12 citations · 28 across the 19 of their papers we have counts for
23 papers
What Effort Level Should I Choose? On the Economics of Reasoning Effort in LLM Agents
Kaiser Sun, Yongchan Kwon, Zain Hasan +3
Generative models increasingly expose a reasoning effort setting that lets users scale inference-time compute, trading higher cost for potentially improved performance. Users must…
Hybrid Reasoning Agents
Jiaru Zou, Yunzhe Qi, Sirui Chen +5
How can we build an agent that thinks beyond human language, yet still acts through it in the external environment? Modern LLM agents still reason and interact through text, while…
Many Brains, One Geometry: A Shared Visual-Semantic Space for Cross-Dataset fMRI Decoding
Moein Khajehnejad, Michelangelo Tronti, Forough Habibollahi +3
Visual decoding from fMRI is typically siloed by participant and experiment, obscuring whether heterogeneous neural measurements can be organized within a common computational geom…
Self-Organizing Agent Teams Learn to Reason Together
Aneesh Pappu, Mirac Suzgun, Yongchan Kwon +5
Collective intelligence depends not only on what team members know, but also on how they organize their work. When the structure of a solution is unknown, useful roles and division…
Agentic AI-enabled discovery across large-scale sleep physiology
Rahul Thapa, Umaer Hanif, Robin Guillard +10
Sleep occupies roughly one-third of human life, yet many aspects of its physiology remain poorly understood. Large polysomnography (PSG) datasets offer new opportunities to study s…
Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoveries
Federico Bianchi, Yongchan Kwon, Aneesh Pappu +1
Scientific discovery is often a collective process: researchers share partial results, inspect failed attempts, and build on each other's ideas over long time horizons. Recent AI s…
Automated Benchmark Auditing for AI Agents and Large Language Models
Junlin Wang, Federico Bianchi, Shang Zhu +4
Modern AI benchmarks operate at a complexity that outpaces traditional verification methods. Tasks authored by domain experts often contain implicit assumptions, incomplete environ…
Voice "Cloning" is Style Transfer
Kaitlyn Zhou, Federico Bianchi, Martijn Bartelds +3
Artificially generated speech is increasingly embedded in everyday life. Voice cloning in particular enables applications where identity preservation is important, such as completi…
Evaluating Commercial AI Chatbots as News Intermediaries
Mirac Suzgun, Emily Shen, Federico Bianchi +5
AI chatbots are rapidly shaping how people encounter the news, yet no prior study has systematically measured how accurately these systems, with their proprietary search integratio…
"Sorry, I Didn't Catch That": How Speech Models Miss What Matters Most
Kaitlyn Zhou, Martijn Bartelds, Federico Bianchi +1
Despite speech recognition systems achieving low word error rates on standard benchmarks, they often fail on short, high-stakes utterances in real-world deployments. Here, we study…
Learning to Discover at Test Time
Mert Yuksekgonul, Daniel Koceja, Xinhao Li +8
How can we use AI to discover a new state of the art for a scientific problem? Prior work in test-time scaling, such as AlphaEvolve, performs search by prompting a frozen LLM. We p…
Test-Time Optimization of Physical Query Plans with LLMs
Mehmet Hamza Erol, Xiangpeng Hao, Federico Bianchi +3
Traditional query optimization relies on cost-based optimizers that estimate execution cost (e.g., runtime, memory, and I/O) using predefined heuristics and statistical models. Imp…
DSGym: A Holistic Framework for Evaluating and Training Data Science Agents
Fan Nie, Junlin Wang, Harper Hua +6
Data science agents promise to accelerate discovery and insight-generation by turning data into executable analyses and findings. Yet existing data science benchmarks fall short du…
To Err Is Human: Systematic Quantification of Errors in Published AI Papers via LLM Analysis
Federico Bianchi, Yongchan Kwon, Zachary Izzo +2
How many mistakes do published AI papers contain? Peer-reviewed publications form the foundation upon which new research and knowledge are built. Errors that persist in the literat…
Exploring the use of AI authors and reviewers at Agents4Science
Federico Bianchi, Owen Queen, Nitya Thakkar +2
There is growing interest in using AI agents for scientific research, yet fundamental questions remain about their capabilities as scientists and reviewers. To explore these questi…
ReasonIF: Large Reasoning Models Fail to Follow Instructions During Reasoning
Yongchan Kwon, Shang Zhu, Federico Bianchi +2
The ability of large language models (LLMs) to follow user instructions is central to their reliability, safety, and usefulness. While prior studies assess instruction adherence in…
Labeling Messages as AI-Generated Does Not Reduce Their Persuasive Effects
Isabel O. Gallegos, Chen Shani, Weiyan Shi +4
As generative artificial intelligence (AI) enables the creation and dissemination of information at massive scale and speed, it is increasingly important to understand how people p…
Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory
Mirac Suzgun, Mert Yuksekgonul, Federico Bianchi +2
Despite their impressive performance on complex tasks, current language models (LMs) typically operate in a vacuum: Each input query is processed separately, without retaining insi…
Belief in the Machine: Investigating Epistemological Blind Spots of Language Models
Mirac Suzgun, Tayfun Gur, Federico Bianchi +4
As language models (LMs) become integral to fields like healthcare, law, and journalism, their ability to differentiate between fact, belief, and knowledge is essential for reliabl…
h4rm3l: A language for Composable Jailbreak Attack Synthesis
Moussa Koulako Bala Doumbouya, Ananjan Nandi, Gabriel Poesia +5
Despite their demonstrated valuable capabilities, state-of-the-art (SOTA) widely deployed large language models (LLMs) still have the potential to cause harm to society due to the…
TextGrad: Automatic "Differentiation" via Text
Mert Yuksekgonul, Federico Bianchi, Joseph Boen +4
AI is undergoing a paradigm shift, with breakthroughs achieved by systems orchestrating multiple large language models (LLMs) and other complex components. As a result, developing…
Large Language Models are Vulnerable to Bait-and-Switch Attacks for Generating Harmful Content
Federico Bianchi, James Zou
The risks derived from large language models (LLMs) generating deceptive and damaging content have been the subject of considerable research, but even safe generations can lead to…
How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis
Federico Bianchi, Patrick John Chia, Mert Yuksekgonul +3
Negotiation is the basis of social interactions; humans negotiate everything from the price of cars to how to share common resources. With rapidly growing interest in using large l…