TRACE is a framework that improves multi-hop KGQA by maintaining semantic continuity through path narratives and reusable experiential priors combined via dual-feedback re-ranking.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2verdicts
UNVERDICTED 2representative citing papers
Mujica-MyGo decomposes multi-turn RAG interactions via multi-agent workflows and applies minimalist policy gradient optimization to improve performance on QA benchmarks while avoiding long-context problems.
citing papers explorer
-
TRACE: An Experiential Framework for Coherent Multi-hop Knowledge Graph Question Answering
TRACE is a framework that improves multi-hop KGQA by maintaining semantic continuity through path narratives and reusable experiential priors combined via dual-feedback re-ranking.
-
Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning
Mujica-MyGo decomposes multi-turn RAG interactions via multi-agent workflows and applies minimalist policy gradient optimization to improve performance on QA benchmarks while avoiding long-context problems.