‘TravelPlanner: A Benchmark for Real-World Planning with Language Agents’ accepted at ICML 2024 with Spotlight (top 3.5%)
‘Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts’ accepted at ICLR 2024 with Spotlight (top 5%)
‘ARM: Adaptive Reasoning Model’ accepted at NeurIPS 2025 with Spotlight (top 3%)
‘AAAR-1.0’ accepted at ICML 2025
‘Mechanistic Interpretability of Implicit Reasoning in Transformers’ accepted at ACL 2025 Findings
Two papers, ‘Irrelevant Information’ and ‘Deductive Beam Search’, accepted at COLM 2024