RL post-training on hallucination-forced multimodal data improves reasoning performance and can outperform standard training.
hub Baseline reference
Inter-gps: Interpretable geometry problem solving with formal language and symbolic reasoning
Baseline reference. 55% of citing Pith papers use this work as a benchmark or comparison.
20
Pith papers citing it
Baseline
55% of classified citations
hub tools
citation-role summary
dataset 6
background 5
citation-polarity summary
representative citing papers
GeoLaux is a new benchmark of 2186 long-step geometry problems requiring auxiliary lines, used to evaluate 23 MLLMs and reveal major drops in performance on complex tasks.
UniR is a composable reasoning module trained with verifiable rewards and added to frozen LLMs via logit summation, enabling modular composition and weak-to-strong generalization across tasks and model sizes.
PRIMETIME generator reveals that LLM datetime parsing and arithmetic primitives are individually unreliable but fully learnable via fine-tuning, enabling frontier-level accuracy on event planning with small LoRA models.
WE-MATH benchmark reveals most LMMs rely on rote memorization for visual math while GPT-4o has shifted toward knowledge generalization.
MathVerse is a benchmark that tests multi-modal LLMs on visual math by providing each problem in six versions with progressively less diagram and text information to measure true visual understanding.
SAPO introduces segment-level policy optimization using a step-wise MDP abstraction to better align RL updates with reasoning structure in multi-modal LLM tasks.
OMIBench benchmark reveals that current LVLMs achieve at most 50% on Olympiad problems requiring reasoning across multiple images.
MapTab is a new multimodal benchmark with 328 images and nearly 200k queries that shows current MLLMs have substantial difficulty with multi-criteria route planning when visual and tabular information must be combined.
Thinking with Drafting reconceptualizes visual reasoning as optical decompression by forcing models to draft mental models into executable DSL code for deterministic self-verification on the VisAlg benchmark.
SPHINX generates synthetic visual puzzles for benchmarking LVLMs, where GPT-5 scores 51.1% and RLVR training improves both in-domain and external visual reasoning performance.
Activation Replay boosts multimodal reasoning in post-trained LMMs by replaying low-entropy activations from base models to RLVR counterparts at test time via visual token manipulation.
ViSurf unifies SFT and RLVR for LVLMs in one training stage by injecting ground-truth labels into rollouts and applying novel reward controls, outperforming standalone and two-stage baselines on diverse benchmarks.
InternVL3-78B sets a new open-source SOTA of 72.2 on MMMU via native joint multimodal pre-training, V2PE, MPO, and test-time scaling while remaining competitive with proprietary models.
InternVL 2.5 is the first open-source MLLM to surpass 70% on the MMMU benchmark via model, data, and test-time scaling, with a 3.7-point gain from chain-of-thought reasoning.
Mixed Preference Optimization with the MMPR dataset boosts multimodal CoT reasoning, lifting InternVL2-8B to 67.0 accuracy on MathVista (+8.7 points) and matching the 76B model.
A neuro-symbolic engine generates GeoSym127K, a 127K-question dataset with symbolic ground truths and verified CoT pairs, yielding +22.21% gains on MathVerse Vision-Only after SFT on Qwen3-VL-8B.
InternVL 1.5 narrows the performance gap to proprietary multimodal models via a stronger transferable vision encoder, dynamic high-resolution tiling, and curated English-Chinese training data.
Position paper claims multimodal LLMs can significantly advance scientific reasoning and proposes a four-stage roadmap plus challenges and suggestions.
citing papers explorer
-
Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning Models
RL post-training on hallucination-forced multimodal data improves reasoning performance and can outperform standard training.
-
GeoLaux: A Benchmark for Evaluating MLLMs' Geometry Performance on Long-Step Problems Requiring Auxiliary Lines
GeoLaux is a new benchmark of 2186 long-step geometry problems requiring auxiliary lines, used to evaluate 23 MLLMs and reveal major drops in performance on complex tasks.
-
Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs
UniR is a composable reasoning module trained with verifiable rewards and added to frozen LLMs via logit summation, enabling modular composition and weak-to-strong generalization across tasks and model sizes.
-
PRIMETIME : Limits of LLMs in Temporal Primitives
PRIMETIME generator reveals that LLM datetime parsing and arithmetic primitives are individually unreliable but fully learnable via fine-tuning, enabling frontier-level accuracy on event planning with small LoRA models.
-
We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?
WE-MATH benchmark reveals most LMMs rely on rote memorization for visual math while GPT-4o has shifted toward knowledge generalization.
-
MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?
MathVerse is a benchmark that tests multi-modal LLMs on visual math by providing each problem in six versions with progressively less diagram and text information to measure true visual understanding.
-
Segment-Aligned Policy Optimization for Multi-Modal Reasoning
SAPO introduces segment-level policy optimization using a step-wise MDP abstraction to better align RL updates with reasoning structure in multi-modal LLM tasks.
-
OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Model
OMIBench benchmark reveals that current LVLMs achieve at most 50% on Olympiad problems requiring reasoning across multiple images.
-
MapTab: Are MLLMs Ready for Multi-Criteria Route Planning in Heterogeneous Graphs?
MapTab is a new multimodal benchmark with 328 images and nearly 200k queries that shows current MLLMs have substantial difficulty with multi-criteria route planning when visual and tabular information must be combined.
-
Thinking with Drafting: Optical Decompression via Logical Reconstruction
Thinking with Drafting reconceptualizes visual reasoning as optical decompression by forcing models to draft mental models into executable DSL code for deterministic self-verification on the VisAlg benchmark.
-
SPHINX: A Synthetic Environment for Visual Perception and Reasoning
SPHINX generates synthetic visual puzzles for benchmarking LVLMs, where GPT-5 scores 51.1% and RLVR training improves both in-domain and external visual reasoning performance.
-
Boosting Reasoning in Large Multimodal Models via Activation Replay
Activation Replay boosts multimodal reasoning in post-trained LMMs by replaying low-entropy activations from base models to RLVR counterparts at test time via visual token manipulation.
-
ViSurf: Visual Supervised-and-Reinforcement Fine-Tuning for Large Vision-and-Language Models
ViSurf unifies SFT and RLVR for LVLMs in one training stage by injecting ground-truth labels into rollouts and applying novel reward controls, outperforming standalone and two-stage baselines on diverse benchmarks.
-
InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
InternVL3-78B sets a new open-source SOTA of 72.2 on MMMU via native joint multimodal pre-training, V2PE, MPO, and test-time scaling while remaining competitive with proprietary models.
-
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
InternVL 2.5 is the first open-source MLLM to surpass 70% on the MMMU benchmark via model, data, and test-time scaling, with a 3.7-point gain from chain-of-thought reasoning.
-
Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization
Mixed Preference Optimization with the MMPR dataset boosts multimodal CoT reasoning, lifting InternVL2-8B to 67.0 accuracy on MathVista (+8.7 points) and matching the 76B model.
-
GeoSym127K: Scalable Symbolically-verifiable Synthesis for Multimodal Geometric Reasoning
A neuro-symbolic engine generates GeoSym127K, a 127K-question dataset with symbolic ground truths and verified CoT pairs, yielding +22.21% gains on MathVerse Vision-Only after SFT on Qwen3-VL-8B.
-
How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites
InternVL 1.5 narrows the performance gap to proprietary multimodal models via a stronger transferable vision encoder, dynamic high-resolution tiling, and curated English-Chinese training data.
-
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.
- Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models