RLinf/WideSeek-R1-4b
TEXT GENERATIONConcurrency Cost:1Model Size:4BQuant:BF16Ctx Length:32kPublished:Feb 4, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Warm

RLinf/WideSeek-R1-4b is a 4 billion parameter multi-agent system developed by RLinf, designed for broad information seeking tasks. It utilizes a lead-agent-subagent framework trained via multi-agent reinforcement learning (MARL) to enable scalable orchestration and parallel execution. This model explores width scaling, allowing it to achieve performance comparable to much larger single-agent models on complex information retrieval benchmarks.

Loading preview...