Research graph
References from Ego-R1: Agentic Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning. Local targets link to admitted publications; unresolved targets remain external evidence.
GPT-4 technical report
2023 · External reference
Claude 3.5 sonnet
2024 · External reference
Qwen2. 5-vl technical report
2025 · External reference
10.52202/079017-1684
10.52202/079017-1684 · External reference
10.1609/aaai.v39i2.32214
10.1609/aaai.v39i2.32214 · External reference
10.1007/s11263-025-02676-0
10.1007/s11263-025-02676-0 · External reference
LongVILA: Scaling long-context visual language models for long videos
2025 · External reference
10.1109/cvpr52733.2024.01355
10.1109/cvpr52733.2024.01355 · External reference
SFT memorizes, RL generalizes: A comparative study of foundation model post-training
2025 · External reference
Scaling egocentric vision: The epic-kitchens dataset
External reference
10.1038/s41586-025-09422-z
10.1038/s41586-025-09422-z · External reference
10.52202/085713-4126
10.52202/085713-4126 · External reference
10.1109/cvpr52733.2024.01229
10.1109/cvpr52733.2024.01229 · External reference
10.1109/cvpr52734.2025.00847
10.1109/cvpr52734.2025.00847 · External reference
10.1007/978-3-031-72670-5_5
10.1007/978-3-031-72670-5_5 · External reference
ReTool: Reinforcement learning for strategic tool use in LLMs
2026 · External reference
10.52202/085713-3310
10.52202/085713-3310 · External reference
10.1177/001316447303300309
10.1177/001316447303300309 · External reference
10.1109/cvpr52734.2025.02245
10.1109/cvpr52734.2025.02245 · External reference
Gemini 3.1 pro preview
2026 · External reference
10.1007/978-3-031-72624-8_6
10.1007/978-3-031-72624-8_6 · External reference
Gemini 2.5: Our most intelligent AI model
2025 · External reference
ToRA: A tool-integrated reasoning agent for mathematical problem solving
2024 · External reference
10.1109/cvpr52688.2022.01842
10.1109/cvpr52688.2022.01842 · External reference
10.1109/cvpr52733.2024.01834
10.1109/cvpr52733.2024.01834 · External reference
Vision-R1: Incentivizing reasoning capability in multimodal large language models
2026 · External reference
10.1109/iccvw69036.2025.00614
10.1109/iccvw69036.2025.00614 · External reference
Search-R1: Training LLMs to reason and leverage search engines with reinforcement learning
2025 · External reference
VideoMem: Enhancing ultra-long video understanding via adaptive memory management
2025 · External reference
10.1109/iccv51701.2025.00323
10.1109/iccv51701.2025.00323 · External reference
10.1007/978-3-032-37627-5_35
10.1007/978-3-032-37627-5_35 · External reference
LLaVA-onevision: Easy visual task transfer
2025 · External reference
VideoChat: Chat-centric video understanding
2024 · External reference
TORL: Scaling tool-integrated RL
2026 · External reference
EgoToM: Benchmarking theory of mind reasoning from egocentric videos
2025 · External reference
10.18653/v1/2024.findings-acl.53
10.18653/v1/2024.findings-acl.53 · External reference
Coarse correspondence elicit 3D spacetime understanding in multimodal language model
2024 · External reference
Oryx MLLM: On-demand spatial-temporal understanding at arbitrary resolution
2025 · External reference
Chain-of-spot: Interactive reasoning improves large vision-language models
2024 · External reference
10.24894/sprengglossarium_o01535
10.24894/sprengglossarium_o01535 · External reference
10.52202/085713-5602
10.52202/085713-5602 · External reference
10.18653/v1/2025.emnlp-main.564
10.18653/v1/2025.emnlp-main.564 · External reference
10.18653/v1/2024.acl-long.679
10.18653/v1/2024.acl-long.679 · External reference
10.52202/075280-2004
10.52202/075280-2004 · External reference
Hello GPT-4o
2024 · External reference
Introducing GPT-4.1 in the API
2025 · External reference
Openai O3 and O4-mini system card
2025 · External reference
TALM: Tool augmented language models
2025 · External reference
10.1109/cvpr52734.2025.02226
10.1109/cvpr52734.2025.02226 · External reference
10.52202/085713-3524
10.52202/085713-3524 · External reference
ToolLLM: Facilitating large language models to master 16000 real-world apis
2024 · External reference
10.1109/iccv51701.2025.01942
10.1109/iccv51701.2025.01942 · External reference
10.1109/cvpr52733.2024.01762
10.1109/cvpr52733.2024.01762 · External reference
10.52202/075280-2997
10.52202/075280-2997 · External reference
DeepSeekMath: Pushing the limits of mathematical reasoning in open language models
2024 · External reference
LongVU: Spatiotemporal adaptive compression for long video-language understanding
2025 · External reference
10.1109/cvpr52734.2025.02436
10.1109/cvpr52734.2025.02436 · External reference
10.1109/cvpr52733.2024.01725
10.1109/cvpr52733.2024.01725 · External reference
10.52202/075280-1688
10.52202/075280-1688 · External reference
OpenThinkIMG: Learning to think with images via visual tool reinforcement learning
2025 · External reference
10.52202/075280-3309
10.52202/075280-3309 · External reference
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
2024 · External reference
10.18653/v1/2025.findings-acl.1247
10.18653/v1/2025.findings-acl.1247 · External reference
OTC: Optimal tool calls via reinforcement learning
2025 · External reference
MathCoder: Seamless code integration in LLMs for enhanced mathematical reasoning
2024 · External reference
10.52202/085713-2243
10.52202/085713-2243 · External reference
10.1007/978-3-031-72989-8_4
10.1007/978-3-031-72989-8_4 · External reference
InternVideo2. 5: Empowering video MLLMs with long and rich context modeling
2025 · External reference
LifelongMemory: Leveraging LLMs for answering queries in long-form egocentric videos
2023 · External reference
10.1109/cvpr52734.2025.00311
10.1109/cvpr52734.2025.00311 · External reference
10.52202/068431-1800
10.52202/068431-1800 · External reference
10.1007/978-3-031-73414-4_26
10.1007/978-3-031-73414-4_26 · External reference
AutoGen: Enabling next-gen LLM applications via multi-agent conversation
2024 · External reference
Grounded chain-of-thought for multimodal large language models
2026 · External reference
10.1109/iccv51701.2025.00202
10.1109/iccv51701.2025.00202 · External reference
10.1109/cvpr52733.2024.01284
10.1109/cvpr52733.2024.01284 · External reference
Qwen2. 5-math technical report: Toward mathematical expert model via self-improvement
2024 · External reference
10.1007/978-3-031-73232-4_2
10.1007/978-3-031-73232-4_2 · External reference
10.1109/cvpr52734.2025.02690
10.1109/cvpr52734.2025.02690 · External reference
10.1109/iccv51701.2025.00229
10.1109/iccv51701.2025.00229 · External reference
LongVT: Incentivizing ‘thinking with long videos’ via native tool calling
2026 · External reference
10.52202/085713-5450
10.52202/085713-5450 · External reference
10.18653/v1/2025.emnlp-main.158
10.18653/v1/2025.emnlp-main.158 · External reference
PRL: Process reward learning improves LLMs’ reasoning ability and broadens the reasoning boundary
2026 · External reference
ReAct: Synergizing reasoning and acting in language models
External reference
10.1109/cvpr52734.2025.00802
10.1109/cvpr52734.2025.00802 · External reference
10.1109/iccv51701.2025.00181
10.1109/iccv51701.2025.00181 · External reference
Long context transfer from language to vision
2024 · External reference
10.1109/iccv51701.2025.01918
10.1109/iccv51701.2025.01918 · External reference
LLaVA-next: A strong zero-shot video understanding model
2024 · External reference
10.18653/v1/2026.findings-acl.351
10.18653/v1/2026.findings-acl.351 · External reference
10.18653/v1/2025.emnlp-main.22
10.18653/v1/2025.emnlp-main.22 · External reference
VideoAgent2: Enhancing the LLM-based agent system for long-form video understanding by uncertainty-aware cot
2025 · External reference
Solving challenging math word problems using GPT-4 code interpreter with code-based self-verification
2024 · External reference
