons learned' as long-term memory across multiple episodes
Summary
The Reflexion agent keeps a running log of its own after-action notes from each task attempt and pulls from that log in later attempts, so it gradually improves without any external retraining. This means its performance in any given episode is partly shaped by how well it reflected on earlier ones, making the quality of those self-generated summaries a critical dependency for ongoing progress.
Dependents
These beliefs depend on this one:
- IN agentic-memory-spans-three-temporal-levels — Several techniques address memory coherence at different temporal scales in agentic LLM systems: Ghost Attention supports intra-turn consistency by concatenating system instructions to each user message (with loss zeroed on prompt tokens), Reflexion accumulates episodic 'lessons learned' across multiple attempts, and Dreaming (a May 2026 research preview) consolidates persistent memory between sessions by merging duplicates and removing stale entries — suggesting a pattern where different temporal horizons of agent continuity may benefit from distinct mechanisms.