RRM: Experience-Driven Reflective Retrieval Memory for Long-Horizon Multimodal Reasoning

arXiv:2607.28156 · cs.CL · Submitted 2026-07-30 · Read on arXiv

Jingxiang Fan, Junbao Zhuo, Bochao Zou

cs.CL

Submitted: 2026-07-30

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Multimodal Reasoning — 11× in this paper · explained in 5 episodes
• Benchmark — 8× in this paper · explained in 2 episodes
• Reflective Retrieval Memory — 7× in this paper
• Accuracy — 5× in this paper · explained in 1 episode
• Online Query Reflection — 5× in this paper
• Adaptation — 4× in this paper · explained in 1 episode
• Redundancy — 4× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Generator — 3× in this paper · explained in 2 episodes
• Procedural Knowledge — 3× in this paper · explained in 3 episodes
• Ablation Study — 2× in this paper · explained in 3 episodes
• Failure Modes — 2× in this paper · explained in 3 episodes
• General Knowledge — 2× in this paper
• Hyperparameters — 2× in this paper · explained in 2 episodes
• Online Adaptation — 2× in this paper · explained in 3 episodes
• Person Understanding — 2× in this paper
• Benchmarking — 1× in this paper · explained in 4 episodes
• Core — 1× in this paper · explained in 2 episodes
• Evaluation Protocol — 1× in this paper · explained in 2 episodes
• MLLMs — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 6 episodes

Sources

• Qwen2.5-VL Technical Report
• Advancing Multimodal Agent Reasoning with Long-Term Neuro-Symbolic Memory
• Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
• Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory
• Qwen2.5-Omni Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering