Pith. sign in

REVIEW 7 cited by

Point-RFT: Improving Multimodal Reasoning with Visually Grounded Reinforcement Finetuning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2505.19702 v1 pith:YVOGZY6Q submitted 2025-05-26 cs.CV

Point-RFT: Improving Multimodal Reasoning with Visually Grounded Reinforcement Finetuning

classification cs.CV
keywords reasoningvisualfinetuninggroundedmultimodalreinforcementdocumentpoint-rft
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Recent advances in large language models have significantly improved textual reasoning through the effective use of Chain-of-Thought (CoT) and reinforcement learning. However, extending these successes to vision-language tasks remains challenging due to inherent limitations in text-only CoT, such as visual hallucinations and insufficient multimodal integration. In this paper, we introduce Point-RFT, a multimodal reasoning framework explicitly designed to leverage visually grounded CoT reasoning for visual document understanding. Our approach consists of two stages: First, we conduct format finetuning using a curated dataset of 71K diverse visual reasoning problems, each annotated with detailed, step-by-step rationales explicitly grounded to corresponding visual elements. Second, we employ reinforcement finetuning targeting visual document understanding. On ChartQA, our approach improves accuracy from 70.88% (format-finetuned baseline) to 90.04%, surpassing the 83.92% accuracy achieved by reinforcement finetuning relying solely on text-based CoT. The result shows that our grounded CoT is more effective for multimodal reasoning compared with the text-only CoT. Moreover, Point-RFT exhibits superior generalization capability across several out-of-domain visual document reasoning benchmarks, including CharXiv, PlotQA, IconQA, TabMWP, etc., and highlights its potential in complex real-world scenarios.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. V-Reflection: Transforming MLLMs from Passive Observers to Active Interrogators

    cs.CV 2026-03 unverdicted novelty 7.0

    V-Reflection introduces a think-then-look mechanism where MLLM latent states actively interrogate visual features via two-stage distillation from a box-guided teacher to a dynamic autoregressive student, narrowing the...

  2. Latent Visual Reasoning

    cs.CV 2025-09 unverdicted novelty 7.0

    Latent Visual Reasoning enables autoregressive generation of latent visual states that reconstruct critical image tokens, yielding gains on perception-heavy VQA benchmarks such as 71.67% on MMVP.

  3. BVS: Bayesian Visual Search with Multimodal Large Language Model for Fine-grained Perception

    cs.CV 2026-07 conditional novelty 6.0

    BVS combines early-stop attention rollout priors with a scale-aware non-stationary kernel and GP-UCB to locate tiny objects in UHR images more accurately and with fewer MLLM queries than prior visual-search methods.

  4. CARE: Competence-Aware Reward Shaping for Adaptive Reasoning Length in Video-MLLMs

    cs.CV 2026-06 unverdicted novelty 6.0

    CARE uses exponential moving average competence estimates to progressively shift RL rewards from exploration-oriented long reasoning to efficiency-oriented concise reasoning in video-MLLMs, with batch normalization an...

  5. From Token to Token Pair: Efficient Prompt Compression for Large Language Models in Clinical Prediction

    cs.CL 2026-05 unverdicted novelty 6.0

    MedTPE compresses EHR token sequences by up to 31% via merging common medical token pairs, reducing LLM inference latency 34-63% while maintaining or improving performance on mortality and phenotyping tasks.

  6. CharTide: Data-Centric Chart-to-Code Generation via Tri-Perspective Tuning and Inquiry-Driven Evolution

    cs.CV 2026-04 conditional novelty 6.0

    A 7B/8B model trained with decoupled tri-perspective SFT and QA-verified RL matches GPT-4o and approaches GPT-5 on chart-to-code generation benchmarks.

  7. CharTide: Data-Centric Chart-to-Code Generation via Tri-Perspective Tuning and Inquiry-Driven Evolution

    cs.CV 2026-04 unverdicted novelty 6.0

    CharTide decouples chart-to-code data into three perspectives and uses inquiry-driven RL with atomic QA verification to let smaller VLMs surpass GPT-4o on chart-to-code tasks.