ACON: Optimizing Context Compression for Long-horizon LLM Agents
Minki Kang, Wei-Ning Chen, Dongge Han, Huseyin Inan, Lukas Wutschitz, Yanzhi Chen, Robert Sim, Saravan Rajmohan
ICML 2026 | June 2026
Dongge Han
Senior Researcher
论文与出版物
-
-
-
A Tale of Two Graphs: Separating Knowledge Exploration from Outline Structure for Open-Ended Deep Research
Zhuofan Shi, M. Ma, Zekun Yao, Fangkai Yang, Jue Zhang, Dongge Han, Victor Ruhle, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang
ICML 2026 | February 2026
-
LEGOMem: Modular Procedural Memory for Multi-agent LLM Systems for Workflow Automation
Dongge Han, Camille Couturier, Daniel Madrigal, Xuchao Zhang, Victor Ruehle, Saravan Rajmohan
AAMAS 2026 | January 2026
-
-
-
OdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application Workflows
Weixuan Wang, Dongge Han, Daniel Madrigal, Jin Xu, Victor Ruehle, Saravan Rajmohan
ArXiv | August 2025
-
Enhancing Reasoning Capabilities of Small Language Models with Blueprints and Prompt Template Search
Dongge Han, Menglin Xia, Daniel Madrigal, Samuel Kessler, Ankur Mallick, Xuchao Zhang, Mirian Hipolito Garcia, Jin Xu, Victor Ruehle, Saravan Rajmohan
ICML TTODLer-FM Workshop 2025 | June 2025
-
-
-
On Efficient Distillation from LLMs to SLMs
Metod Jazbec, Menglin Xia, Ankur Mallick, Daniel Madrigal, Dongge Han, Samuel Kessler, Victor Ruehle
NeurIPS FITML workshop 2024 | December 2024
-
-
-
ACON: Optimizing Context Compression for Long-horizon LLM Agents
Minki Kang, Wei-Ning Chen, Dongge Han, Huseyin Inan, Lukas Wutschitz, Yanzhi Chen, Robert Sim, Saravan Rajmohan
ICML 2026 | June 2026
-
A Tale of Two Graphs: Separating Knowledge Exploration from Outline Structure for Open-Ended Deep Research
Zhuofan Shi, M. Ma, Zekun Yao, Fangkai Yang, Jue Zhang, Dongge Han, Victor Ruhle, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang
ICML 2026 | February 2026
-
LEGOMem: Modular Procedural Memory for Multi-agent LLM Systems for Workflow Automation
Dongge Han, Camille Couturier, Daniel Madrigal, Xuchao Zhang, Victor Ruehle, Saravan Rajmohan
AAMAS 2026 | January 2026
-
OdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application Workflows
Weixuan Wang, Dongge Han, Daniel Madrigal, Jin Xu, Victor Ruehle, Saravan Rajmohan
ArXiv | August 2025
-
Enhancing Reasoning Capabilities of Small Language Models with Blueprints and Prompt Template Search
Dongge Han, Menglin Xia, Daniel Madrigal, Samuel Kessler, Ankur Mallick, Xuchao Zhang, Mirian Hipolito Garcia, Jin Xu, Victor Ruehle, Saravan Rajmohan
ICML TTODLer-FM Workshop 2025 | June 2025
-
On Efficient Distillation from LLMs to SLMs
Metod Jazbec, Menglin Xia, Ankur Mallick, Daniel Madrigal, Dongge Han, Samuel Kessler, Victor Ruehle
NeurIPS FITML workshop 2024 | December 2024
-
-
-
A Tale of Two Graphs: Separating Knowledge Exploration from Outline Structure for Open-Ended Deep Research
Zhuofan Shi, M. Ma, Zekun Yao, Fangkai Yang, Jue Zhang, Dongge Han, Victor Ruhle, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang
ICML 2026 | February 2026
-
-
-
ACON: Optimizing Context Compression for Long-horizon LLM Agents
Minki Kang, Wei-Ning Chen, Dongge Han, Huseyin Inan, Lukas Wutschitz, Yanzhi Chen, Robert Sim, Saravan Rajmohan
ICML 2026 | June 2026
-
A Tale of Two Graphs: Separating Knowledge Exploration from Outline Structure for Open-Ended Deep Research
Zhuofan Shi, M. Ma, Zekun Yao, Fangkai Yang, Jue Zhang, Dongge Han, Victor Ruhle, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang
ICML 2026 | February 2026
-
LEGOMem: Modular Procedural Memory for Multi-agent LLM Systems for Workflow Automation
Dongge Han, Camille Couturier, Daniel Madrigal, Xuchao Zhang, Victor Ruehle, Saravan Rajmohan
AAMAS 2026 | January 2026
-
Enhancing Reasoning Capabilities of Small Language Models with Blueprints and Prompt Template Search
Dongge Han, Menglin Xia, Daniel Madrigal, Samuel Kessler, Ankur Mallick, Xuchao Zhang, Mirian Hipolito Garcia, Jin Xu, Victor Ruehle, Saravan Rajmohan
ICML TTODLer-FM Workshop 2025 | June 2025
-
On Efficient Distillation from LLMs to SLMs
Metod Jazbec, Menglin Xia, Ankur Mallick, Daniel Madrigal, Dongge Han, Samuel Kessler, Victor Ruehle
NeurIPS FITML workshop 2024 | December 2024
-
-
-
OdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application Workflows
Weixuan Wang, Dongge Han, Daniel Madrigal, Jin Xu, Victor Ruehle, Saravan Rajmohan
ArXiv | August 2025
-