On Randomness in Agentic Evals

📰 ArXiv cs.AI

Agentic system evaluations may not be reliable due to substantial variance in single-run performance estimates

advanced Published 26 Mar 2026
Action Steps
  1. Collect a large number of agentic trajectories to estimate performance variance
  2. Analyze the variance in single-run pass@1 estimates to determine reliability
  3. Consider using multiple runs or alternative evaluation metrics to improve reliability
Who Needs to Know This

AI researchers and engineers working on agentic systems can benefit from understanding the limitations of current evaluation methods, as it can impact the development of more robust and reliable models

Key Insight

💡 Single-run performance estimates may not be reliable for agentic systems due to substantial variance

Share This
🤖 Agentic system evaluations may be flawed due to high variance in single-run performance estimates

Key Takeaways

Agentic system evaluations may not be reliable due to substantial variance in single-run performance estimates

Full Article

Title: On Randomness in Agentic Evals

Abstract:
arXiv:2602.07150v3 Announce Type: replace-cross Abstract: Agentic systems are evaluated on benchmarks where agents interact with environments to solve tasks. Most papers report a pass@1 score computed from a single run per task, assuming this gives a reliable performance estimate. We test this assumption by collecting 60,000 agentic trajectories on SWE-Bench-Verified, spanning three models and two scaffolds. We find substantial variance: single-run pass@1 estimates vary by 2.2 to 6.0 percentage
Read full paper → ← Back to Reads

Related Videos

5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
Dave Ebbelaar (LLM Eng)
Claude Code vs. Codex: Who Builds Minecraft BETTER? 🧱⚡
Claude Code vs. Codex: Who Builds Minecraft BETTER? 🧱⚡
Ascent
WHICH AI Do High Schoolers Use and WHY? 🧠 #ai #highschoollife #chatgpt #gemini #claude
WHICH AI Do High Schoolers Use and WHY? 🧠 #ai #highschoollife #chatgpt #gemini #claude
Ascent
State Spaced Model (SSM) - Mamba LLM models #aiwithakash #genai #aiintamil
State Spaced Model (SSM) - Mamba LLM models #aiwithakash #genai #aiintamil
AI with Akash
9. BERT Special Tokens for Beginners | Explained in Tamil | GenAI | Agents | Embedding Model | BERT
9. BERT Special Tokens for Beginners | Explained in Tamil | GenAI | Agents | Embedding Model | BERT
AI with Akash
8. Tokenizers for Beginners | Explained in Tamil | GenAI | Agents | RAG
8. Tokenizers for Beginners | Explained in Tamil | GenAI | Agents | RAG
AI with Akash