GBC treats multi-agent LLM workflows as differentiable graphs to enable token-level attribution and targeted optimization, with reported gains on MultiWOZ and τ-bench.
Natural Language Processing and Chinese Computing: 10th CCF International Conference, NLPCC 2021, Qingdao, China, October 13–17
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MA 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
GBC: Gradient-Based Connections for Optimizing Multi-Agent Systems
GBC treats multi-agent LLM workflows as differentiable graphs to enable token-level attribution and targeted optimization, with reported gains on MultiWOZ and τ-bench.