SVAgent improves long video question answering by constructing storylines via multi-agent collaboration and aligning cross-modal predictions for more robust, human-like reasoning.
Open- mmreasoner: Pushing the frontiers for multimodal rea- soning with an open and general recipe
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
dataset 2
background 1
citation-polarity summary
representative citing papers
AnE combines Truth Anchor Expansion and Scaffold-Stripping to deliver 10.3% gains on eight multimodal reasoning benchmarks for MLLMs.
ParaVT introduces the first multi-agent RL framework for parallel video tool calling in LMMs, using PARA-GRPO to resolve the Tool Prior Paradox and achieve +7.9% average improvement over Qwen3-VL baseline across six benchmarks.
PVM adds a parallel branch to LVLMs that directly supplies visual embeddings to prevent attention decay over long generated sequences, yielding accuracy gains on reasoning tasks with minimal overhead.
ChartVerse uses Rollout Posterior Entropy and truth-anchored inverse QA synthesis to produce 640K high-quality chart reasoning samples, training an 8B model that surpasses its 30B teacher.
LongVT adds native video-cropping tool calling to LMMs for interleaved multimodal chain-of-tool-thought reasoning on long videos and releases VideoSIAH data for training and evaluation.
RLR³ extends RLVR to criterion-level rubric verification via dual execution paths, minimal exposure masking, hierarchical aggregation, and saturation mitigation, delivering 4.7-point gains over base on 15 benchmarks with Qwen3-VL-30B-A3B.
OmniThoughtVis curates 1.8M multimodal CoT samples via teacher distillation, difficulty annotation, and tag-based sampling, yielding consistent gains on nine reasoning benchmarks and allowing 4B models to match or beat undistilled 8B baselines.
HDPO reframes tool efficiency as a conditional objective within accurate trajectories, enabling Metis to reduce tool invocations by orders of magnitude while raising reasoning accuracy.
Stage-1 warm-starts control the entropy regime entering RL but yield small and localized effects on final in-domain and out-of-domain performance.
citing papers explorer
-
Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs
PVM adds a parallel branch to LVLMs that directly supplies visual embeddings to prevent attention decay over long generated sequences, yielding accuracy gains on reasoning tasks with minimal overhead.
-
Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models
HDPO reframes tool efficiency as a conditional objective within accurate trajectories, enabling Metis to reduce tool invocations by orders of magnitude while raising reasoning accuracy.