qwen-3-vl-2b-247125c7·2 events·first seen Aliases: Qwen-3-VL-2B, QwenVL3-2B
Researchers propose SD-GPS, a neuro-symbolic framework for geometry problem solving that treats a symbolic solver as an execution oracle during both formalization and deduction stages. The system combines solvability-guided reinforcement learning for autoformalization (built on QwenVL3-2B) with an impasse-aware agent that proposes and symbolically verifies auxiliary lemmas. Evaluations on Geometry3K and PGPS9K show SD-GPS outperforms existing multimodal, neural, and neuro-symbolic baselines across multiple task regimes. The work advances the line of research on grounding neural agents in formal systems for verifiable mathematical reasoning.
A new arXiv paper demonstrates that verifier-driven self-DPO, a common recipe for self-improving visual-language models, can silently degrade student model performance when the verifier's task-rubric accuracy is insufficient for the target task. Experiments on Qwen-3-VL-2B and Qwen-2.5-VL-3B across MathVista, MMMU, and BLINK show regressions of 3.4–10.9 percentage points below frozen baselines, with the counterintuitive finding that more accurate-but-still-wrong verifiers cause larger regressions than near-random ones. The authors provide a mechanistic explanation via a variance theorem for progress-gated replay and offer operational guidance: measure target-task rubric accuracy before running any verifier-driven loop and rank verifiers by task-specific quality rather than parameter count.