An LLM multi-agent framework with critic feedback and knowledge-graph grounding achieves higher scores on a new 50-paper benchmark for materials hypothesis generation, but the evaluation is LLM-based and human validation is limited.
Expert_1, Expert_2, Expert_3, Expert_4, Expert_5
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Hypothesis Generation for Materials Discovery and Design Using Goal-Driven and Constraint-Guided LLM Agents
An LLM multi-agent framework with critic feedback and knowledge-graph grounding achieves higher scores on a new 50-paper benchmark for materials hypothesis generation, but the evaluation is LLM-based and human validation is limited.