AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Reliable Reasoning in SVG-LLMs via Multi-Task Multi-Reward Reinforcement Learning

Haomin Wang, Qi Wei, Qianli Ma, Shengyuan Ding, Jinhui Yin, Kai Chen, hongjie Zhang

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Reinforcement learning for visual reasoning · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add chain-of-thought reasoning to SFT+RL model (ablation)CTRL-S (SFT+RL) · SArena-Icon Text-to-SVGFID: 12.161 -> 11.584Improved
add chain-of-thought reasoning to SFT model (ablation)CTRL-S (SFT) · SArena-Icon Text-to-SVGsuccess rate (%): 85.75 -> 92.02Improved
add chain-of-thought reasoning to SFT model (ablation)CTRL-S (SFT) · SArena-Icon Image-to-SVGsuccess rate (%): 81.96 -> 90.12Improved
add chain-of-thought to SFT+RL model (token cost) (ablation)CTRL-S (SFT+RL) · SArena-Icon Text-to-SVGoutput tokens: 274 -> 346Hurt
add RL post-training after SFTCTRL-S · SArena-Icon Text-to-SVGFID: 18.154 -> 11.584Improved
add RL post-training after SFTCTRL-S · SArena-Icon Text-to-SVGoutput tokens: 1.1k -> 346Improved
add RL post-training after SFTCTRL-S · SVG-Sophia Code Refinementsuccess rate (%): 84.37 -> 99.79Improved
add Long-CLIP image-text similarity reward (ablation)CTRL-S RL · SArena-Icon Text-to-SVGCLIP-T2I: 24.573 -> 25.444Improved
add code efficiency reward (ablation)CTRL-S RL · SArena-Icon Text-to-SVGoutput tokens: 701 -> 346Improved
add code efficiency reward (ablation)CTRL-S RL · SArena-Icon Text-to-SVGinference time (s/svg): 7.121 -> 4.439Improved
use reward ratio 2:1:1 instead of 1:1:1 (ablation)CTRL-S RL · SArena-Icon Text-to-SVGFID: 12.575 -> 11.584Improved
use reward ratio 2:1:1 instead of 5:3:1 (ablation)CTRL-S RL · SArena-Icon Text-to-SVGCLIP-T2I: 24.653 -> 25.944Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy