pith. sign in

Agent Explorative Policy Optimization for Multimodal Agentic Reasoning

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it
abstract

Vision-language models with extended reasoning succeed on complex problems, but many real-world problems require external tools that internal reasoning alone often cannot resolve. Agentic reasoning therefore interleaves two behaviors with a structural asymmetry: thinking (the self-contained default) and tool use (a high-variance auxiliary acting). We refer to this asymmetry as the Thinking-Acting Gap. Under standard RL recipes like GRPO, the gap manifests as two diagnostic symptoms during training: tool use is attempted on only ~30% of rollouts, and when attempted, the tool-using rollouts within a group are all-wrong on ~40% of questions, suppressing the learning signal at the tool calls that needed it. We propose AXPO (Agent eXplorative Policy Optimization): for each all-wrong tool-using subgroup, AXPO fixes the thinking prefix and resamples the tool call and its continuation, paired with uncertainty-based prefix selection. Across nine multimodal benchmarks and three scales of Qwen3-VL-Thinking, SFT+AXPO outperforms SFT+GRPO at average (+1.8pp Pass@1 and +1.8pp Pass@4 at 8B on average) and 8B with SFT+AXPO surpasses the 32B Base on Pass@4 with 4 times fewer parameters.

fields

cs.CL 2

years

2026 2

verdicts

UNVERDICTED 2

clear filters

representative citing papers

Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients

cs.CL · 2026-06-16 · unverdicted · novelty 7.0

ZPPO improves distillation to small vision-language models by using binary and negative candidate prompts plus a replay buffer for hard questions, outperforming standard distillation and GRPO on a 31-benchmark suite with largest gains at the 0.8B scale.

citing papers explorer

Showing 2 of 2 citing papers after filters.

  • Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients cs.CL · 2026-06-16 · unverdicted · none · ref 62 · internal anchor

    ZPPO improves distillation to small vision-language models by using binary and negative candidate prompts plus a replay buffer for hard questions, outperforming standard distillation and GRPO on a 31-benchmark suite with largest gains at the 0.8B scale.

  • Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks cs.CL · 2026-06-27 · unverdicted · none · ref 50 · internal anchor

    Evolution Fine-Tuning trains LLMs on 156K trajectories spanning 371 tasks to achieve 10.22% average improvement on 22 held-out optimization tasks and match SOTA on select circle-packing problems when combined with test-time RL.