Autonomous agents executing human instructions must operate reliably even when instructions are incomplete. While recent approaches improve detection of missing information, detection alone is insufficient: agents often proceed to execution even after recognizing underspecification, leading to incorrect or unsafe actions. We identify this failure as arising from a lack of coupling between detection and execution, and propose that reliable behavior requires enforcing missing information as a precondition for action. We instantiate this principle in Cocoreli, a modular architecture that represents task structure, tracks missing information, and blocks execution until required details are resolved through targeted clarification. In Cocoreli, detection and prevention are structurally coupled: detecting a missing parameter simultaneously blocks execution. We evaluate Cocoreli in a controlled construction environment isolating underspecification and sequential execution. Cocoreli makes execution reliable by imposing explicit task structure: instructions are represented as parameterized executable objects and execution under unresolved specifications is blocked by construction, eliminating hallucinated actions. In contrast, chain-of-thought, prompt-chaining, and ReAct-style reasoning may still execute under incomplete specifications despite high detection rates. The same representation supports abstraction and reuse, and generalizes to API workflow tasks on ToolBench. These results show that reliable collaborative execution under underspecified instructions requires architectural enforcement, not just model capability.

Most models for triple extraction from texts primarily focus on named entities. However, real-world applications often comprise non-named entities that pose serious challenges for entity linking and disambiguation. We focus on these entities and propose the first LLM-based entity revision framework to improve the quality of extracted triples via a multi-choice question-answering mechanism. When evaluated on two benchmark datasets, our results show a significant improvement, thereby generating more reliable triples for knowledge graphs.

We present an approach for discourse segmentation and discourse connective identification, both at the sentence and document level, within the Disrpt 2021 shared task, a multi-lingual and multi-formalism evaluation campaign. Building on the most successful architecture from the 2019 similar shared task, we leverage datasets in the same or similar languages to augment training data and improve on the best systems from the previous campaign on 3 out of 4 subtasks, with a mean improvement on all 16 datasets of 0.85%. Within the Disrpt 21 campaign the system ranks 3rd overall, very close to the 2nd system, but with a significant gap with respect to the best system, which uses a rich set of additional features. The system is nonetheless the best on languages that benefited from crosslingual training on sentence internal segmentation (German and Spanish).