Agents
Adding a verifier improves every agentic AI system. But frontier verifiers are expensive - so we trained our own. Matching quality, at a fra…
Adding a verifier improves every agentic AI system. But frontier verifiers are expensive - so we trained our own. Matching quality, at a fraction of the cost. Thread below 🧵 1/ Your agent already foun
Adding a verifier improves every agentic AI system. But frontier verifiers are expensive - so we trained our own. Matching quality, at a fraction of the cost. Thread below 🧵 1/ Your agent already found the right answer, but your aggregation threw it away. Across every generator we tested (weak and frontier, open and closed), pass@k surpasses pass@1. Correct answers are routinely in the pool and just not selected. The binding constraint isn't answer g…
Related
- 1/5 We’re seeing 4 common agent optimization methods for hitting the right accuracy-cost or accuracy-latency tradeoff. We tried them all out…
- Notes from evaluating a customer support chat agent system: heuristic evaluators give false signal, retrieval bugs masquerade as LLM failures, and the cost/quality Pareto frontier is rarely where you think [D]
- Evals shape agent behavior. Every eval is a vector that shifts the behavior of your agentic system. More evals ≠ better agents. Instead, bui…
Source: AI21 Labs (X) | 2026-08-23