VRRL trains LVLMs for visually grounded self-reflection via prefix masking and buffered roll-ins, yielding higher out-of-distribution accuracy on grounding and navigation tasks than standard RL baselines.
Proceedings of the 33rd ACM International Conference on Multimedia , pages =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
LearnWeak specializes small CUAs via weakness detection by a reference agent, targeted task synthesis, and error-aware training, delivering 11+ point gains on OSWorld.
WinDOM dataset plus SFD yields +5.4 OOD-mean gain on Qwen3.5-2B via early-init GRPO from same-family cold-start.
citing papers explorer
-
Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents
LearnWeak specializes small CUAs via weakness detection by a reference agent, targeted task synthesis, and error-aware training, delivering 11+ point gains on OSWorld.