6Mikao9/jev-agent-design-with-topk-logits-choices
Research design for a Jev-native agent system: tool integration, speculative parameter proposals, external helper logits Top-k proposals with Jev-controlled fallback ,decision-aware hierarchical memory, and dependency-aware replanning.Feature:Jev naturallanguage conversation prototype using external helper logits and dynamic Top-k token selection.
GitHub repository with 21 stars and 1 forks.
Language: Python
Topics: agent-memory, ai-agents, decision-models, diffusion-language-models, function-calling, hierarchical-memory, jev, logits, natural-language-generation, research