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 TurbopolicyNoNot recorded: verify in the paper/code
text-davinci-003criticNoNot recorded: verify in the paper/code
Llama 2 70B ChatbaselineNoNot recorded: verify in the paper/code

CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing

2023-05-19 · Verified

Paper info

Evolution targets
Self-correction, Tool use
Benchmark
HotpotQA, GSM8K, HumanEval
Category
Self-evolving agent, Reflection, Tool use
Model relations
3
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.

Policy
GPT-3.5 Turbo
Critic
text-davinci-003
Baseline
Llama 2 70B Chat

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

Policy · weights not updated · GPT-3.5 Turbo as initial generator corrected via tool-interactive critique.

text-davinci-003

Critic · weights not updated · text-davinci-003 evaluated as a CRITIC backbone.

GPT-3.5

Llama 2 70B Chat

Baseline · weights not updated · Llama-2-70B-Chat evaluated as open-source CRITIC backbone.