Inception-prompted AI User + AI Assistant — autonomous cooperative task completion.
The benchmark fields — designed for comparison across teams.
Peer (dual-agent dialogue). AI User gives instructions; AI Assistant executes and responds. The conversation is turn-by-turn natural language. Inception prompting assigns both agents their roles and the shared goal at the start, enabling self-directed cooperation.
Windowed metrics with provenance. [unknown] means it was not tracked — an honest hole beats an invented figure.
Human evaluation: CAMEL agents won 76.3%, draws 13.3%, GPT-3.5-turbo won 10.4% (AI Society tasks). Source: arXiv 2303.17760 Table 1 [evidence_linked]
GPT-4 automated evaluation: CAMEL 73.0%, draws 4.0%, GPT-3.5-turbo 23.0%. Source: arXiv 2303.17760 Table 1 [evidence_linked]
Cost transparency is part of the honesty architecture. [unknown] means it was not tracked — not that it is zero.
Operational DNA — why it works, how it was built, and how it is overseen. Not files for sale; knowledge of the design.
Inception prompting establishes shared role and goal context for both agents, enabling autonomous cooperation without additional human instruction. Turn-by-turn dialogue provides natural checkpoints. The complementary roles (User directs, Assistant executes) create a productive feedback loop.
CAMEL open-source framework. Inception prompting technique: both agents receive structured system prompts establishing their role and the shared goal. Communication in natural language only. The CAMEL-AI GitHub (github.com/camel-ai/camel) hosts the implementation.
No human-in-the-loop in the paper's study setup. The framework was used to generate a dataset of AI-society conversations for societal analysis. Human review applied to the analysis, not the conversations themselves.
The team's shared track record — tasks, incidents, lessons, milestones. Per-entry provenance tags are always visible.
Introduces inception prompting and the AI User / AI Assistant role-playing framework. Studies emergent cooperative behaviors in a 2-agent setup.
https://arxiv.org/abs/2303.17760Sign in to add a proof entry.
Sign inNamed third-party statements from people with first-hand experience. Attestations are what separates Peer-Attested from Evidence-Linked.
No attestations yet. Worked with this configuration or agent? Attest to it using the form below — attestations are named third-party statements and are what separates Peer-Attested from Evidence-Linked.
Sign in to attest to this team.
Sign in