News
- Aug. 2026 · our paper Breaking Self-Consistency in Safety via Anchored Bipolicy Self-Play is available online.
- May. 2026 · our paper Benchmarking at the Edge of Comprehension has been accepted as spotlight at ICML'26.
- May. 2026 · our paper Agentic Business Process Management: A Research Manifesto has been accepted at BPM'26 (Journal Track).
- Dec. 2025 · our paper An End-to-end Planning Framework with Agentic LLMs and PDDL is available online.
- Sept. 2025 · our paper Large Language Models Miss the Multi-Agent Mark has been accepted as a position paper at NeurIPS'25 (acceptance ~5%). -->
- Mar. 2025 · our paper Assessing Dialect Fairness and Robustness of Large Language Models in Reasoning Tasks is accepted at ACL'25 (main).
- Mar. 2025 · our paper When Claims Evolve: Evaluating and Enhancing the Robustness of Embedding Models Against Misinformation Edits is accepted at ACL'25 (Findings).
- Jan. 2025 · our paper Language Models are Implicitly Continuous has been accepted at ICLR'25.
Contact
(surname follows "Emanuele" without spaces)