🧑‍🔬 Xunliang Cai

🏛️ Affiliations

🏢MeituanBeijing · China2021–2026 · 88 paperscurrent🎓University of Chinese Academy of SciencesBeijing · China2025–2026 · 6 paperscurrent🎓University of Science and Technology of ChinaHefei · China2026 · 1 papercurrent🏛️Chinese Academy of SciencesBeijing · China2025 · 2 papers🔬Institute of AutomationBeijing · China2025 · 2 papers🔬Institute of Computing TechnologyBeijing · China2025 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

🧭 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. LLMs Know What They Need: Leveraging a Missing Information Guided Framework to Empower Retrieval-Augmented Generation (2025 · 14 citations)
   Retrieval-augmented generation (RAG) helps LLMs with outdated or missing knowledge, but multi-hop questions remain difficult.
2. Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs (2025 · 12 citations)
   LLM error detectors often treat agreement across sampled answers as a sign of correctness. This paper identifies a blind spot in that assumption: self-consistent errors , where a model gives the same wrong answer, up to semantic equivalence, in its greedy output and in all stochastic samples. The authors define these…
3. LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning (2025 · 8 citations)
   Large language models often fail at multi-step logical reasoning when a task is posed in plain text, even when the same task is easy to solve with code.
4. MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning (2026 · 7 citations)
   RLVR methods like GRPO inherit PPO-style hard clipping, which the authors argue is poorly suited to how LLMs learn reasoning.
5. Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text (2026 · 4 citations)
   Training LLM agents for multi-turn tool use is limited by a shortage of realistic trajectories. Most existing synthesis methods start from a fixed API collection, so the data can only be as broad as that collection. The authors invert this approach. They argue that ordinary web text, such as how-to guides and…
6. AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation (2026)
   As reinforcement learning is scaled up for LLM-based agents, checking whether an agent actually did its job becomes a bottleneck.
7. MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks (2026)
   Conversational retrieval decides which evidence a RAG system can use, but its benchmarks have two kinds of flaws.

All works

13 works of theirs in our library, the most cited first; 7 with a page here, the others link their original until we summarise them.

1. From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decoding ↗Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · no summary yetShan Wu et al.2021 · 37 citations
2. LLMs Know What They Need: Leveraging a Missing Information Guided Framework to Empower Retrieval-Augmented GenerationInternational Conference on Computational Linguistics (COLING)Keheng Wang, Feiyu Duan, Peiguang Li, et al.2025 · 14 citations
3. Too Consistent to Detect: A Study of Self-Consistent Errors in LLMsConference on Empirical Methods in Natural Language Processing (EMNLP)Hexiang Tan, Fei Sun, Sha Liu, et al.2025 · 12 citations
4. LogicPro: Improving Complex Logical Reasoning via Program-Guided LearningAnnual Meeting of the Association for Computational Linguistics (ACL)Jin Jiang, Yuchen Yan, Yang Liu, et al.2025 · 8 citations
5. MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM ReasoningAnnual Meeting of the Association for Computational Linguistics (ACL)Xiaoliang Fu, Jiaye Lin, Yangyi Fang, et al.2026 · 7 citations
6. Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level ↗arXiv:2605.06387 · no summary yetNan Jia et al.2026 · 6 citations
7. Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from TextAnnual Meeting of the Association for Computational Linguistics (ACL)Zhihao Xu, Rumei Li, Jiahuan Li, et al.2026 · 4 citations
8. AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware EvaluationFindings of the Association for Computational LinguisticsWentao Shi, Yu Wang, Yuyang Zhao, et al.2026
9. MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval BenchmarksAnnual Meeting of the Association for Computational Linguistics (ACL)Junhao Ruan, Abudukeyumu Abudula, Bei Li, et al.2026
10. Attribution-Based Analysis and Optimization of Modular Agentic Workflows ↗Findings of the Association for Computational Linguistics: ACL 2026 · no summary yetYingxuan Yang et al.2026
11. Large-Scale Diverse Synthesis for Mid-Training ↗Findings of the Association for Computational Linguistics: ACL 2026 · no summary yetXuemiao Zhang et al.2026
12. LinkQA: Synthesizing Diverse QA from Multiple Seeds Strongly Linked by Knowledge Points ↗Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetXuemiao Zhang et al.2026
13. DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding ↗Findings of the Association for Computational Linguistics: ACL 2026 · no summary yetJiaming Zhou et al.2026

🤝 Co-authors here

12 of 34 co-authors with a page, the most papers together first.

• Jingang Wang ×3
• Xin Chen ×2
• Bei Li
• Binbin Zheng
• Du Su
• Fei Sun
• Fuli Feng
• Hexiang Tan
• Huawei Shen
• Hui Su
• Jiahuan Li
• Jianing Wang

Venues

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

• Annual Meeting of the Association for Computational Linguistics (ACL) ×5: ACL 2026 ×3, ACL 2025
• Findings of the Association for Computational Linguistics: ACL 2026 ×3
• International Conference on Computational Linguistics (COLING): COLING 2025
• Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2025
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026
• Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

🔗 Cited by

Papers of our library cite their works 62 times (of the 149,439 papers whose bibliographies we read); 16 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

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