Reproduce “Symbolic Guidance for LLM Agents in Distributed Multiagent Coordination” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Ben Rachmut, Ning Zhang, Yevgeniy Vorobeychik, William Yeoh
The Symbolic Guidance Taxonomy evaluates how LLM agents coordinate on graph tasks with varying forms of algorithmic guidance. It ranges from task instructions alone to pseudocode and algorithm execution, testing local heuristics and distributed search. For Gemini-2.5 on global 3-coloring, function-pseudocode guidance scores 1.56 ± 0.24 versus 2.35 ± 0.33 without guidance; results vary by model and task.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.