Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-22T08:59:28.405218Z
Paper Citation Record · LEDGER
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning
As of 11 August 2026, this Paper Citation Record lists 56 of 56 outbound references and 0 inbound Pith citation observations for arXiv:2605.20342.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
56 of 56 outbound references displayed
- verified exact39
- verified fuzzy14
- unresolved1
- parse uncertain0
- malformed identifier1
- metadata mismatch1
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 11d64e63-8697-451f-ab17-adb889e689be · outbound
This paper cites Qwen3-VL Technical Report.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Qwen3-VL Technical Report
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T09:01:19.357015Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation b9ab5b36-e97a-4777-a6cb-7a72e05e156b · outbound
This paper cites Videochat-m1: Collaborative policy planning for video understanding via multi-agent reinforcement learning.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Videochat-m1: Collaborative policy planning for video understanding via multi-agent reinforcement learning
Reference 2
- Resolution
- verified exact
- arxiv_id, observed 2026-05-22T09:01:19.363227Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation a07535a1-ea6f-42e5-93cc-bd3e67c0ec95 · outbound
This paper cites Lvagent: Long video understanding by multi-round dynamical collaboration of mllm agents.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Lvagent: Long video understanding by multi-round dynamical collaboration of mllm agents
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-22T09:01:20.930201Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 9c4da7a0-ffc7-4c00-80cf-4061d5bc8e99 · outbound
This paper cites Scaling rl to long videos.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Scaling rl to long videos
Reference 4
- Resolution
- verified exact
- arxiv_id, observed 2026-05-22T09:01:19.345470Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 4bda5484-570b-42a7-a569-1bde97498c72 · outbound
This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Reference 5
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T09:01:19.429746Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 5d373ee7-5850-47a2-bc2d-27ed854fd62b · outbound
This paper cites Videozoomer: Reinforcement-learned temporal focusing for long video reasoning.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Videozoomer: Reinforcement-learned temporal focusing for long video reasoning
Reference 6
- Resolution
- verified exact
- arxiv_id, observed 2026-05-22T09:01:19.393906Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 10e7a9e4-510a-4ae6-bbf7-f0072826bd41 · outbound
This paper cites Video-R1: Reinforcing Video Reasoning in MLLMs.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Video-R1: Reinforcing Video Reasoning in MLLMs
Reference 7
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T09:01:19.493287Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 43c23bfe-62e2-4bed-9bf6-18f65201e346 · outbound
This paper cites Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-22T09:01:20.993140Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 9e9eaa7f-0e39-4bfc-9791-380ff2587424 · outbound
This paper cites Love- r1: Advancing long video understanding with an adaptive zoom-in mechanism via multi-step reasoning.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Love- r1: Advancing long video understanding with an adaptive zoom-in mechanism via multi-step reasoning
Reference 9
- Resolution
- verified exact
- arxiv_id, observed 2026-05-22T09:01:19.313489Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 15a3adf2-8211-4f33-84b2-6124d127428b · outbound
This paper cites AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning
Reference 10
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T09:01:19.399223Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 01b19d05-c715-48f4-bcee-fcf5a7706839 · outbound
This paper cites Tall: Temporal activity localization via language query.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Tall: Temporal activity localization via language query
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-22T09:01:20.974857Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 64069ec1-39cf-441b-bdc2-66a380f07e77 · outbound
This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Reference 12
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T09:01:19.333120Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 4491bede-b39f-4dfe-be41-aa9c2f3a23c6 · outbound
This paper cites Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
Reference 13
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T09:01:19.452182Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 835da0e0-7969-4c58-b50b-0d44511cf5fd · outbound
This paper cites GPT-4o System Card.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning GPT-4o System Card
Reference 14
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T09:01:19.463016Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 5c96d7f0-6cf8-4193-b55f-be3596f6bcd2 · outbound
This paper cites Sage: Training smart any-horizon agents for long video reasoning with reinforcement learning.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Sage: Training smart any-horizon agents for long video reasoning with reinforcement learning
Reference 15
- Resolution
- verified exact
- arxiv_id, observed 2026-05-22T09:01:19.505342Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation dcd26375-f579-4fbb-a128-30fe1406fc17 · outbound
This paper cites VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning
Reference 16
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T09:01:19.480880Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 2a996420-c494-44da-807e-579e2af75a27 · outbound
This paper cites Longvideoagent: Multi-agent reasoning with long videos.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Longvideoagent: Multi-agent reasoning with long videos
Reference 17
- Resolution
- verified exact
- arxiv_id, observed 2026-05-22T09:01:19.499479Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 3333968e-5d03-4a75-8f9f-4b7c2843ad0f · outbound
This paper cites MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding
Reference 18
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T09:01:19.306955Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation d8dd16e2-9b44-41e6-8459-ed5c2c9ff29c · outbound
This paper cites MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning
Reference 19
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T09:01:19.375108Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 66263d3d-1e07-46c2-9bf7-313456d8880d · outbound
This paper cites Sparse but critical: A token-level analysis of distributional shifts in rlvr fine-tuning of llms.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Sparse but critical: A token-level analysis of distributional shifts in rlvr fine-tuning of llms
Reference 20
- Resolution
- verified exact
- arxiv_id, observed 2026-05-22T09:01:19.418117Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 63265969-52a1-418b-911e-bf4039e3173f · outbound
This paper cites Conan: Progressive learning to reason like a detective over multi-scale visual evidence.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Conan: Progressive learning to reason like a detective over multi-scale visual evidence
Reference 21
- Resolution
- verified exact
- arxiv_id, observed 2026-05-22T09:01:19.288368Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 4dceac67-6f16-4c5c-b430-8424f0cdd054 · outbound
This paper cites LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL
Reference 22
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T09:01:19.446979Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 0c86dbcc-5cd4-4e1c-85ed-99cd3007d537 · outbound
This paper cites Safety Alignment Should Be Made More Than Just a Few Tokens Deep.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Safety Alignment Should Be Made More Than Just a Few Tokens Deep
Reference 23
- Resolution
- verified exact
- arxiv_id, observed 2026-05-22T09:01:19.405588Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 9577281b-0530-42f5-b15d-1405b49175e6 · outbound
This paper cites ToolRL: Reward is All Tool Learning Needs.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning ToolRL: Reward is All Tool Learning Needs
Reference 24
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T09:01:19.468570Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 9fec77ae-da37-46ec-8e5f-eb70100f53c7 · outbound
This paper cites Qwen2.5-VL Technical Report.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Qwen2.5-VL Technical Report
Reference 25
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T09:01:19.320041Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 318600d3-154c-4be7-b6a7-e1ddb14efdd7 · outbound
This paper cites Revisiting the Superficial Alignment Hypothesis.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Revisiting the Superficial Alignment Hypothesis
Reference 26
- Resolution
- verified exact
- arxiv_id, observed 2026-05-22T09:01:19.369543Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 34c13d4f-32c9-49db-a094-eb0077c25ab4 · outbound
This paper cites Toolformer: Language models can teach themselves to use tools.Advances in neural information processing systems, 36: 68539–68551.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Toolformer: Language models can teach themselves to use tools.Advances in neural information processing systems, 36: 68539–68551
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-22T09:01:20.984137Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 93b694e0-e2b5-4647-bc9f-35bd577131b2 · outbound
This paper cites Zoom-zero: Reinforced coarse-to-fine video understanding via temporal zoom-in.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Zoom-zero: Reinforced coarse-to-fine video understanding via temporal zoom-in
Reference 28
- Resolution
- verified exact
- arxiv_id, observed 2026-05-22T09:01:19.339818Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 6335e4ab-42b2-4114-be63-130c9bad0569 · outbound
This paper cites Defining and characterizing reward gaming.Advances in Neural Information Processing Systems, 35:9460– 9471.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Defining and characterizing reward gaming.Advances in Neural Information Processing Systems, 35:9460– 9471
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-22T09:01:20.978251Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 0e369321-cba3-46a9-bba5-bdc3c1ffcb3b · outbound
This paper cites Enhancing agentic rl with progressive reward shaping and value-based sampling policy optimization.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Enhancing agentic rl with progressive reward shaping and value-based sampling policy optimization
Reference 30
- Resolution
- verified exact
- arxiv_id, observed 2026-05-22T09:01:19.282064Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 426f22e1-0f62-4fb6-989e-b07d4be97c33 · outbound
This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
Reference 31
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T09:01:19.326982Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation cc5ffa93-4aa7-4fbb-8afa-8c7c0ad5032c · outbound
This paper cites Ignore the kl penalty! boosting exploration on critical tokens to enhance rl fine-tuning.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Ignore the kl penalty! boosting exploration on critical tokens to enhance rl fine-tuning
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-22T09:01:20.987834Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation f56c6107-f6a2-4284-9e06-839afd8ae116 · outbound
This paper cites Videorft: Incentivizing video reasoning capability in mllms via reinforced fine-tuning.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Videorft: Incentivizing video reasoning capability in mllms via reinforced fine-tuning
Reference 33
- Resolution
- verified exact
- arxiv_id, observed 2026-05-22T09:01:19.412131Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 447ca47e-b469-4201-ae53-6c35e39e9d54 · outbound
This paper cites Video-thinker: Sparking” thinking with videos” via reinforcement learning.arXiv preprint arXiv:2510.23473.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Video-thinker: Sparking” thinking with videos” via reinforcement learning.arXiv preprint arXiv:2510.23473
Reference 34
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-22T09:01:19.423879Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation ee9f4ea0-3d77-455a-9db0-c087dd67995c · outbound
This paper cites Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL
Reference 35
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T09:01:19.381541Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 4a6146b1-1afc-48b8-aecf-5823935a520f · outbound
This paper cites Lvbench: An extreme long video understanding benchmark.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Lvbench: An extreme long video understanding benchmark
Reference 36
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-22T09:01:20.968664Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation e7c0e7d3-1838-4170-b85c-c3ce2f1d2511 · outbound
This paper cites Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding
Reference 37
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T09:01:19.294041Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 16e6aac2-8b40-4e69-92b0-fcd993528ea5 · outbound
This paper cites Longvideobench: A benchmark for long- context interleaved video-language understanding.Advances in Neural Information Processing Systems, 37:28828–28857.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Longvideobench: A benchmark for long- context interleaved video-language understanding.Advances in Neural Information Processing Systems, 37:28828–28857
Reference 38
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-22T09:01:20.922182Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation dfdd3cfb-8742-4a43-94a0-7c5b9e6e09e9 · outbound
This paper cites SVAgent: Storyline-Guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning SVAgent: Storyline-Guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration
Reference 39
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T09:01:19.300469Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation caa806a2-4ea6-4fe6-8ce5-3067612f734c · outbound
This paper cites Inex: Hallucination mitigation via introspection and cross-modal multi-agent collaboration.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Inex: Hallucination mitigation via introspection and cross-modal multi-agent collaboration
Reference 40
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-22T09:01:20.934646Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 9d494c51-66e2-4e41-8b30-5e2ce9880069 · outbound
This paper cites LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling
Reference 41
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T09:01:19.351659Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation a9c212c8-6ef0-4c3a-b18f-328a8d6ed33f · outbound
This paper cites ReAct: Synergizing Reasoning and Acting in Language Models.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning ReAct: Synergizing Reasoning and Acting in Language Models
Reference 42
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T09:01:19.387738Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 32069add-ff4e-47a2-87aa-6ed8d5967fb7 · outbound
This paper cites Re-thinking temporal search for long-form video understanding.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Re-thinking temporal search for long-form video understanding
Reference 43
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-22T09:01:20.916561Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 3085af64-b957-48ed-8cce-23e773a66606 · outbound
This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning DAPO: An Open-Source LLM Reinforcement Learning System at Scale
Reference 44
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T09:01:19.441375Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation bd90550d-0b58-44b7-9105-d3fe25a305a5 · outbound
This paper cites Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning
Reference 45
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T09:01:19.474877Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 5b30b0c5-9fc2-4cc5-8af5-5cda085f1ec7 · outbound
This paper cites Rewatch-r1: Boosting complex video reasoning in large vision-language models through agentic data synthesis.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Rewatch-r1: Boosting complex video reasoning in large vision-language models through agentic data synthesis
Reference 46
- Resolution
- verified exact
- arxiv_id, observed 2026-05-22T09:01:19.511483Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation bb64a801-46c1-4a1a-96ba-865f08b1e2d4 · outbound
This paper cites Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning
Reference 47
- Resolution
- verified exact
- arxiv_id, observed 2026-05-22T09:01:19.487650Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 14135592-ea68-402b-900d-2c6c8c6161e5 · outbound
This paper cites Open- mmreasoner: Pushing the frontiers for multimodal rea- soning with an open and general recipe.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Open- mmreasoner: Pushing the frontiers for multimodal rea- soning with an open and general recipe
Reference 48
- Resolution
- verified exact
- arxiv_id, observed 2026-05-22T09:01:19.435943Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation f33abe2f-cb93-4886-89c8-3f7ba45f623c · outbound
This paper cites Deep video discovery: Agentic search with tool use for long-form video understanding.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Deep video discovery: Agentic search with tool use for long-form video understanding
Reference 49
- Resolution
- verified exact
- arxiv_id, observed 2026-05-22T09:01:19.517616Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 8ceb8f83-95d5-4e8c-83b8-9d9cccdc2844 · outbound
This paper cites LLaVA-Video: Video Instruction Tuning With Synthetic Data.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning LLaVA-Video: Video Instruction Tuning With Synthetic Data
Reference 50
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T09:01:19.457893Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 73b7b9ae-961d-4a95-a61b-aab26c351ad9 · outbound
This paper cites Mmvu: Measuring expert-level multi-discipline video understanding.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Mmvu: Measuring expert-level multi-discipline video understanding
Reference 51
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-22T09:01:21.002747Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation b7f2ff73-8b85-4aff-9276-6c7d28623b5f · outbound
This paper cites Lima: Less is more for alignment.Advances in Neural Information Processing Systems, 36:55006–55021.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Lima: Less is more for alignment.Advances in Neural Information Processing Systems, 36:55006–55021
Reference 52
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-22T09:01:20.960210Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation cb1244fc-d923-4232-8cb4-750fef90a4c6 · outbound
This paper cites inspect 00:30–00:50.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning inspect 00:30–00:50
Reference 53
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-22T09:01:20.952117Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 4be40d03-7c59-480e-b679-19a571246cfb · outbound
This paper cites an unresolved cited work.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Unresolved cited work
Reference 54
- Resolution
- unresolved
- raw_fallback, observed 2026-05-22T09:01:20.945995Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 1b5ec251-eabc-421c-a2cd-5e2391d8222a · outbound
This paper cites You may issue multiple <tool_call> blocks in one turn to inspect different temporal windows in parallel.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning You may issue multiple <tool_call> blocks in one turn to inspect different temporal windows in parallel
Reference 55
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-22T09:01:20.939425Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 2ea4707c-0ac8-4e46-a62d-54cea6b15466 · outbound
This paper cites name": "crop_video.
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning name": "crop_video
Reference 56
- Resolution
- malformed identifier
- raw_fallback, observed 2026-05-22T09:01:20.997201Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Pith citing papers
No inbound Pith citation observations are available.