agent/papers/items/2026-2605-16233-forge-self-evolving-agent-memory-with-no-weight-updates-via-population-broadcast.md

Paper: FORGE: Self-Evolving Agent Memory With No Weight Updates via Population Broadcast

---

type: paper title: "FORGE: Self-Evolving Agent Memory With No Weight Updates via Population Broadcast" authors: Igor Bogdanov, Chung-Horng Lung, Thomas Kunz, Jie Gao, Adrian Taylor, Marzia Zaman year: 2026 venue: arXiv url: https://arxiv.org/abs/2605.16233 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-05-15 updated_at: 2026-05-15 status: queued relevance: high topics:

• agent-evaluation
• memory
• rag
• reasoning methods:

benchmarks:

models:

datasets:

• cs.AI
• cs.CL
• cs.LG
• cs.MA
• eess.SY related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 16 collection_queries: agent-memory

One-line Takeaway

Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.

Why Collected

• matched queries: agent-memory
• inferred topics: agent-evaluation, memory, rag, reasoning
• arXiv categories: cs.AI, cs.CL, cs.LG, cs.MA, eess.SY
• collection score: 16

Review Checklist

• Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
• Does it include a benchmark, dataset, code, or reproducible experimental setup?
• Should it be promoted from queued to skimmed or summarized?

Links

• arXiv: https://arxiv.org/abs/2605.16233