3 Papers Accepted to EMNLP 2026: RL User Simulators & CoT Steps
shi_weiyan · x · 2026-08-26
All 3 papers submitted to EMNLP 2026 by the author were accepted. The research covers: 1) Building diverse user simulators in RL; 2) Identifying decorative thinking steps in Chain-of-Thought; 3) Combining human annotations with LLM-as-a-judge for reliable evaluation. The author notes that human taste and effort are becoming increasingly distinguishable and valued amidst the sea of AI-flavored papers.
Related event: Professor Gets 3/3 Papers Accepted at EMNLP 2026(2 posts)→
More from Research
- Iliad Intensive Releases Course Materials: Covers SLT and Data Attribution — jd_pressman · 2026-08-26
- Prime Agent technical report: memory hierarchy enables state management via code — rohanpaul_ai · 2026-08-26
- Evo-Harness Paper Finds Verifiers, Not Reflection, Drive Agent Improvement — solyarisoftware · 2026-08-26
- A roadmap to the ColBERT research lineage: From v1 to OBLIQ — anshulkundaje · 2026-08-26
- Google's ReasoningBank: distilling strategies from trajectories turns LLMs into self-improving agents — solyarisoftware · 2026-08-26
- New method boosts AME training efficiency by 5x and scales better to large maps — ChongZzZhang · 2026-08-26