Highlights
- Strong long-horizon search performance: LongSeeker achieves 61.5 on BrowseComp, 62.5 on BrowseComp-ZH, 78.0 on xbench-2505, and 77.7 on GAIA-text, demonstrating competitive capability across both web search and general agent benchmarks.
- Elastic context orchestration for search agents: We introduce Context-ReAct, a new agentic paradigm that jointly generates reasoning, context meta-operations, and tool calls, enabling agents to dynamically decide when, where, and how to reshape their working context during long-horizon search.
- Comprehensive and fine-grained context control: Context-ReAct defines five atomic operations—Skip, Compress, Rollback, Snippet, and Delete—forming an expressively complete yet efficient operation set for multi-resolution context management.
- Efficient context management at extended horizons: LongSeeker maintains a stable working context of around 15k tokens even across long trajectories, using only a small fraction of its 256k context window while avoiding the rapid context growth of standard ReAct agents.
For more details, please refer to our GitHub repository.
Paper: arXiv:2603.15594