@hwchase17: Verifiers are important for scaling evals/RL But costs add up! So can we make them cheaper? Some great work by @Vtrived…
Summary
Tweet highlighting work on making verifiers cheaper for scaling evaluations and reinforcement learning, by researchers from Harvey.
View Cached Full Text
Cached at: 06/03/26, 03:51 PM
Verifiers are important for scaling evals/RL
But costs add up! So can we make them cheaper?
Some great work by @Vtrivedy10 @jakebroekhuizen in conjunction with @nikogrupen @gabepereyra and the Harvey team on this
Similar Articles
AgentV-RL: Scaling Reward Modeling with Agentic Verifier
AgentV-RL introduces an Agentic Verifier framework that enhances reward modeling through bidirectional verification with forward and backward agents augmented with tools, achieving 25.2% improvement over state-of-the-art ORMs. The approach addresses error propagation and grounding issues in verifiers for complex reasoning tasks through multi-turn deliberative processes combined with reinforcement learning.
@omarsar0: Verifiers are a big deal. Without good verifiers, /goal & /loop breaks a lot. Anything out of distribution for an LLM, …
Emphasizes the importance of verifiers for LLM-based agents, noting that out-of-distribution tasks cause failures, and suggests tuning custom verifiers.
The verifier based vs verifier free test time scaling result is older than people act, and it keeps getting confirmed [D]
The post discusses the confirmed research finding that verifier-based test-time compute scaling dominates verifier-free methods, with practical examples like Apodex showing gains from separate verification processes. It argues that building independent verifiers is a key path for future AI capability improvements.
@bcherny: We talk a lot about how important it is to set up self-verification loops. Especially in the age of powerful models tha…
Discussion on the importance of self-verification loops in AI models like Claude to improve reliability and reduce the need for manual oversight.
@LangChain: https://x.com/LangChain/status/2061864647884464430
A study by LangChain and Harvey explores methods to reduce the cost of verifying legal agent outputs by batching criteria evaluations and using open models, achieving order-of-magnitude cost savings while maintaining near-frontier performance.