Search papers, labs, and topics across Lattice.
5
0
6
4
Context-sensitive hallucinations in LLMs can be mitigated by a new optimization technique that rewards step-level consistency, leading to significant improvements in reasoning accuracy.
Qwen-AgentWorld achieves unprecedented simulation fidelity, outperforming existing models and enabling scalable agentic reinforcement learning across diverse real-world environments.
ISPO reduces critical reasoning failures in RLVR by transforming reward structures, leading to superior performance on complex reasoning tasks.
SkillComposer enables language models to self-evolve skills in real-time, achieving up to +4.5 improvements on agent tasks compared to larger models.
Forget static rubrics and expensive external models: EvoRubric co-evolves a single policy to generate both responses and the rubrics to evaluate them, outperforming traditional RLHF methods in open-ended generation tasks.
