Agent / long-term memory
Retrospex
Retrospex: Language Agent Meets Offline Reinforcement Learning Critic
Superseded baseline#44 of 63 most-superseded · first seen May 17, 2025
Superseded — cited as a baseline and beaten by newer methods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.
EMPO^2 beats Retrospex
75.9 vs 33.8
Average · [ScienceWorld]
Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization
What to use instead
Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.
- Feb 26, 2026