MetaCogAgent: A Metacognitive Multi-Agent LLM Framework with Self-Aware Task Delegation
The article introduces MetaCogAgent, a multi-agent large language model framework designed to enhance task delegation through self-awareness. It incorporates a Metacognitive Self-Assessment Unit that allows agents to evaluate their own capabilities before undertaking tasks. Experimental results indicate that this framework significantly improves task accuracy while reducing API calls compared to existing methods.
- ▪MetaCogAgent utilizes a self-assessment mechanism to estimate task confidence.
- ▪The framework features an adaptive delegation protocol for routing tasks to suitable agents.
- ▪Experiments show that MetaCogAgent achieves 82.4% task accuracy, outperforming the best routing baseline by 8.7%.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2605.17292 |
| Publication time | Tue, 19 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-19T04:04:57.272Z |
| Last seen | 2026-05-19T04:04:57.272Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | ORQmtpPDmins · 2 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2605.17292 (cs) [Submitted on 17 May 2026] Title:MetaCogAgent: A Metacognitive Multi-Agent LLM Framework with Self-Aware Task Delegation Authors:Chenyu Wang, Yang Shu View a PDF of the paper titled MetaCogAgent: A Metacognitive Multi-Agent LLM Framework with Self-Aware Task Delegation, by Chenyu Wang and 1 other authors View PDF HTML (experimental) Abstract:Multi-agent large language model (LLM) systems have shown promise for solving complex tasks through agent collaboration. However, existing frameworks assign tasks based on predefined roles without considering whether an agent can accurately assess its own competence boundaries, leading to overconfident execution on tasks beyond its expertise.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
