EIG represents research ideas as evolving graphs with nodes for claims and edges for relations, using a learned controller for edits and commits to produce higher-quality scientific proposals than text-only multi-agent baselines.
CAMEL: Communicative agents for ”mind” exploration of large language model society
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.MA 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Systematic study of inter-agent communication in LLM multi-agent systems shows reasoning and verification are critical for performance, with a new augmentation technique recovering 86.2% of failures.
citing papers explorer
-
Evolving Idea Graphs with Learnable Edits-and-Commits for Multi-Agent Scientific Ideation
EIG represents research ideas as evolving graphs with nodes for claims and edges for relations, using a learned controller for edits and commits to produce higher-quality scientific proposals than text-only multi-agent baselines.
-
What Do Agents Communicate? Characterizing Information Exchange in Multi-Agent Systems
Systematic study of inter-agent communication in LLM multi-agent systems shows reasoning and verification are critical for performance, with a new augmentation technique recovering 86.2% of failures.