OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior Simulation (2026 · 8 citations)
LLM agents can produce plausible web behavior, but it is hard to check whether they reproduce what a specific person would actually do.
On-Policy Self-Distillation for Efficient Diffusion Language Models with Early-Stage Calibration (2026 · 2 citations)
Diffusion language models such as masked diffusion models (MDMs) decode many tokens in parallel. Their first decoding steps are unreliable because almost every position is still masked. Those early errors carry forward, lowering output quality. They also force the model to unmask only a few tokens per step, which…
Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents (2026 · 2 citations)
Tool-calling agents used in customer service often meet users whose requests lack key details, shift during the conversation, or break system policy.

All works

4 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction ↗arXiv:2508.03613 · no summary yetYong Lin et al.2025 · 67 citations
OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior SimulationAnnual Meeting of the Association for Computational Linguistics (ACL)Ziyi Wang, Yuxuan Lu, Wenbo Li, et al.2026 · 8 citations
On-Policy Self-Distillation for Efficient Diffusion Language Models with Early-Stage CalibrationFindings of the Association for Computational LinguisticsHuaisheng Zhu, MingYu Liu, Junze Liu, et al.2026 · 2 citations
Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User IntentsAnnual Meeting of the Association for Computational Linguistics (ACL)Ziyi Wang, Yuxuan Lu, Yimeng Zhang, et al.2026 · 2 citations

Co-authors here

12 of 18 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 78 times (of the 149,439 papers whose bibliographies we read); 11 citing papers with a page here →.

Updated 31 October 2026