Paper Detail

SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization

Qile Jiang, George Em Karniadakis

arxiv Score 6.2

Published 2026-11-05 · First seen 2026-11-07

General AI

Abstract

LLM-guided evolutionary search uses AI agents to improve programs for mathematical and computational problems by iteratively refining solutions and combining high-scoring methods. However, the process is often slow because the LLM generates a long textual chain of thought for each round and must repeat this generation many times to maintain population diversity. We present SwarmEvolve, a framework in which hundreds of low-cost agents per round work in swarms, reason in latent space without decoding to text, and share information by passing KV caches. Each swarm studies the problem from a different angle. A novelty filter keeps the most distinct agent ideas by directly measuring the distances between the agents' hidden state vectors. Crossover of ideas happens naturally in latent space, as a summarizer agent receives the combined KV caches of all swarm members. On 21 problems in mathematical discovery and scientific computing, SwarmEvolve gets the highest average score and needs a median of only 3 to 8 minutes to reach the best scores that other state-of-the-art frameworks reach in 60 minutes. On several problems, SwarmEvolve with Qwen3 8B improves on the solutions that AlphaEvolve first found with frontier LLMs. Our work shows that agent swarms that communicate in latent space offer a fast, low-cost approach to program search for scientific problems.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
later
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{jiang2026swarmevolve,
  title = {SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization},
  author = {Qile Jiang and George Em Karniadakis},
  year = {2026},
  abstract = {LLM-guided evolutionary search uses AI agents to improve programs for mathematical and computational problems by iteratively refining solutions and combining high-scoring methods. However, the process is often slow because the LLM generates a long textual chain of thought for each round and must repeat this generation many times to maintain population diversity. We present SwarmEvolve, a framework in which hundreds of low-cost agents per round work in swarms, reason in latent space without decod},
  url = {https://arxiv.org/abs/2611.08483},
  keywords = {cs.AI, cs.NE, code available, huggingface daily, Computer science, Crossover, Population, Novelty, Artificial intelligence},
  eprint = {2611.08483},
  archiveprefix = {arXiv},
}

Metadata

{}