Agentic Systems Lab | ETH Zurich

We design, develop, and evaluate AI systems that run the real world, and shape the researchers and founders who will define its future. Based at ETH Zurich.

[Agentic Systems Lab | ETH Zurich @ETH_agent_lab]

Earlier this year, we launched the first student batch of the 𝗘𝗧𝗛 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗦𝘆𝘀𝘁𝗲𝗺𝘀 𝗟𝗮𝗯. Today, applications for Batch 2 are officially open! 🚀

𝗦𝘁𝘂𝗱𝗲𝗻𝘁𝘀 𝗶𝗻 𝗼𝘂𝗿 𝗳𝗶𝗿𝘀𝘁 𝗕𝗮𝘁𝗰𝗵 𝗵𝗮𝘃𝗲 𝗮𝗹𝗿𝗲𝗮𝗱𝘆:

→ Published papers at ICLR and ICML
→ Advised executives at SMI-listed companies
→ Raised seven-figure funding for their startups
→ Secured full-time offers from frontier AI labs

Today, our work spans the cutting edge of AI, from Agentic Systems and Multimodal AI to TSLMs and RLMs — applied across sectors like healthcare, energy, financial services, manufacturing, and robotics.

𝗡𝗼𝘄, 𝗶𝘁’𝘀 𝘁𝗶𝗺𝗲 𝗳𝗼𝗿 𝘁𝗵𝗲 𝘀𝗲𝗰𝗼𝗻𝗱 𝗕𝗮𝘁𝗰𝗵.

The goal? Help you turn your semester project, bachelor’s thesis, or master’s thesis into frontier AI research, an AI startup, or a transformative industry collaboration. With you in the driver's seat.

𝗔𝗽𝗽𝗹𝗶𝗰𝗮𝘁𝗶𝗼𝗻𝘀 𝗮𝗿𝗲 𝗼𝗽𝗲𝗻 𝘁𝗼 𝗘𝗧𝗛 𝘀𝘁𝘂𝗱𝗲𝗻𝘁𝘀 𝗮𝗻𝗱 𝗴𝘂𝗲𝘀𝘁 𝘀𝘁𝘂𝗱𝗲𝗻𝘁𝘀 𝗳𝗿𝗼𝗺 𝗼𝘁𝗵𝗲𝗿 𝘂𝗻𝗶𝘃𝗲𝗿𝘀𝗶𝘁𝗶𝗲𝘀.

Who's next? 👀

👇 Link to apply in the comments.

[Agentic Systems Lab | ETH Zurich @ETH_agent_lab]

You can find more information about the lab, available student tracks, and the application process here:
🌐 Lab Website: https://t.co/S2grmYTMT4
🎓 Student Tracks: https://t.co/YheWnd6ECa
📝 Application Form: https://t.co/sYdVheDI3i

[Agentic Systems Lab | ETH Zurich @ETH_agent_lab]

Earlier this year, we launched the first student batch of the 𝗘𝗧𝗛 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗦𝘆𝘀𝘁𝗲𝗺𝘀 𝗟𝗮𝗯. Today, applications for Batch 2 are officially open! 🚀

𝗦𝘁𝘂𝗱𝗲𝗻𝘁𝘀 𝗶𝗻 𝗼𝘂𝗿 𝗳𝗶𝗿𝘀𝘁 𝗕𝗮𝘁𝗰𝗵 𝗵𝗮𝘃𝗲 𝗮𝗹𝗿𝗲𝗮𝗱𝘆:

→ Published papers at ICLR and ICML
→ Advised executives at SMI-listed companies
→ Raised seven-figure funding for their startups
→ Secured full-time offers from frontier AI labs

Today, our work spans the cutting edge of AI, from Agentic Systems and Multimodal AI to TSLMs and RLMs — applied across sectors like healthcare, energy, financial services, manufacturing, and robotics.

𝗡𝗼𝘄, 𝗶𝘁’𝘀 𝘁𝗶𝗺𝗲 𝗳𝗼𝗿 𝘁𝗵𝗲 𝘀𝗲𝗰𝗼𝗻𝗱 𝗕𝗮𝘁𝗰𝗵.

The goal? Help you turn your semester project, bachelor’s thesis, or master’s thesis into frontier AI research, an AI startup, or a transformative industry collaboration. With you in the driver's seat.

𝗔𝗽𝗽𝗹𝗶𝗰𝗮𝘁𝗶𝗼𝗻𝘀 𝗮𝗿𝗲 𝗼𝗽𝗲𝗻 𝘁𝗼 𝗘𝗧𝗛 𝘀𝘁𝘂𝗱𝗲𝗻𝘁𝘀 𝗮𝗻𝗱 𝗴𝘂𝗲𝘀𝘁 𝘀𝘁𝘂𝗱𝗲𝗻𝘁𝘀 𝗳𝗿𝗼𝗺 𝗼𝘁𝗵𝗲𝗿 𝘂𝗻𝗶𝘃𝗲𝗿𝘀𝗶𝘁𝗶𝗲𝘀.

Who's next? 👀

👇 Link to apply in the comments.

[Agentic Systems Lab | ETH Zurich @ETH_agent_lab]

📄 Paper 6/6

Preserving Plasticity in Continual Learning via Dynamical Isometry

Rosseau A, Müller R, Nowe A.

Accepted at ICML 2026 Main Track

ICML: https://t.co/7g9RKRDeZ5

@deepqlearning

[Agentic Systems Lab | ETH Zurich @ETH_agent_lab]

Excited to share that members of our lab co-authored 6 papers accepted at #ICML2026, including three Main Track and three Workshop papers 🔥🚀

📄 Accepted papers:

▪️ OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data [Main Track]

▪️ Auditing Emotion-Vector-Steered Political Bias in Open-Weight LLMs [AI4GOOD Workshop]

▪️ Reinforcement Learning of Karma Bidding Strategies [NExT-Game Workshop]

▪️ Cinematic Source Separation with Dialogue-Driven Sidechain Ducking [Workshop on Machine Learning for Audio]

▪️ Reinforcement Learning for Tool-Calling Agents in Fast Healthcare Interoperability Resources (FHIR) [Main Track]

▪️ Preserving Plasticity in Continual Learning via Dynamical Isometry [Main Track]

@robertjakob @PatrickLanger20 @gaborhollbeck @f14wn @DerRiehl @atoof_sh @deepqlearning @kev_osull @cs06thegreat @nzuma0 @maxrosenblattl

Huge congratulations to everyone involved. We are looking forward to presenting these works, reconnecting with colleagues, and meeting new friends in Seoul 🇰🇷

🔗 Full links in the comments.

[Agentic Systems Lab | ETH Zurich @ETH_agent_lab]

#ICML2026 Accepted Papers and Authors 👇📄

[Agentic Systems Lab | ETH Zurich @ETH_agent_lab]

📄 Paper 5/6⁠

Reinforcement Learning for Tool-Calling Agents in Fast Healthcare Interoperability Resources (FHIR)

Knorr M*, Müller R*, Bremer JP, Schweingruber N.

Accepted at ICML 2026 Main Track

arXiv: https://t.co/Oa4t6oqHtL
ICML: https://t.co/e3IY8pA3UT

@deepqlearning

[Agentic Systems Lab | ETH Zurich @ETH_agent_lab]

📄 Paper 4/6

Cinematic Source Separation with Dialogue-Driven Sidechain Ducking

Shakir A, Groetschla F, Lanzendoerfer L, Wattenhofer R.

Accepted at ICML 2026 Workshop on Machine Learning for Audio

Workshop: https://t.co/xiVVEH6d7D

@atoof_sh

[Agentic Systems Lab | ETH Zurich @ETH_agent_lab]

📄 Paper 3/6

Multi-Agent Reinforcement Learning of Karma Bidding Strategies

Riehl K, Psarou A, Müller R, Wu F, Langer P, Jakob R, Hollbeck G, Kouvelas A, Kucharski R, Makridis MA.

Accepted at ICML 2026 NExT-Game Workshop

OpenReview: https://t.co/Xjk4KQcXnH

@DerRiehl @deepqlearning @PatrickLanger20 @robertjakob @gaborhollbeck

[Agentic Systems Lab | ETH Zurich @ETH_agent_lab]

📄 Paper 2/6

Auditing Emotion-Vector-Steered Political Bias in Open-Weight LLMs

Hollbeck G, Peters B, von Recum A, Riehl K, McGail A, Windeck J, O’Sullivan K, Jakob R.

Accepted at ICML 2026 Workshop: AI4GOOD

OpenReview: https://t.co/iIfuVswGEJ

@gaborhollbeck @f14wn @DerRiehl @kev_osull @robertjakob

[Agentic Systems Lab | ETH Zurich @ETH_agent_lab]

📄 Paper 1/6

OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data

Langer P, Kaar T, Rosenblattl M, Xu MA, Chow W, Maritsch M, Jakob R, Wang N, Liu J, Verma A, Han B, Kim DS, Chubb H, Ceresnak S, Zahedivash A, Sandhu ATS, Rodriguez F, McDuff D, Fleisch E, Aalami O, Barata F, Schmiedmayer P.

Accepted at ICML 2026 Main Track

arXiv: https://t.co/BPr5T3NcUL
Github: https://t.co/sw81tmyFcD (+1200 ⭐️)
ICML: https://t.co/xFjz6xMie4
Website: https://t.co/kt881bDtlT
X: @OpenTSLM

@PatrickLanger20 @robertjakob @cs06thegreat @nzuma0 @maxrosenblattl @maxxu05 @PSchmiedmayer

[Robert Müller @deepqlearning]

Why do models that score well on standard benchmarks still make bad strategic decisions?

In Cattle Trade, accepted at @MALGAI_ICLR2026 , LLMs play a 4-player 50+ turn game of auctions, hidden offers, bluffing, and limited cash.

Some LLMs lose to simple Python agents.
🧵

[Agentic Systems Lab | ETH Zurich @ETH_agent_lab]

Our members Nicolas Zumarraga & Robert Jakob are in Brazil 🇧🇷 for ICLR 2026 presenting our poster on TS-Haystack: A Multi-Scale Retrieval Benchmark for Time Series Language Models

Come by the poster session today and say hi!

Paper: https://t.co/RIUHpATAFx

@iclr_conf @nzuma0 @robertjakob

[Agentic Systems Lab | ETH Zurich @ETH_agent_lab]

Robotics & intelligent systems in the Greater Zurich Area.

by GREATER ZURICH AREA
https://t.co/JwYBsWGcg8

[Roland Graser @roland_graser]

recap of our zurich visit with @theresidency:

> spent 3 days in zurich, it feels like the place to be in europe
> technical talent, high substance, no noise
> 3 places you must visit:

1. @ethroboticsclub - ETH robotics club. a hangar with 50 students on a saturday, working on robotics & physical ML projects

2. @ETH_agent_lab - an ETH chair that let's european students work on their projects, while giving them their master's thesis + credits -> perfect for students who want to build but NOT drop out

3. @thejfloor - the community that formed at the ETH's student project house, now a coworking space for startups in zurich

funniest roadtrip I could have imagined with @ArvindAGI22 , @_sethmorton and @chrisbrolin123

the conversations we've been having can be boiled down to one question:

will transformers get to AGI faster than other, more exotic models that run on new alternative hardware (e.g. neuromorphic or thermo compute).

until next time!

[Lukas Ziegler @lukas_m_ziegler]

there's another reason to study the ETH and EPFL models closely 🇨🇭

both universities are also European leaders in spawning startups

[Agentic Systems Lab | ETH Zurich @ETH_agent_lab]

Drop the “Agentic Systems”. Just “The Lab”. It’s cleaner.

[Roland Graser @roland_graser]

update:
> went to zurich
> crashed into @thejfloor
> went to eth student bar
> asked random ppl if they know tbpn
> 5th group we asked said yes
> turns out they’re all building at ‘the lab’ in zurich
> 10/10 culture fit with the residency
> 10/10 serendipity
> immediately decided to stay longer in zurich

[Agentic Systems Lab | ETH Zurich @ETH_agent_lab]

Rajiv is now building Studyflash ⚡📝

They’re building a “Cursor for Learning” that helps students turn notes, slides, and docs into effective study resources.

Bootstrapped, ~10 full-time builders, and already at multi-million $ ARR.

Check them out: https://t.co/rE6rRjMTBq

[Agentic Systems Lab | ETH Zurich @ETH_agent_lab]

Congrats to our lab member Rajiv Manichand (@frederik_rajiv) on his AAAI 2026 paper, “Digital Scale: Open-Source On-Device BMI Estimation from Smartphone Camera Images Trained on a Large-Scale Real-World Dataset” 🎉

The paper presents a privacy-preserving way to estimate BMI from smartphone camera images, with the full pipeline running entirely on-device.

Thread below 🧵
#AAAI2026 #DigitalHealth #MachineLearning

[Agentic Systems Lab | ETH Zurich @ETH_agent_lab]

@frederik_rajiv Digital Scale shows that BMI estimation can be made more private, portable, and usable in real-world settings.

📃 Full paper: https://t.co/oPPZloWTM1
💻 Code: https://t.co/oPPZloWTM1

[Agentic Systems Lab | ETH Zurich @ETH_agent_lab]

Congrats to our lab member Rajiv Manichand (@frederik_rajiv) on his AAAI 2026 paper, “Digital Scale: Open-Source On-Device BMI Estimation from Smartphone Camera Images Trained on a Large-Scale Real-World Dataset” 🎉

The paper presents a privacy-preserving way to estimate BMI from smartphone camera images, with the full pipeline running entirely on-device.

Thread below 🧵
#AAAI2026 #DigitalHealth #MachineLearning

[Agentic Systems Lab | ETH Zurich @ETH_agent_lab]

@frederik_rajiv A key contribution is deployment: the full pipeline runs on Android using CLAID, including image filtering and local BMI inference.

The code is released open-source, making the system easier to reproduce and extend.