🧑‍🔬 Hongjin Qian

🏛️ Affiliations

🔬Beijing Academy of Artificial IntelligenceBeijing · China2026 · 4 paperscurrent🎓Peking UniversityBeijing · China2026 · 1 papercurrent

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. LiveLongBench: Tackling Long-Context Understanding for Spoken Texts from Live Streams (2026 · 1 citation)
   Current long-context benchmarks are built mostly from polished written text. Real conversational speech is different: it is full of fillers, repetition, fragmented syntax and topic shifts. The authors address this gap with LiveLongBench, a benchmark built from transcripts of Douyin e-commerce live streams. Its…
2. MemoBrain: Executive Memory as an Agentic Brain for Reasoning (2026 · 1 citation)
   Tool-using LLM agents on long-horizon tasks accumulate reasoning traces and tool outputs. These fill their limited context window with noise, which weakens coherence and goal alignment. The authors propose "executive memory" as a remedy. It is a per-task memory that starts empty, evolves online with the reasoning…
3. AWARE: Agentic Knowledge Warehousing for Contextual Intelligence (2026)
   LLMs often fail on questions that need specialized or recent knowledge, and current fixes involve trade-offs.
4. Reinforcing Agentic Search Via Reward Density Optimization (2026)
   Training search agents with reinforcement learning from verifiable rewards (RLVR) runs into a sparsity problem.

All works

5 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

1. LiveLongBench: Tackling Long-Context Understanding for Spoken Texts from Live StreamsFindings of the Association for Computational LinguisticsYongxuan Wu, Runyu Chen, Peiyu Liu, et al.2026 · 1 citation
2. MemoBrain: Executive Memory as an Agentic Brain for ReasoningFindings of the Association for Computational LinguisticsHongjin Qian, Zhao Cao, Zheng Liu2026 · 1 citation
3. AWARE: Agentic Knowledge Warehousing for Contextual IntelligenceFindings of the Association for Computational LinguisticsHongjin Qian, Siqi Bao, Zhao Cao, et al.2026
4. Reinforcing Agentic Search Via Reward Density OptimizationAnnual Meeting of the Association for Computational Linguistics (ACL)Kun Luo, Hongjin Qian, Zheng Liu, et al.2026
5. AgentFactory: A Self-Evolving Framework Through Executable Subagent Accumulation and Reuse ↗Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations) · no summary yetZhang Zhang et al.2026

🤝 Co-authors here

9 co-authors with a page, the most papers together first.

• Zhao Cao ×3
• Zheng Liu ×3
• Siqi Bao ×2
• Jun Zhao
• Kang Liu
• Kun Luo
• Peiyu Liu
• Runyu Chen
• Shitao Xiao

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Findings of the Association for Computational Linguistics ×3: Findings of the Association for Computational Linguistics 2026 ×3
• Annual Meeting of the Association for Computational Linguistics (ACL) ×2: ACL 2026

🔗 Cited by

Papers of our library cite their works 1 time (of the 149,439 papers whose bibliographies we read).

Updated 1 November 2026

This page in Markdown → https://md.research.elamur.ai/free/en/authors/hongjin-qian/