Introduces the Oracle benchmark of 96 black-box environments across 6 task types to measure integrated reasoning in LLMs through interactive function discovery, with o3 leading but all models showing planning weaknesses on hard instances.
CoRR , volume =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2verdicts
UNVERDICTED 2representative citing papers
LLMs trained via rubric-based self-rewarding RL with GRPO enhanced feeling expression and sycophancy robustness but degraded truthful QA performance.
citing papers explorer
-
Investigating Advanced Reasoning of Large Language Models via Black-Box Environment Interaction
Introduces the Oracle benchmark of 96 black-box environments across 6 task types to measure integrated reasoning in LLMs through interactive function discovery, with o3 leading but all models showing planning weaknesses on hard instances.
-
When AI Says It Feels
LLMs trained via rubric-based self-rewarding RL with GRPO enhanced feeling expression and sycophancy robustness but degraded truthful QA performance.