OLIVIA treats LLM agent action selection as a contextual linear bandit over frozen hidden states and applies UCB exploration to adapt online, yielding consistent gains over static ReAct and prompt-based baselines on four benchmarks.
arXiv preprint arXiv:2502.11740 , volume=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
CMIB uses a conditional multimodal information bottleneck to create reusable agent skills that separate verbalizable text content from predictive perceptual residuals, improving execution stability.
LASER uses Visual Grounding Reward and Sink Suppression Reward to preserve visual attention trajectories and suppress sink tokens, reducing visual forgetting in LVLMs.
The survey formalizes MLLM perception as a unified vision-language capability and traces its evolution via a new five-stage taxonomy while outlining future challenges.
citing papers explorer
-
OLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct Agents
OLIVIA treats LLM agent action selection as a contextual linear bandit over frozen hidden states and applies UCB exploration to adapt online, yielding consistent gains over static ReAct and prompt-based baselines on four benchmarks.