Job opportunities

Centres Inria associés

Type de contrat

Stage/Internship

Contexte

The emergence of Large Language Models (LLMs) has recently accelerated the use and advanced integration of Artificial Intelligence in business tasks, most recently through conversational multi-agent systems. However, extended interactions between agents raise several continuity and consistency issues: loss of task context, history, or decisions, or exchange of redundant or contradictory information. These issues limit the use of LLM-based multi-agent systems in business tasks such as project management. Their mitigation is therefore an active research direction, for example with the design of an external memory [5,6]. In parallel, knowledge graphs (KGs) of the Semantic Web have been mentioned as a source of knowledge to complement LLMs and mitigate their hallucinations [3,4]. In particular, facts from KGs can be used to ground LLMs with processes such as Retrieval Augmented Generation (RAG) [1] or GraphRAG [2]. Interestingly, KGs could also be seen as an external memory for LLM-based agents, where facts could represent decisions, actions, and context. Such a representation could leverage existing ontologies such as PROV-O, Activity Streams, or FOAF. This line of research is associated with major challenges such as:
<ul>
<li style="font-weight: 400;">The need to represent agents discussions, actions, decisions, results within KGs, potentially with different granularity levels</li>
<li style="font-weight: 400;">The need to retrieve relevant context, actions, and results from KGs at the correct granularity level to support agents when they start a new task or encounter a blocking issue (e.g., contradictory information, loss of context)</li>
<li style="font-weight: 400;">The need to detect those blocking situations</li>
</ul>

Mission confié

In this internship, we propose to study the use of knowledge graphs as an external memory for a system constituted by LLM-based conversational agents.
This internship is a collaboration between the Wimmics team (Université Côte d'Azur, Inria, CNRS, I3S) and the Forgeron3 company. It will take place on the premises of the Wimmics team in Sophia Antipolis, in collaboration with Forgeron3 and under the supervision of:
<ul>
<li style="font-weight: 400;">Pierre Monnin (<a href="mailto:pierre.monnin@inria.fr">pierre.monnin@inria.fr</a> – <a href="https://pmonnin.github.io">https://pmonnin.github.io</a>)</li>
<li style="font-weight: 400;">Fabien Gandon (<a href="mailto:fabien.gandon@inria.fr">fabien.gandon@inria.fr</a> – <a href="http://fabien.info">http://fabien.info</a>)</li>
</ul>
Wimmics (Web-Instrumented huMan-Machine Interactions, Communities and Semantics) is a joint research team at Université Côte d’Azur, Inria, CNRS, I3S, whose research lies at the intersection of artificial intelligence and the Web. Wimmics members work on methods to extract, control, query, validate, infer, explain and interact with knowledge.
Forgeron3 develops a platform of collaborative intelligent assistants, based on open source LLMs such as those of Meta and Mistral. Forgeron3's goal is to democratize AI for European SMEs, allowing employees to focus on what matters while repetitive tasks are handled by intelligent assistants, improving every human interaction.

Principales activités

In this internship, we propose to study the use of knowledge graphs as an external memory for a system constituted by LLM-based conversational agents. In particular, the internship will include the following tasks:
<ol>
<li style="font-weight: 400;">State of the art and skills development on LLMs, RAG, GraphRAG, Semantic Web, agents collaboration and memory</li>
<li style="font-weight: 400;">Study of the limitations of an LLM-based agent collaboration from a company-based scenario</li>
<li style="font-weight: 400;">Prototyping a KG memory for multi-agent collaboration</li>
<ol>
<li style="font-weight: 400;">Designing the KG: key entities, classes, relations, potentially re-using and adapting existing ontologies</li>
<li style="font-weight: 400;">Designing a KG construction and completion process where agents complete the KG with relevant information</li>
<li style="font-weight: 400;">Designing a retrieval process to enhance agents context when needed</li>
</ol>
<li style="font-weight: 400;">Experiment and evaluation of results.</li>
<ol>
<li style="font-weight: 400;">Definition of metrics of interest (e.g., information coherence, process achievement, performance of agents)</li>
<li style="font-weight: 400;">Validation on a company-based scenario</li>
</ol>
</ol>

Compétences

You are studying in Master Year 2 / final year of engineering school, with a specialty in computer science or applied mathematics. You are proficient in:
<ul>
<li style="font-weight: 400;">Python programming</li>
<li style="font-weight: 400;">Machine Learning / Deep Learning, especially with frameworks like PyTorch or Tensorflow</li>
<li style="font-weight: 400;">Knowledge of LLMs, multi-agents systems, frameworks like LangChain, and (Graph)RAG would be appreciated.</li>
<li style="font-weight: 400;">Knowledge of the Semantic Web (RDF, RDFS, OWL, SPARQL, knowledge graphs and ontologies) would be appreciated.</li>
<li style="font-weight: 400;">Ability to read and write in English</li>
</ul>
You are curious, eager to learn, face challenges, experiment and discover by yourself.

Référence

2025-09584

Thème

Data and Knowledge Representation and Processing