Internship: Memory for LLM Agents F/M

About NAVER LABS Europe

NAVER LABS Europe is part of the R&D division of NAVER, Korea’s leading Internet portal and a global tech company with a range of services that include search, commerce, content, fintech, robotics and cloud.

The position

In this internship, we are looking for a PhD or MSc student to join us in creating effective and flexible memory mechanisms for LLM Agents.

LLM Agents, equipped with tool use modules, reasoning, and planning, have emerged as a rapidly growing area of research and development, with a vast range of applications including robotics, web automation, programming, and scientific discovery. Recent research efforts [1] focus on building strong domain-adapted agents and studying aspects such as continual self-improvement, training data creation, multi-aspect evaluation, and memory design. This internship focuses on memory [2-4], a crucial component of building effective production-ready agents, enabling them to accumulate insights from prior experience, reuse successful strategies, and avoid repeating mistakes.

The research internship will include:

• conducting research on the latest advancements in natural language processing and LLMs
• designing and implementing memory mechanisms for LLM agents
• testing memory approaches on several agentic environments
• analyzing success and failure cases
• participating in team meetings and brainstorming sessions
• documenting research findings (the primary goal of the internship is to submit a research paper)

Details:

• Duration: six months
• Start date: as soon as possible
• Intern will be working with a team of researchers with a strong background in retrieval-augmented generation [5-7], natural language processing [8-9], and information retrieval [10-11].

About the research team

In the Interactive Systems group, we develop AI capabilities that enable robots to interact safely with humans, other robots, and systems. For a robot to be truly useful, it must represent its knowledge of the world, share what it learns, and interact with other agents, particularly humans. Our research integrates expertise in human-robot interaction, natural language processing, speech, information retrieval, data management, and low-code/no-code programming to create AI components that empower next-generation robots to perform complex real-world tasks.

What we're looking for

• A PhD or final-year MSc student in NLP-related domains

• Solid background in deep learning and natural language processing

• Hands-on experience with PyTorch, Hugging Face, and Slurm 

• High autonomy in conducting NLP research, i.e. implementing approaches, running experiments, and documenting results

• Accepted publications at top-tier conferences such as ACL, EMNLP, NAACL, or EACL are a strong plus

• Background in retrieval-augmented generation or LLM agents is a strong plus

What we offer

• We foster a collaborative environment dedicated to ambitious, multidisciplinary projects that translate advanced research into impactful, real-world solutions, supported by 30+ years of experience in AI and related fields.
• Flexible work/life balance.

• We are an equal opportunity employer that hires based on skills, experience, and merit. We foster an inclusive and diverse workplace where all qualified candidates are considered fairly, regardless of background.

• We’re based in Meylan, close to Grenoble, a city that offers the perfect balance of urban life, cutting-edge research and technology, and spectacular mountain landscapes that provide countless opportunities to relax, recharge, and enjoy the outdoors.

All applications will be carefully considered, even if not all required skills are met. We value diverse backgrounds and the potential of each candidate, and we offer training to support the development of necessary skills.

NAVER LABS, co-located in Korea and France, is the organization dedicated to preparing NAVER’s future. Scientists at NAVER LABS Europe are empowered to pursue long-term research problems that, if successful, can have significant impact and transform NAVER. We take our ideas as far as research can to create the best technology of its kind. Active participation in the academic community and collaborations with world-class public research groups are, among others, important ways to achieve these goals. Teamwork, focus and persistence are important values for us.

 When applying for this position online, please don't forget to upload your CV and cover letter. Incomplete applications will not be considered.

NAVER LABS Europe is subject to French jurisdiction requiring organisations to stipulate that a job/internship is open to both women and men. None of our jobs/internships are gender specific.

References

1. A Survey of Self-Evolving Agents: On Path to Artificial Super Intelligence. Huan-ang Gao et al. 2025 (https://arxiv.org/abs/2507.21046)

2. ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory. Siru Ouyang et al. 2025 (https://arxiv.org/abs/2509.25140)

3. AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents. Yao Fu et al. NeurIPS 2024 (https://arxiv.org/abs/2403.08978)

4. Agent Workflow Memory. Zora Zhiruo Wang, Jiayuan Mao, Daniel Fried, Graham Neubig. ICML 2025 (https://arxiv.org/abs/2409.07429)

5. Provence: efficient and robust context pruning for retrieval-augmented generation. Nadezhda Chirkova, Thibault Formal, Vassilina Nikoulina, Stéphane Clinchant. ICLR 2025 (https://arxiv.org/abs/2501.16214)

6. BERGEN: A Benchmarking Library for Retrieval-Augmented Generation. David Rau, Hervé Déjean, Nadezhda Chirkova, Thibault Formal, Shuai Wang, Vassilina Nikoulina, Stéphane Clinchant. Findings of EMNLP 2024 (https://arxiv.org/abs/2407.01102)

7. PISCO: Pretty Simple Compression for Retrieval-Augmented Generation. Maxime Louis, Hervé Déjean, Stéphane Clinchant. Findings of ACL 2025 (https://arxiv.org/abs/2501.16075)

8. Key ingredients for effective zero-shot cross-lingual knowledge transfer in generative tasks. Nadezhda Chirkova and Vasilina Nikoulina, NAACL 2024 (https://arxiv.org/abs/2402.12279)

9. Memory-efficient NLLB-200: Language-specific Expert Pruning of a Massively Multilingual Machine Translation Model. Yeskendir Koishekenov, Alexandre Berard, Vassilina Nikoulina. ACL 2023 (https://arxiv.org/abs/2212.09811)

10. SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking. Thibault Formal, Benjamin Piwowarski, Stéphane Clinchant. SIGIR 2021 (https://arxiv.org/abs/2107.05720)

11. SPLATE: Sparse Late Interaction Retrieval. Thibault Formal, Stéphane Clinchant, Hervé Déjean, Carlos Lassance. SIGIR 2024 (https://arxiv.org/abs/2404.13950)

Réf: 0488901b-29e7-406f-8979-6ded151d1ba6