{"total":65,"rows":[{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2505.13032","title":"MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix","created":"2025-05-19","cited_by_count":117,"area":"lr"},{"id":"2505.04921","title":"Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models","created":"2025-05-08","cited_by_count":90,"area":"lr"},{"id":"2511.20785","title":"LongVT: Incentivizing \"Thinking with Long Videos\" via Native Tool Calling","created":"2025-11-25","cited_by_count":61,"area":"lr"},{"id":"2504.21277","title":"Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models","created":"2025-04-30","cited_by_count":44,"area":"lr"},{"id":"2511.15848","title":"Step-Audio-R1 Technical Report","created":"2025-11-19","cited_by_count":36,"area":"lr"},{"id":"2504.15900","title":"SARI: Structured Audio Reasoning via Curriculum-Guided Reinforcement Learning","created":"2025-04-22","cited_by_count":34,"area":"lr"},{"id":"2505.00551","title":"100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models","created":"2025-05-01","cited_by_count":30,"area":"lr"},{"id":"2507.15375","title":"STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Models","created":"2025-07-21","cited_by_count":26,"area":"lr"},{"id":"2508.15827","title":"Mini-Omni-Reasoner: Token-Level Thinking-in-Speaking in Large Speech Models","created":"2025-08-18","cited_by_count":21,"area":"lr"},{"id":"2508.08039","title":"Audio-Thinker: Guiding Audio Language Model When and How to Think via Reinforcement Learning","created":"2025-08-11","cited_by_count":19,"area":"lr"},{"id":"2604.10905","title":"Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music","created":"2026-04-13","cited_by_count":19,"area":null},{"id":"2505.09655","title":"DRA-GRPO: Your GRPO Needs to Know Diverse Reasoning Paths for Mathematical Reasoning","created":"2025-05-14","cited_by_count":18,"area":"lr"},{"id":"2505.09558","title":"WavReward: Spoken Dialogue Models With Generalist Reward Evaluators","created":"2025-05-14","cited_by_count":15,"area":"alignment"},{"id":"2505.18536","title":"Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models","created":"2025-05-24","cited_by_count":14,"area":"lr"},{"id":"2510.20867","title":"Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards","created":"2025-10-23","cited_by_count":12,"area":"lr"},{"id":"2510.09592","title":"Mind-Paced Speaking: A Dual-Brain Approach to Real-Time Reasoning in Spoken Language Models","created":"2025-10-10","cited_by_count":9,"area":"lr"},{"id":"2508.20916","title":"SageLM: A Multi-aspect and Explainable Large Language Model for Speech Judgement","created":"2025-08-28","cited_by_count":7,"area":null},{"id":"2602.23306","title":"ThinkOmni: Lifting Textual Reasoning to Omni-modal Scenarios via Guidance Decoding","created":"2026-02-26","cited_by_count":7,"area":"lr"},{"id":"2602.13685","title":"AuTAgent: A Reinforcement Learning Framework for Tool-Augmented Audio Reasoning","created":"2026-02-14","cited_by_count":6,"area":"lr"},{"id":"2602.14224","title":"The Interspeech 2026 Audio Reasoning Challenge: Evaluating Reasoning Process Quality for Audio Reasoning Models and Agents","created":"2026-02-15","cited_by_count":6,"area":"lr"},{"id":"2512.03783","title":"Omni-AutoThink: Adaptive Multimodal Reasoning via Reinforcement Learning","created":"2025-12-03","cited_by_count":5,"area":"lr"},{"id":"2509.16990","title":"Advancing Speech Understanding in Speech-Aware Language Models with GRPO","created":"2025-09-21","cited_by_count":4,"area":"lr"},{"id":"2603.06854","title":"Are Audio-Language Models Listening? Audio-Specialist Heads for Adaptive Audio Steering","created":"2026-03-06","cited_by_count":4,"area":"mllm"},{"id":"2509.18569","title":"Explore the Reinforcement Learning for the LLM based ASR and TTS system","created":"2025-09-23","cited_by_count":3,"area":null},{"id":"2510.11454","title":"Audio-Maestro: Enhancing Large Audio-Language Models with Tool-Augmented Reasoning","created":"2025-10-13","cited_by_count":3,"area":"lr"},{"id":"2510.18346","title":"AV-Master: Dual-Path Comprehensive Perception Makes Better Audio-Visual Question Answering","created":"2025-10-21","cited_by_count":3,"area":null},{"id":"2602.10439","title":"AudioRouter: Data Efficient Audio Understanding via RL based Dual Reasoning","created":"2026-02-11","cited_by_count":3,"area":"lr"},{"id":"2602.11909","title":"Echo: Towards Advanced Audio Comprehension via Audio-Interleaved Reasoning","created":"2026-02-12","cited_by_count":3,"area":"lr"},{"id":"2607.20166","title":"Audio-Zero: Label-Free Self-Evolution for Fine-Grained Audio Reasoning","created":"2026-07-22","cited_by_count":3,"area":"lr"},{"id":"2608.02831","title":"Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoning","created":"2026-08-03","cited_by_count":3,"area":null},{"id":"2508.10955","title":"Empowering Multimodal LLMs with External Tools: A Comprehensive Survey","created":"2025-08-14","cited_by_count":2,"area":"mllm"},{"id":"2509.07526","title":"Competitive Audio-Language Models with Data-Efficient Single-Stage Training on Public Data","created":"2025-09-09","cited_by_count":2,"area":null},{"id":"2509.12275","title":"Omni-CLST: Error-aware Curriculum Learning with guided Selective chain-of-Thought for audio question answering","created":"2025-09-14","cited_by_count":2,"area":"lr"},{"id":"2509.18579","title":"Teaching Audio Models to Reason: A Unified Framework for Source- and Layer-wise Distillation","created":"2025-09-23","cited_by_count":2,"area":"lr"},{"id":"2509.22461","title":"CMDAR: A Chinese Multi-scene Dynamic Audio Reasoning Benchmark with Diverse Challenges","created":"2025-09-26","cited_by_count":2,"area":"lr"},{"id":"2601.11039","title":"SonicBench: Dissecting the Physical Perception Bottleneck in Large Audio Language Models","created":"2026-01-16","cited_by_count":2,"area":null},{"id":"2605.00969","title":"MedMosaic: A Challenging Large Scale Benchmark of Diverse Medical Audio","created":"2026-05-01","cited_by_count":2,"area":"lr"},{"id":"2605.27190","title":"Learning When to Think While Listening in Large Audio-Language Models","created":"2026-05-26","cited_by_count":2,"area":"lr"},{"id":"2607.16107","title":"Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos","created":"2026-07-17","cited_by_count":2,"area":"lr"},{"id":"2508.03360","title":"CogBench: A Large Language Model Benchmark for Multilingual Speech-Based Cognitive Impairment Assessment","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2509.15661","title":"SightSound-R1: Cross-Modal Reasoning Distillation from Vision to Audio Language Models","created":"2025-09-19","cited_by_count":1,"area":"lr"},{"id":"2509.21960","title":"Think Smart, Not Hard: Difficulty Adaptive Reasoning for Large Audio Language Models","created":"2025-09-26","cited_by_count":1,"area":"lr"},{"id":"2511.09682","title":"Rebellion: Noise-Robust Reasoning Training for Audio Reasoning Models","created":"2025-11-12","cited_by_count":1,"area":"lr"},{"id":"2603.02266","title":"When Scaling Fails: Mitigating Audio Perception Decay of LALMs via Multi-Step Perception-Aware Reasoning","created":"2026-02-28","cited_by_count":1,"area":"lr"},{"id":"2604.12506","title":"Beyond Transcription: Unified Audio Schema for Perception-Aware AudioLLMs","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2604.18187","title":"Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language Models","created":"2026-04-20","cited_by_count":1,"area":"lr"},{"id":"2605.09996","title":"Omni-Persona: Systematic Benchmarking and Improving Omnimodal Personalization","created":"2026-05-11","cited_by_count":1,"area":"mllm"},{"id":"2606.00507","title":"LaSR: Context-Aware Speech Recognition via Latent Reasoning","created":"2026-05-30","cited_by_count":1,"area":"lr"},{"id":"2608.29999","title":"TEMPO: Temporally-grounded Multi-task Post-training for Large Audio-Language Models","created":"2026-08-30","cited_by_count":1,"area":null},{"id":"2609.20849","title":"Enhancing Audio Reasoning via Semantic Summary Prediction","created":"2026-08-07","cited_by_count":1,"area":"lr"},{"id":"2511.14307","title":"Audio Question Answering with GRPO-Based Fine-Tuning and Calibrated Segment-Level Predictions","created":"2025-11-18","cited_by_count":0,"area":"lr"},{"id":"2602.04085","title":"BASS: Benchmarking Audio LMs for Musical Structure and Semantic Reasoning","created":"2026-02-03","cited_by_count":0,"area":"lr"},{"id":"2602.07978","title":"Cross-Linguistic Persona-Driven Data Synthesis for Robust Multimodal Cognitive Decline Detection","created":"2026-02-08","cited_by_count":0,"area":"synth"},{"id":"2603.27667","title":"EvA: An Evidence-First Audio Understanding Paradigm for LALMs","created":"2026-03-29","cited_by_count":0,"area":null},{"id":"2605.00371","title":"GaMMA: Towards Joint Global-Temporal Music Understanding in Large Multimodal Models","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.15984","title":"Beyond Content: A Comprehensive Speech Toxicity Dataset and Detection Framework Incorporating Paralinguistic Cues","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2606.02615","title":"FSA-GRPO: Teaching Auditory LLMs to Use Few-Shot Demonstrations","created":"2026-05-26","cited_by_count":0,"area":"lr"},{"id":"2606.14591","title":"AudioDER: A Deduplication-Enhanced Reasoning Dataset for Post-Training Large Audio-Language Models","created":"2026-06-12","cited_by_count":0,"area":"lr"},{"id":"2609.21666","title":"Samsone: A Family of Open Small Audio Language Models for On-Device Inference","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.22771","title":"ParA-LLM: A Unified Approach to Paralinguistic and Acoustic Speech Understanding","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.26488","title":"Spoken Language Models that Think Aloud","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2609.28344","title":"Mizar: A 159M-Parameter Audio-Language Model for Audio Understanding","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.32536","title":"Do Audio LLMs Listen Before They Act? Diagnosing Acoustic-Context Gating in Voice Agents","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2610.19476","title":"What Does LALM Post-training Learn? Rethinking Audio Understanding and Reasoning Capabilities","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}