AgentPatch is a training-free, coarse-to-fine repair method that merges agentic multimodal LLMs into one static checkpoint while recovering weak-task and behavior-critical capabilities.
boost" and target_span_role=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models
AgentPatch is a training-free, coarse-to-fine repair method that merges agentic multimodal LLMs into one static checkpoint while recovering weak-task and behavior-critical capabilities.