pith. sign in

Divide, conquer and combine: A training-free framework for high-resolution image perception in multimodal large language models

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CL 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Agent Explorative Policy Optimization for Multimodal Agentic Reasoning

cs.CL · 2026-05-27 · unverdicted · novelty 6.0

AXPO addresses the Thinking-Acting Gap in agentic RL training by targeted resampling of tool calls in all-wrong subgroups, delivering +1.8pp gains over GRPO on nine multimodal benchmarks with an 8B model beating a 32B baseline on Pass@4.

citing papers explorer

Showing 1 of 1 citing paper.

  • Agent Explorative Policy Optimization for Multimodal Agentic Reasoning cs.CL · 2026-05-27 · unverdicted · none · ref 46

    AXPO addresses the Thinking-Acting Gap in agentic RL training by targeted resampling of tool calls in all-wrong subgroups, delivering +1.8pp gains over GRPO on nine multimodal benchmarks with an 8B model beating a 32B baseline on Pass@4.