TVI-CoT introduces learnable control tokens <THINK>, <LOOK>, <ANSWER> that let multimodal LLMs interleave textual reasoning with dynamic visual feature access, reporting gains of 3.4-6.1% on eight benchmarks over prior CoT baselines.
hub Canonical reference
Mulberry: Empowering mllm with o1-like reasoning and reflection via collective monte carlo tree search
Canonical reference. 78% of citing Pith papers cite this work as background.
23
Pith papers citing it
Background
78% of classified citations
hub tools
citation-role summary
background 7
baseline 2
citation-polarity summary
representative citing papers
RAPO uses an information-theoretic lower bound on visual gain to select high-entropy reflection anchors and optimizes a chain-masked KL surrogate, delivering gains over baselines on reasoning benchmarks across LVLM backbones.
RL post-training on hallucination-forced multimodal data improves reasoning performance and can outperform standard training.
FLARE is a vision-language model family using text-guided vision encoding, context-aware alignment decoding, dual-semantic mapping loss, and text-driven VQA synthesis to achieve deep cross-modal integration, outperforming larger models with only 630 vision tokens at 3B scale.
R1-VL uses StepGRPO with rule-based StepRAR and StepRVR rewards to let MLLMs learn step-by-step reasoning beyond imitation of positive paths.
AnE combines Truth Anchor Expansion and Scaffold-Stripping to deliver 10.3% gains on eight multimodal reasoning benchmarks for MLLMs.
ForeSight lets VLMs use low-level visual cues and mask-based visual feedback within an RL loop to reason more accurately, with the 7B model beating same-scale peers and some closed-source SOTA on a new benchmark.
A trajectory-aware process reward using DTW on sentence embeddings, combined with exact-match in GRPO after SFT, raises mean medical VQA accuracy from 0.598 to 0.689 across six benchmarks.
Saliency-R1 uses a novel saliency map technique and GRPO with human bounding-box overlap as reward to improve VLM reasoning faithfulness and interpretability.
OmniDrive-R1 boosts VLM reasoning score from 51.77% to 80.35% and answer accuracy from 37.81% to 73.62% on DriveLMM-o1 via reinforcement-driven interleaved multi-modal chain-of-thought with annotation-free grounding.
AutoRubric generates rubric-based process rewards from self-aggregated successful trajectories to improve faithful multimodal reasoning in MLLMs under RLVR without human annotation or teacher models.
ViGoRL introduces visually grounded RL that anchors reasoning steps to image coordinates and uses multi-turn zooming to outperform standard RL and supervised baselines on spatial and GUI reasoning benchmarks.
Iterative SFT-RL cycles enable a 7B LVLM to develop sophisticated visual chain-of-thought reasoning and improve performance on math and general reasoning benchmarks.
A two-stage RL framework first boosts text reasoning in 3B LMMs then adapts it to multimodal inputs, producing modest benchmark gains of 4.5-4.8%.
Search-o1 integrates agentic retrieval-augmented generation and a Reason-in-Documents module into large reasoning models to dynamically supply missing knowledge and improve performance on complex science, math, coding, and QA tasks.
MathVis-Fine proposes a dataset with fine-grained visual annotations and dependency ratings plus a progressive two-stage training paradigm to align visual supervision with sample-specific necessity in multimodal mathematical reasoning.
A survey of test-time scaling for multimodal foundation models that introduces a three-way taxonomy of sampling, feedback, and search approaches along with applications and benchmarks.
MoVT unifies different visual reasoning modes in a single model and uses the AdaVaR two-stage framework with supervised cold-start and RL via AdaGRPO to enable context-adaptive mode selection, yielding consistent gains on visual reasoning tasks.
R1-Onevision turns images into structured text for multimodal reasoning, trains on a custom dataset with RL, and claims SOTA results on an educational benchmark.
The survey organizes the shift of LLMs toward deliberate System 2 reasoning, covering model construction techniques, performance on math and coding benchmarks, and future research directions.
The paper provides the first comprehensive survey of multimodal chain-of-thought reasoning, including foundational concepts, a taxonomy of methodologies, application analyses, challenges, and future directions.
Position paper claims multimodal LLMs can significantly advance scientific reasoning and proposes a four-stage roadmap plus challenges and suggestions.
citing papers explorer
-
AutoRubric: Rubric-Based Generative Rewards for Faithful Multimodal Reasoning
AutoRubric generates rubric-based process rewards from self-aggregated successful trajectories to improve faithful multimodal reasoning in MLLMs under RLVR without human annotation or teacher models.
-
LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL
A two-stage RL framework first boosts text reasoning in 3B LMMs then adapts it to multimodal inputs, producing modest benchmark gains of 4.5-4.8%.
-
Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning
Position paper claims multimodal LLMs can significantly advance scientific reasoning and proposes a four-stage roadmap plus challenges and suggestions.