This repository accompanies research on improving language model factuality and reasoning through multi-agent debate.
Suspicion Agent
This repository implements a GPT-4 agent for playing imperfect information games with theory of mind.
About Suspicion Agent
Suspicion Agent is a Python code repository that implements a GPT-4 agent for playing imperfect information games with theory of mind. It is the implementation accompanying the paper "Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4" (arXiv 2309.17277). The README gives installation steps (Python 3.8.5 or later and the packages in requirements.txt), describes setting up an OpenAI key, and provides a command to train and evaluate agents against rule-based baseline models.
Using the agent requires an OpenAI API key, so gameplay with GPT-4 depends on an external service. The README is brief and centers on setup and one run command.
Key features
- GPT-4 agent for playing imperfect information games with theory of mind
- Command-line script comparing the agent against baseline models
- Baseline options: cfr, nfsp, dqn, and dmc rule models
- Separate folders for game configuration and person configuration files
- Retriever and context modules used by the agent code
- Sample output and game data files included in the repository
Best for: Researchers studying large language model agents, theory of mind, and decision-making in imperfect information games.
Good for
- Directly tied to a published paper, with a citation provided in the README
- A single documented command runs comparisons against four baseline rule models
Watch out for
- Requires an OpenAI API key, so GPT-4 use depends on an external service
- Requires Python 3.8.5 or later
- The README covers installation and one run command, with limited further documentation
Suspicion Agent at a glance
- Category
- AI & Machine Learning › Models & ML Research
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Not stated
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
Suspicion Agent alternatives
Tools and sites you could use instead, ranked by how closely they match.
DeepSWE benchmarks coding agents on original, long-horizon software engineering tasks.
Open source
24 alternatives
MobiLlama is a small language model designed for edge devices, according to its repository description.
Open source
24 alternatives
This repository contains the DeepSeek-V3 language model project and related source files.
Open source
24 alternatives
This repository contains Google Research code for the Flan-T5 language model project.
Open source
24 alternatives
ImageBind explores a shared embedding space that connects different kinds of data.
Popular in Models & ML Research
Well-known listings from the same topic.
Falcon LLMfalconllm.tii.aeERNIEernie.baidu.comTokenVersetoken-verse.github.iowTAObittensor.comAlpacacrfm.stanford.edu/2023/03/13/alpaca.htmlSmolVLAhuggingface.co/blog/smolvla
Suspicion Agent FAQ
What do I need to run the code?
The README lists Python 3.8.5 or later, installation of the packages in requirements.txt, and an OpenAI key set up as described in the README.
Which baseline models can the agent be compared against?
The run command accepts cfr, nfsp, dqn, or dmc as the rule model option.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.