ARMOR improves reaction feasibility prediction by adaptively prioritizing tools based on learned utilities and resolving conflicts with memory-augmented reasoning, outperforming single-tool and simple aggregation baselines especially on conflicting cases.
We also include closed-source LLMs, including GPT-5.4-mini (Singh et al., 2025), DeepSeek-v4-flash (DeepSeek-AI
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ARMOR: An Agentic Framework for Reaction Feasibility Prediction via Adaptive Utility-aware Multi-tool Reasoning
ARMOR improves reaction feasibility prediction by adaptively prioritizing tools based on learned utilities and resolving conflicts with memory-augmented reasoning, outperforming single-tool and simple aggregation baselines especially on conflicting cases.