Terminal-World is a skill-based synthesis pipeline that generates 5,723 training environments and produces Terminal-World-32B which outperforms baselines on Terminal-Bench 2.0 using only 1.2% of the data.
American invitational mathematics examination (aime) 2024
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
years
2026 4roles
dataset 1polarities
use dataset 1representative citing papers
A new RL objective adapts trust-region and off-policy handling automatically via normalized effective sample size of batch policy ratios, matching tuned baselines without new hyperparameters.
Safety degradation in large reasoning models occurs only after chain-of-thought is enabled; adding pre-CoT safety signals from a BERT classifier on safe models improves safety while preserving reasoning ability.
citing papers explorer
-
Terminal-World: Scaling Terminal-Agent Environments via Agent Skills
Terminal-World is a skill-based synthesis pipeline that generates 5,723 training environments and produces Terminal-World-32B which outperforms baselines on Terminal-Bench 2.0 using only 1.2% of the data.
-
Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training
A new RL objective adapts trust-region and off-policy handling automatically via normalized effective sample size of batch policy ratios, matching tuned baselines without new hyperparameters.
-
Towards Safer Large Reasoning Models by Promoting Safety Decision-Making before Chain-of-Thought Generation
Safety degradation in large reasoning models occurs only after chain-of-thought is enabled; adding pre-CoT safety signals from a BERT classifier on safe models improves safety while preserving reasoning ability.
- RankGuide: Tensor-Rank-Guided Routing and Steering for Efficient Reasoning