List your company

Question Answering on Long-context QA

82.7Task SuccessCVT-RL
50.14858.59967.0575.501Jun 3, 2026

Evaluation results

MethodLinks
CVT-RLVerifier=yes, Constraints=yes, CF rollouts=semantic, Belief=yes, Compute=3.92026.0682.7
Information-matched CF processVerifier=yes, Constraints=yes, CF rollouts=semantic, Belief=yes, Compute=3.92026.0678.4
Q-RAGVerifier=yes, Constraints=no, CF rollouts=no, Belief=no, Compute=1.42026.0675.4
Compute-matched non-causalVerifier=yes, Constraints=yes, CF rollouts=random extra, Belief=yes, Compute=3.82026.0675.2
LongRLVRVerifier=yes, Constraints=no, CF rollouts=no, Belief=no, Compute=1.22026.0673.6
Constrained process RLVerifier=yes, Constraints=yes, CF rollouts=no, Belief=yes, Compute=1.52026.0673.1
RLVMRVerifier=yes, Constraints=no, CF rollouts=no, Belief=no, Compute=1.32026.0670.2
TROLL-styleVerifier=yes, Constraints=no, CF rollouts=no, Belief=no, Compute=1.12026.0667
PPO-RLVRVerifier=yes, Constraints=no, CF rollouts=no, Belief=no, Compute=1.12026.0663.2
SFTVerifier=no, Constraints=no, CF rollouts=no, Belief=no, Compute=1.02026.0651.4