Published on January 28, 2026 4:48 AM GMT

Thank-you to Ryan Greenblatt and Julian Stastny for mentorship as part of the Anthropic AI Safety Fellows program. See Defining AI Truth-Seeking by What It Is Not for the research findings. This post introduces the accompanying open-source infrastructure.

TruthSeekingGym is an open-source framework for evaluating and training language models on truth-seeking behavior. It is in early Beta so please do expect issues.

Core Components

• Evaluation metrics — Multiple experimental setups for operationalizing “truth-seeking”:

  • Ground-truth accuracy: Does the model reach correct conclusions?

  • Martingale property: Are belief updates unpredictable from prior beliefs? (predictable updates suggest bias)

  • Sycophantic reasoning: Does reasoning quality degrade when the user expresses an opinion?

  • Mutual predictability: Does knowing a model’s answers on some questions help predict its answers on others? (measures cross-question consistency)

  • World-in-the-loop: Are the model’s claims useful for making accurate predictions about the world?

  • Qualitative judgment: Does reasoning exhibit originality, curiosity, and willingness to challenge assumptions?

• Domains — Question sets with and without ground-truth labels: research analysis, forecasting, debate evaluation, …

• Reasoning modes — Generation strategies: direct inference, chain-of-thought, self-debate, bootstrap (auxiliary questions to scaffold reasoning), length-controlled generation

• Training — Fine-tuning (SFT/RL) models toward truth-seeking using the same reward signals as in evaluation

Workflow

 1. run_reasoning - Generate model responses across domain questions
 2. run_analyzers - Compute evaluation metrics and aggregate results
 3. run_trainers - Fine-tune models using SFT or various RL objectives (Brier reward, reasoning coverage, etc.)

Infrastructure

• Supports Google, Anthropic, OpenAI, DeepSeek, and Together models via direct APIs or OpenRouter
• Supports local models via SGLang + trl
• Ray integration for distributed evaluation
• Modular design for adding new domains, metrics, and training algorithms
• CLI interface + Web interface

The framework and accompanying datasets are released to enable reproducible research on AI truth-seeking.