A reinforcement-learned vision-language agent adaptively selects and fuses monocular depth experts per sample for better performance across camera geometries.
hub Canonical reference
Reason-rft: Reinforcement fine-tuning for visual reasoning
Canonical reference. 86% of citing Pith papers cite this work as background.
26
Pith papers citing it
Background
86% of classified citations
hub tools
citation-role summary
background 6
method 1
citation-polarity summary
representative citing papers
Formalizes Reasoning Portability (RP) and proposes RDB-CL to modulate per-sample KL regularization in RLVR for MLLM continual learning, achieving +12.0% Last accuracy over vanilla RLVR baseline by preserving reusable reasoning on high-RP samples.
CaC presents a new spatiotemporal concentrating reward model for video anomalies, built on a novel large-scale dataset and three-stage training with RL and IoU rewards, claiming 25.7% accuracy gains and 11.7% anomaly reduction.
Pest-Thinker is a reinforcement learning framework that improves MLLMs' expert-level reasoning on pest morphology via synthesized CoT trajectories, GRPO optimization, and an LLM-judged feature reward on new benchmarks QFSD and AgriInsect.
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.
Reason-SVG adds a Drawing-with-Thought reasoning stage and GRPO-based reinforcement learning with a hybrid reward to improve LLM and VLM performance on accurate SVG generation.
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 and posterior amplification, yielding accuracy gains and shorter traces.
Introduces FFR task, F2RVLM and FFRS models, and MLDR dataset for retrieving coherent multi-modal dialogue fragments, reporting superior performance on single-dialogue and corpus benchmarks.
TRON supplies 520 rule-verifiable online visual reasoning environments across five ability buckets that generate unlimited training instances for RL post-training, yielding consistent gains on ten external multimodal benchmarks for three vision-language models.
ROMA improves MLLM robustness to seen and unseen visual corruptions by +2.3-2.4% over GRPO on seven reasoning benchmarks while matching clean accuracy.
A plug-and-play RL method adds batch-level distributional supervision via CCC rewards to reduce regression-to-the-mean in MLLMs on imbalanced regression benchmarks.
POINTS-Long is a dual-mode multimodal large language model that uses dynamic visual token scaling to retain 97.7-99.7% accuracy on long-form tasks with 1/40 to 1/10th the tokens and supports streaming via detachable KV-cache.
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.
DeepThinkVLA shows CoT improves VLA models only under decoding and causal alignment, delivering 97% success on LIBERO and 21.7-point gains via hybrid attention and SFT-RL training.
Survey that defines agentic RL for LLMs via POMDPs, introduces a taxonomy of planning/tool-use/memory/reasoning capabilities and domains, and compiles open environments from over 500 papers.
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.
CAI is a training-free inference-time attention intervention that uses two-axis selectivity (where to look and when to intervene) via entropy- and depth-gating to mitigate hallucinations in LVLMs while preserving fluency.
CLOSER-VLN combines hierarchical reasoning, multidimensional verification, and triggered retrieval to reach 32.01% SR and 21.28% SPL on CityNav test-unseen without task-specific training.
Longer textual reasoning chains degrade MLLM accuracy on fine-grained visual tasks; a new normalization and constrained-reward training framework mitigates the effect and sets new SOTA numbers.
UAV-VL-R1 combines SFT and multi-stage GRPO reinforcement learning on a new 50,019-sample HRVQA-VL dataset to deliver substantially higher zero-shot accuracy on UAV visual reasoning tasks than both its 2B baseline and a 72B-scale model.
ThinkAct introduces reinforced visual latent planning in a dual VLA system to enable better long-horizon reasoning and adaptation for embodied tasks.
Time-R1 applies RL with verifiable rewards to post-train LVLMs for temporal video grounding, reaching state-of-the-art results on multiple datasets using only 2.5K samples while also improving general video capabilities.
ConsistRoll enforces cross-view consistency during RLVR training for MLLMs by joint rewards on grouped original and augmented views, yielding robustness gains on math, general, and hallucination benchmarks.
A pipeline of chain-of-thought data synthesis, LoRA-based supervised fine-tuning, rejection sampling, and rule-based reinforcement learning raises multi-image grounding accuracy by 9.04% on MIG-Bench and 4.41% on average across seven other benchmarks.
citing papers explorer
-
From System 1 to System 2: A Survey of Reasoning Large Language Models
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.