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.
SILO-BENCH: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systems (2026 · 2 citations)
Multi-agent LLM setups are often proposed as a way around context-window limits: each agent holds part of the data, and together they should compute a global answer.
DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding (2026)
Large audio language models are mostly autoregressive. They need a lot of data and compute to scale, and their token-by-token decoding slows inference. The earlier DIFFA work showed that a diffusion LLM backbone can help audio understanding, but only at a small, proof-of-concept scale. DIFFA-2 develops this into a…
When 20 Agents Fail to Sort: The Distributed Sorting Benchmark for Scalable Multi-Agent Systems (2026)
The paper examines whether LLM-based agents can coordinate without heavy human scaffolding, such as predefined roles or scripted pipelines.

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.

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
Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level ↗arXiv:2605.06387 · no summary yetNan Jia et al.2026 · 6 citations
SILO-BENCH: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM SystemsAnnual Meeting of the Association for Computational Linguistics (ACL)Yuzhe Zhang, Feiran Liu, Yi Shan, et al.2026 · 2 citations
DIFFA-2: A Practical Diffusion Large Language Model for General Audio UnderstandingFindings of the Association for Computational LinguisticsJiaming Zhou, Xuxin Cheng, Shiwan Zhao, et al.2026
When 20 Agents Fail to Sort: The Distributed Sorting Benchmark for Scalable Multi-Agent SystemsFindings of the Association for Computational LinguisticsXin Yang, Junhao Wang, Bintao Tang, et al.2026

Co-authors here

12 of 15 co-authors with a page, the most papers together first.

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

Papers of our library cite their works 15 times (of the 149,439 papers whose bibliographies we read); 5 citing papers with a page here →.

Updated 2 November 2026