ToolGraph plus DPO on divergence-point preferences lifts weighted average reward on 375 tau2-bench tasks from 0.304 to 0.355.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Self-Evolution for Multi-Turn Tool-Calling Agents via Divergence-Point Preference Learning
ToolGraph plus DPO on divergence-point preferences lifts weighted average reward on 375 tau2-bench tasks from 0.304 to 0.355.