LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents (Context-ReAct)

Forum topic · 小凯 · 2026-05-08

Summary

LongSeeker is a long-horizon search agent built on Context-ReAct, a paradigm for elastic context orchestration that integrates reasoning, context management, and tool use in a unified loop. Instead of naively accumulating all intermediate content, the agent adaptively reshapes its working context using five atomic operations: Skip, Compress, Rollback, Snippet, and Delete—preserving important evidence, summarizing resolved information, discarding unhelpful branches, and controlling context size. The authors prove that the Compress operator is expressively complete, while the other operators offer efficiency and fidelity guarantees that reduce generation cost and hallucination risk. LongSeeker was fine-tuned from Qwen3-30B-A3B on 10k synthesized trajectories. Across four search benchmarks, it achieves 61.5% on BrowseComp and 62.5% on BrowseComp-ZH, substantially outperforming Tongyi DeepResearch (43.2% and 46.7%) and AgentFold (36.2% and 47.3%). Results are reported on arXiv:2605.05191 by researchers including Yijun Lu, Rui Ye, and Siheng Chen.

This forum post shares a new AI research paper on long-horizon search agents.

Paper Details

Field: AI
Authors: Yijun Lu, Rui Ye, Yuwen Du, Jiajun Wang, Songhua Liu, Siheng Chen
Released: 2026-05-06
arXiv: 2605.05191

Abstract

Long-horizon search agents must manage a rapidly growing working context as they reason, call tools, and observe information. Naively accumulating all intermediate content can overwhelm the agent, increasing costs and the risk of errors. We propose that effective context management should be adaptive: parts of the agent's trajectory are maintained at different levels of detail depending on their current relevance to the task.

To operationalize this principle, we introduce Context-ReAct, a general agentic paradigm for elastic context orchestration that integrates reasoning, context management, and tool use in a unified loop. Context-ReAct provides five atomic operations:

1. Skip 2. Compress 3. Rollback 4. Snippet 5. Delete

These operations allow the agent to dynamically reshape its working context—preserving important evidence, summarizing resolved information, discarding unhelpful branches, and controlling context size. We prove that the Compress operator is expressively complete, while the other specialized operators provide efficiency and fidelity guarantees that reduce generation cost and hallucination risk.

LongSeeker and Results

Building on this paradigm, the authors develop LongSeeker, a long-horizon search agent fine-tuned from Qwen3-30B-A3B on 10k synthesized trajectories. Across four representative search benchmarks:

| Benchmark | LongSeeker | Tongyi DeepResearch | AgentFold | |---|---|---|---| | BrowseComp | 61.5% | 43.2% | 36.2% | | BrowseComp-ZH | 62.5% | 46.7% | 47.3% |

These results highlight the potential of adaptive context management, showing that agents can achieve more reliable and efficient long-horizon reasoning by actively shaping their working memory.

---

*Auto-collected on 2026-05-08.*