Model AtlasA selection map of agent foundation models 中文
Start researchModelsPapersGuideCompare 中文

Search the atlas

Esc to close · Cmd/Ctrl + K to open

Why these models were selected

Roles and weight updates come from the paper case record. Selection reasons are written only when the paper or code states them; unknown is never inferred as fact.

Paper model roles and selection-evidence status
ModelRoleWeights updatedSelection basis
GPT-3.5 TurboactorNoNot recorded: verify in the paper/code
GPT-4criticNoNot recorded: verify in the paper/code

AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors

2023-08-21 · Verified

Paper info

Evolution targets
Multi-agent roles, Actor policy
Benchmark
ALFWorld, Minecraft, Multi-Agent Reasoning
Category
Multi-agent, Self-evolving agent, Tool use
Model relations
2
Paper link ↗Code link ↗

Start research from this paper

Choose a research mode to carry this paper into the workspace context.

Strict reproductionMethod reproductionModern rerun

Reproducibility status

Code Not verified
Checkpoint Not verified
Config Not verified
Environment Not verified

No structured reproducibility record has been added yet.

Model-role topology

This view only shows recorded model-role relations; it does not invent workflow edges.

Actor
GPT-3.5 Turbo
Critic
GPT-4

This paper record has no workflow edges; the topology above only shows recorded roles and does not treat Actor, Environment, Critic, or Optimizer relations as facts.

Model roles

GPT-3.5 Turbo

Actor · weights not updated · GPT-3.5 Turbo acts as multi-agent collaboration policy.

GPT-4

Critic · weights not updated · GPT-4 used for higher-capability agent roles / evaluation.