Andrei Stefan Bejgu

I build AI agents that hold up in production. At SylloTips I work on the runtime that governs how agents plan, act, and stay grounded: orchestration, guardrails, memory and tooling, so an agent reasons over a real company instead of hallucinating its way through it.

Before this, a Ph.D. in AI with Sapienza’s NLP group and Babelscape, on how machines pin down what words actually mean in context. That work landed at ACL 2024 and EMNLP 2025.

Currently

What I’m building now

Most “AI agents” demo well and fall apart the moment a real workflow touches them. My job is the unglamorous middle: making an agent’s reasoning trustworthy, repeatable, and supervisable.

orchestration

Agent orchestration & governance

Agents that plan multi-step work, recover when a step fails, and stay grounded: they cite what they actually know and say so when they don't, instead of making things up.

memory

Agentic context engineering & memory

Shaping behaviour through evolving context and durable memory. What an agent carries between turns is what makes it reliable.

protocol

MCP & tool execution

Building Model Context Protocol servers, and running agent-written code in sandboxed environments so agents can read, transform and generate complex files, then call real tools safely with the human still in the loop.

human-in-loop

Continuous improvement

Subject-matter experts correct an agent once; those corrections become durable, governed knowledge the whole system learns from. No retraining cycle required.

Agent Orchestration Agent Governance Agentic Context Engineering Model Context Protocol Agent Memory Grounded RAG Multilingual NLP

Background

Research & open source

LLM-OASIS · Computational Linguistics 2026

Co-first author on the largest resource for end-to-end factuality evaluation: can a system tell whether generated text is actually faithful to its sources, not just fluent? The grounding problem behind every agent I build now.

Word Sense Linking · ACL 2024

Disambiguating word meaning on real, messy text, not just curated benchmarks. The hard part isn’t the dictionary; it’s deciding which sense a sentence actually triggers.

ConceptPedia · EMNLP 2025

A large-scale resource connecting concepts across languages, built to give models a shared semantic backbone instead of a per-language patchwork.

Beanis · Redis ODM for Python

A Pydantic-style typed ODM for Redis: ~70% less boilerplate, performance within 8% of raw Redis. For people who want type safety without giving up speed.

I like the seam between research and production: taking something that works in a paper and making it survive contact with messy data and tight latency budgets. When I’m not on that, I’m writing it up or shipping it as open source.

news

Jun 15, 2026	Building SylloTips’ governed agent runtime: orchestration, Model Context Protocol tooling, and agent memory that keeps reasoning grounded and supervisable.
Nov 07, 2025	ConceptPedia accepted at EMNLP 2025: a large-scale, cross-lingual concept resource for grounding semantic understanding.
Oct 23, 2025	Released Beanis, a typed Redis ODM for Python: ~70% less boilerplate, performance within 8% of raw Redis.
Aug 12, 2024	Word Sense Linking presented at ACL 2024: disambiguating word meaning on real, in-the-wild text.

latest posts

Nov 11, 2025	Build Stateful AI Agents with LangGraph + Beanis: RAG with Memory in 200 Lines
Nov 05, 2025	Concept-pedia: Breaking Free from ImageNet's Shadow in Multimodal AI
Oct 30, 2025	Using Redis as a Geo-Spatial Cache: Building a Restaurant Finder with Beanis

selected publications

Truth or Mirage? Towards End-to-End Factuality Evaluation with LLM-OASIS

Alessandro Scirè^*, Andrei Stefan Bejgu^*, Simone Tedeschi, and 3 more authors

Computational Linguistics, 2026

DOI arXiv Bib HTML Code

@article{scie2024truthmirageendtoendfactuality,
  title = {Truth or Mirage? Towards End-to-End Factuality Evaluation with LLM-OASIS},
  author = {Scir{\`e}, Alessandro and Bejgu, Andrei Stefan and Tedeschi, Simone and Ghonim, Karim and Martelli, Federico and Navigli, Roberto},
  journal = {Computational Linguistics},
  year = {2026},
  volume = {52},
  number = {1},
  pages = {1--41},
  publisher = {MIT Press},
  author+an = {2=highlight},
  doi = {10.1162/coli.a.575},
}

EMNLP

Concept-pedia: A Wide-coverage Semantically-annotated Multimodal Dataset

Karim Ghonim, Andrei Stefan Bejgu, Alberte Fernández-Castro, and 1 more author

In EMNLP, 2025

Bib PDF

@inproceedings{ghonim2025conceptpedia,
  title = {Concept-pedia: A Wide-coverage Semantically-annotated Multimodal Dataset},
  author = {Ghonim, Karim and Bejgu, Andrei Stefan and Fern{\'a}ndez-Castro, Alberte and Navigli, Roberto},
  booktitle = {EMNLP},
  year = {2025},
  author+an = {2=highlight},
  url = {https://aclanthology.org/2025.emnlp-main.1745/},
}

ACL

Word Sense Linking: Disambiguating Outside the Sandbox

Andrei Stefan Bejgu, Edoardo Barba, Luigi Procopio, and 2 more authors

In ACL, 2024

Bib Code

@inproceedings{wordsenselinking,
  title = {Word Sense Linking: Disambiguating Outside the Sandbox},
  author = {Bejgu, Andrei Stefan and Barba, Edoardo and Procopio, Luigi and Fernández-Castro, Alberte and Navigli, Roberto},
  booktitle = {ACL},
  year = {2024},
  author+an = {1=highlight},
}

EACL

CroCoAlign: A Cross-Lingual, Context-Aware and Fully-Neural Sentence Alignment System for Long Texts

Francesco Molfese, Andrei Stefan Bejgu, Simone Tedeschi, and 2 more authors

In EACL, 2024

Bib Code

@inproceedings{molfese-etal-2024-neuralign,
  title = {CroCoAlign: A Cross-Lingual, Context-Aware and Fully-Neural Sentence Alignment System for Long Texts},
  author = {Molfese, Francesco and Bejgu, Andrei Stefan and Tedeschi, Simone and Conia, Simone and Navigli, Roberto},
  booktitle = {EACL},
  year = {2024},
  author+an = {2=highlight},
}