Dimensions overall score 8.0

GitHub Code Pulse

No public code linked for this paper yet.

• CoVe is a post-training data synthesis framework for training interactive tool-use agents that ensures both data complexity and correctness.method 70%
• Explicit task constraints in CoVe guide the generation of complex trajectories and act as deterministic verifiers for trajectory quality.method 70%
• CoVe enables the creation of high-quality training trajectories for supervised fine-tuning (SFT) and the derivation of accurate reward signals for reinforcement learning (RL).method 70%
• The CoVe-4B model achieves a 43.0% success rate in the Airline domain on the τ^2-bench benchmark.result 70%
• The CoVe-4B model achieves a 59.4% success rate in the Retail domain on the τ^2-bench benchmark.result 70%
• The CoVe-4B model significantly outperforms strong baselines of similar scale in its overall performance.result 70%
• The CoVe-4B model remains competitive with models up to 17 times its size.result 70%
• The generalizability of the CoVe framework might be limited when handling unseen constraints or rapidly changing dataset attributes.limitation 70%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card