RefEvo achieves 95% pass rate on 20 hardware modules for SystemC reference model generation using dynamic multi-agent planning, co-evolutionary verification, and spec anchoring, with 71% token reduction.
Divergent thoughts toward one goal: LLM-based multi-agent collaboration system for electronic design automation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
RefEvo: Agentic Design with Co-Evolutionary Verification for Agile Reference Model Generation
RefEvo achieves 95% pass rate on 20 hardware modules for SystemC reference model generation using dynamic multi-agent planning, co-evolutionary verification, and spec anchoring, with 71% token reduction.