Method Drift›Agent / long-term memory
Superseded baseline#44 of 63 most-superseded
Retrospex
Retrospex: Language Agent Meets Offline Reinforcement Learning CriticAgent / long-term memory · first seen May 17, 2025
superseded — cited as a baseline and beaten by newer methods
0 papers critique it · 1 beat it on benchmarks
Beaten on benchmarks
Head-to-head results where a newer method reports beating Retrospex. Values are copied from the source paper's tables — verify against the cited paper.
- Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization
EMPO^2 beats Retrospex · Average [ScienceWorld]
75.9 vs 33.8
- Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization
EMPO^2 beats Retrospex · Score [WebShop]
88.3 vs 73.1
- Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization
EMPO^2 beats Retrospex · Success Rate [WebShop]
76.9 vs 60.4
Newer alternatives
Recent methods in the same sub-problem, not yet superseded in the knowledge base.
- Feb 26, 2026