{
  "id": 11848,
  "url": "https://arxiv.org/abs/2607.16062v1",
  "title": "When Model Merging Rivals Joint Multi-Task Reinforcement Learning: A Task-Vector Geometry Analysis",
  "summary": "Model merging is promoted as a substitute for joint multi-task training, yet in the reinforcement-learning setting this substitution is essentially never tested against the baseline it claims to replace: methods merge independently released agents precisely because a joint model is unavailable. We build the missing comparison. Training difficulty-1 and difficulty-2 Qwen3-8B specialists on the AppWorld agent benchmark with LOOP, we merge them (TIES, RAM+) and pit the result against a jointly trai",
  "authors": "S. Aaron McClendon",
  "category": "research",
  "topics": "agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-17T15:41:09.000Z",
  "fetched_at": "2026-07-20T05:10:09.534Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/11848",
  "original_url": "https://arxiv.org/abs/2607.16062v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}