Emre Can Acikgoz

Emre Can Acikgoz

PhD Student · UIUC NLP

I am a second-year PhD student in Computer Science at UIUC, advised by Gokhan Tur and Dilek Hakkani-Tur. My research focuses on self-evolving LLM agents and agentic learning, with broader interests in reinforcement learning, self-play, and test-time training. I received an MSc in Computer Science from Koc University and a BSc in Electrical and Electronics Engineering (AI focus) from the same institution. My work has been published in top-tier venues including but not limited to NeurIPS, ICLR, ACL, and EMNLP - representative works include ToolRL, TT-SI, and Tool-R0. I am the co-founding organizer of The First Workshop on Lifelong Agents: Learning, Aligning, and Evolving at ICLR 2026, as part of Project Lifelong Agent.

Mission: Project Lifelong Agent

Ongoing Research Effort

My Motivation: agents that can continually learn, adapt, and generalize with minimal supervision; the dream of superintelligent systems that don't stop learning after deployment. This is the broader vision shaping my PhD.

The project is structured around three pillars. I focus primarily on the Evolving side: how agents can adapt themselves to any environment through experience, self-play, and test-time training.

Learning Aligning Evolving
Visit the project page

News

conferenceTwo papers accepted to ACL 2026: TT-SI: Self-Improving LLM Agents with Test-Time Training and Current Agents Fail to Leverage World Model as Tool for Foresight.
workshopOrganizedthe First Workshop on Lifelong Agents at ICLR 2026 — thanks to all attendees, speakers, and reviewers! The next edition is already in the works.
new paperWe released Tool-R0 as a strong contender for self-evolving LLM agents part of Project Lifelong Agent!

Publications

Tool-R0
Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data
Emre Can Acikgoz, Cheng Qian, Jonas Hübotter, Heng Ji, Dilek Hakkani-Tür, Gokhan Tur
Under Review
PDF arXiv Code Evolving
World Model
Current Agents Fail to Leverage World Model as Tool for Foresight
Cheng Qian, Emre Can Acikgoz, Bingxuan Li, Xiusi Chen, Yuji Zhang, Bingxiang He, Qinyu Luo, Dilek Hakkani-Tür, Gokhan Tur, Yunzhu Li, Heng Ji
ACL 2026 Main
PDF arXiv Aligning
TT-SI
TT-SI: Self-Improving LLM Agents with Test-Time Training
Emre Can Acikgoz, Cheng Qian, Heng Ji, Dilek Hakkani-Tür, Gokhan Tur
ACL 2026 Findings
PDF arXiv Evolving
Lifelong
Lifelong Agents: Learning, Aligning, Evolving
Cheng Qian, Emre Can Acikgoz, Zhenfei Yin, Manling Li, Yun-Nung Chen, Mengdi Wang, Caiming Xiong
ICLR 2026 Workshop · Accepted Proposal
Proposal Website Workshop
SpeakRL
SpeakRL: Learning to Speak Before You Act with LLM Agents
Emre Can Acikgoz, Jinoh Oh, Jie Hao, Joo Hyuk Jeon, Heng Ji, Dilek Hakkani-Tür, Gokhan Tur, Xiang Li, Chengyuan Ma, Xing Fan
IWSDS 2026
PDF Aligning
MAC
MAC: A Multi-Agent Framework for Interactive User Clarification in Multi-turn Conversations
Emre Can Acikgoz, Jinoh Oh, Joo Hyuk Jeon, Jie Hao, Heng Ji, Dilek Hakkani-Tür, Gokhan Tur, Xiang Li, Chengyuan Ma, Xing Fan
NeurIPS 2025 MTI-LLM Workshop · IWSDS 2026 (Oral)
PDF Aligning
ToolRL
ToolRL: Reward is All Tool Learning Needs
Cheng Qian*, Emre Can Acikgoz*, Qi He, Hongru Wang, Xiusi Chen, Dilek Hakkani-Tür, Gokhan Tur, Heng Ji
NeurIPS 2025
PDF arXiv Code Learning
SPM
Conversational Agents in the Era of Large Language Models
Emre Can Acikgoz*, Dilek Hakkani-Tür, Gokhan Tur
IEEE Signal Processing Magazine 2025
PDF Aligning
CoALM
Can a Single Model Master Both Multi-turn Conversations and Tool Use? CoALM: A Unified Conversational Agentic Language Model
Emre Can Acikgoz*, Jeremiah Greer, Akul Datta, Ze Yang, William Zeng, Oussama Elachqar, Emmanouil Koukoumidis, Dilek Hakkani-Tür, Gokhan Tur
ACL 2025 Main
PDF arXiv Code Learning
SMART
SMART: Self-Aware Agent for Tool Overuse Mitigation
Cheng Qian, Emre Can Acikgoz*, Hongru Wang, Xiusi Chen, Avirup Sil, Dilek Hakkani-Tür, Gokhan Tur, Heng Ji
ACL 2025 Findings
PDF arXiv Code Aligning
TD-EVAL
TD-EVAL: Revisiting Task-Oriented Dialogue Evaluation by Combining Turn-Level Precision with Dialogue-Level Comparisons
Emre Can Acikgoz*, Carl Guo*, Suvodip Dey*, Akul Datta, Takyoung Kim, Gokhan Tur, Dilek Hakkani-Tür
SIGDIAL 2025 (Oral)
PDF Aligning
Desid.
A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directions
Emre Can Acikgoz*, Cheng Qian*, Hongru Wang*, Vardhan Dongre, Xiusi Chen, Heng Ji, Dilek Hakkani-Tür, Gokhan Tur
arXiv 2025 · Under Review
arXiv Learning Aligning Evolving
PIPA
PIPA: A Unified Evaluation Protocol for Diagnosing Interactive Planning Agents
Takyoung Kim, Janvijay Singh, Shuhaib Mehri, Emre Can Acikgoz, Sagnik Mukherjee, Nimet Beyza Bozdag, Sumuk Shashidhar, Gokhan Tur, Dilek Hakkani-Tür
Under Review
PDF Aligning
ReSpAct
ReSpAct: Harmonizing Reasoning, Speaking, and Acting Towards Building LLM-Based Conversational AI Agents
Vardhan Dongre, Xiaocheng Yang, Emre Can Acikgoz, Suvodip Dey, Gokhan Tur, Dilek Hakkani-Tur
IWSDS 2025
PDF Aligning
Bosphorus
Bridging the Bosphorus: Advancing Turkish Large Language Models through Strategies for Low-Resource Language Adaptation and Benchmarking
Emre Can Acikgoz, Mete Erdoğan, Deniz Yuret
ACL MRL 2024
PDF First Open
Hippocrates
Hippocrates: An Open-Source Framework for Advancing Large Language Models in Healthcare
Emre Can Acikgoz, Osman İnce, Rayene Bech, Ilker Kesen, Aykut Erdem, Erkut Erdem
NeurIPS GenAI4Health 2024 (Oral)
PDF Code First fully open source Medical LLM family
ViLMA
ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models
Ilker Kesen, Andrea Pedrotti, Mustafa Dogan, Michele Cafagna, Emre Can Acikgoz, Letitia Parcalabescu, Iacer Calixto, Anette Frank, Albert Gatt, Aykut Erdem, Erkut Erdem
ICLR 2024
PDF arXiv Vision-Language
MRL
Transformers on Multilingual Clause-Level Morphology
Emre Can Acikgoz, Tilek Chubakov, Müge Kural, Gözde Gül Şahin, Deniz Yuret
EMNLP MRL Shared Task 2022 · Winner (all 3 subtasks)
PDF Shared Task Winner

Academic Service

Workshops Organized

Apr 2026

ICLR 2026 Workshop on Lifelong Agents: Learning, Aligning, Evolving

Co-organizer · Rio de Janeiro, Brazil

April 26, 2026 · lifelongagent.github.io

2026

Midwest Speech and Language Days (MSLD) 2026

Co-organizer · University of Illinois Urbana-Champaign

Reviewing

ML NeurIPS 2026, 2025, 2024 · ICLR 2026 · COLM 2026, 2025
NLP ACL 2026, 2025 · EMNLP 2025, 2022 · NAACL 2025 · EACL 2026 · AACL 2025
Others SIGDial 2026 · MTI-LLM Workshop @ NeurIPS 2025 · SIGTURK Workshop @ EACL 2026 · ACM CAIS 2026

Teaching

Spring 2024

Teaching Assistant

Fall 2023

Teaching Assistant

Comp 541: Deep Learning — Koc University
Spring 2023

Teaching Assistant

Comp 542: Natural Language Processing — Koc University
Fall 2022

Teaching Assistant

Comp 541: Deep Learning — Koc University
Spring 2022

Teaching Assistant

Two Truths and a Lie

Two truths and one fun fact about me — guess which is which:

  1. I won national math olympiads twice.
  2. I made my own custom Harley Davidson when I was 16.
  3. I used to play college football.