APEX maintains an explicit strategy space via a DAG with fork discovery and policy selection to sustain exploration in self-evolving LLM agents and reports outperformance on Jericho games and WebArena.
Reflexion: language agents with verbal reinforcement learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
APEX: Autonomous Policy Exploration for Self-Evolving LLM Agents
APEX maintains an explicit strategy space via a DAG with fork discovery and policy selection to sustain exploration in self-evolving LLM agents and reports outperformance on Jericho games and WebArena.