RRO samples LLM agent actions until a step shows a rising process reward, converts those steps into DPO preference pairs, and reports modest gains on WebShop and InterCode-SQL with fewer samples.
Complexity-based prompting for multi-step reasoning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
RRO: LLM Agent Optimization Through Rising Reward Trajectories
RRO samples LLM agent actions until a step shows a rising process reward, converts those steps into DPO preference pairs, and reports modest gains on WebShop and InterCode-SQL with fewer samples.