Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 17 additions & 0 deletions source/_data/SymbioticLab.bib
Original file line number Diff line number Diff line change
Expand Up @@ -2387,3 +2387,20 @@ @Article{kairos:arxiv26
We present KAIROS, a context-aware power optimization system for agentic AI serving. KAIROS uses agent context as a first-class control signal to jointly manage GPU frequency, per-instance concurrency, and multi-instance request placement. This enables KAIROS to save power when memory headroom exists while avoiding thrashing and preserving performance targets. At a high level, KAIROS tracks requests at agent granularity, adapts local control to context growth and agent progress, and routes agents across instances to jointly improve power efficiency and memory stability. Evaluated across diverse software and data engineering agentic tasks, KAIROS achieves an average of 27% (up to 39.8%) power reduction while meeting the performance targets.
}
}

@Article{ara:arxiv26,
author = {Jiachen Liu and Jiaxin Pei and Jintao Huang and Chenglei Si and Ao Qu and Xiangru Tang and Runyu Lu and Lichang Chen and Xiaoyan Bai and Haizhong Zheng and Carl Chen and Zhiyang Chen and Haojie Ye and Yujuan Fu and Zexue He and Zijian Jin and Zhenyu Zhang and Shangquan Sun and Maestro Harmon and John Dianzhuo Wang and Jianqiao Zeng and Jiachen Sun and Mingyuan Wu and Baoyu Zhou and Yuchen You and Shijian Lu and Yiming Qiu and Fan Lai and Yuan Yuan and Yao Li and Junyuan Hong and Ruihao Zhu and Beidi Chen and Alex Pentland and Ang Chen and Mosharaf Chowdhury and Zechen Zhang},
title = {The Last Human-Written Paper: Agent-Native Research Artifacts},
year = {2026},
month = {Apr},
volume = {abs/2604.24658},
archivePrefix = {arXiv},
eprint = {2604.24658},
url = {https://arxiv.org/abs/2604.24658},
publist_confkey = {arXiv:2604.24658},
publist_link = {paper || https://arxiv.org/abs/2604.24658},
publist_topic = {Systems + AI},
publist_abstract = {
Scientific publication compresses a branching, iterative research process into a linear narrative, discarding the majority of what was discovered along the way. This compilation imposes two structural costs: a Storytelling Tax, where failed experiments, rejected hypotheses, and the branching exploration process are discarded to fit a linear narrative; and an Engineering Tax, where the gap between reviewer-sufficient prose and agent-sufficient specification leaves critical implementation details unwritten. Tolerable for human readers, these costs become critical when AI agents must understand, reproduce, and extend published work. We introduce the Agent-Native Research Artifact (ARA), a protocol that replaces the narrative paper with a machine-executable research package structured around four layers: scientific logic, executable code with full specifications, an exploration graph that preserves the failures compilation discards, and evidence grounding every claim in raw outputs. Three mechanisms support the ecosystem: a Live Research Manager that captures decisions and dead ends during ordinary development; an ARA Compiler that translates legacy PDFs and repos into ARAs; and an ARA-native review system that automates objective checks so human reviewers can focus on significance, novelty, and taste. On PaperBench and RE-Bench, ARA raises question-answering accuracy from 72.4% to 93.7% and reproduction success from 57.4% to 64.4%. On RE-Bench's five open-ended extension tasks, preserved failure traces in ARA accelerate progress, but can also constrain a capable agent from stepping outside the prior-run box depending on the agent's capabilities.
}
}
6 changes: 3 additions & 3 deletions source/people/index.md
Original file line number Diff line number Diff line change
Expand Up @@ -25,13 +25,12 @@ excerpt: "SymbioticLab current & past members"
1. [Dr. Hasan Al Maruf](https://www.linkedin.com/in/hasanalmaruf/) (2023) → AMD ➠ Meta
1. [Prof. Fan Lai](https://www.linkedin.com/in/fan-lai-a27764147/) (2023) → Assistant Professor @UIUC
1. [Dr. Yiwen Zhang](https://www.linkedin.com/in/yiwen-zhang-a75719112/) (2024) → Google
1. [Dr. Jiachen Liu](https://www.linkedin.com/in/jiachen-amber-liu-872506169/) (2025) → Meta
1. [Dr. Jiachen Liu](https://www.linkedin.com/in/jiachen-amber-liu-872506169/) (2025) → Meta ➠ Co-Founder @Orchestra Research


## Current Non-Ph.D. Students
1. Aakash Puntambekar (CSE MSE)
1. Wonbin Jin (CSE MSE)
1. Jisang Ahn (CS-LSA BS)
1. Letian Ruan (CSE BSE)
1. David McDermott (CS-LSA & Interdisciplinary Physics BS)

Expand Down Expand Up @@ -98,5 +97,6 @@ excerpt: "SymbioticLab current & past members"
1. Jenny Xun (CE BSE)
1. Vishwa Ramanakumar (CSE MSE)
1. Vatsal Joshi (CSE MSE) → Meta
1. Wenxuan Tan (CS & Math BS@UW-Madison)
1. Wenxuan Tan (CS & Math BS@UW-Madison) → ByteDance
1. Rishika Kalidindi (CSE MSE) → Ph.D. @UT Austin
1. Jisang Ahn (CS-LSA BS) → Google
Loading