v0.5.1-alpha

KeygraphHQ/shannonv0.5.1-alphaJul 16, 2025by paulosalem

AI Summary

This release accompanies the publication of the TinyTroupe paper, introducing parallel execution for agents and factories, and adding an @llm decorator for easier LLM integration and verification propositions.

Key Highlights

Release of TinyTroupe paper (preprint) on arXiv
TinyPersons now include action correction mechanisms
Parallel generation of agents in TinyPersonFactory
Parallel execution of agents in TinyWorld
Introduction of InPlaceExperimentRunner for controlled experiments

New Features

TinyPersons action correction mechanisms for persona adherence
Parallel agent generation using a plan-based approach
Parallel execution within simulation steps for faster runs
InPlaceExperimentRunner class for A/B testing
Standard Propositions for common verifications (e.g., persona_adherence)
LLMChat class and @llm decorator for internal LLM usage
Dynamic programmatic configuration mechanism

Full Release Notes

**[2025-07-15] Release 0.5.1 with various improvements. Some highlights:**

  - Released the first version of the [TinyTroupe paper (as a preprint)](https://arxiv.org/abs/2507.09788), which describes the library and its use cases in more detail. You can find the related experiments and complementary material in the [publications/](https://github.com/microsoft/TinyTroupe/blob/main/publications) folder.
  - TinyPersons now include action correction mechanisms, allowing better adherence to persona specification, self-consistency and/or fluency (for details, refer to the paper we are releasing at the same time now).
  - Substantial improvements to the TinyPersonFactory class, which now: uses a plan-based approach to generate new agents, allowing better sampling of larger populations; generate agents in parallel.
  - TinyWorld now run agents in parallel within each simulation step, allowing faster simulations.
  - InPlaceExperimentRunner class introduced to allow running controlled experiments (e.g., A/B testing) in a single file (by simply running it multiple times).
  -Various standard Propositions were introduced to make it easier to run common verifications and monitoring of agent behavior (e.g., persona_adherence, hard_persona_adherence, self_consistency, fluency, etc.).
  - Internal LLM usage is now better supported via the LLMChat class, and also the @llm decorator, which transform any standard Python function into an LLM-based one (i.e., by using the docstring as part of the prompt, and some other nuances). This is meant to make it easier to continue advancing TinyTroupe and also allow for some creative explorations of LLM tooling possibilities.
  - Configuration mechanism has been refactored to allow, besides the static config.ini file, also the dynamic programmatic reconfiguration.
  - Renamed Jupyter notebooks examples for better readability and consistency.
  -Added many more tests.