7 citations · 12 across the 12 of their papers we have counts for
13 papers
Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries
Anikait Singh, Teresa Zhang, Yoonho Lee +3
Reasoning over long document contexts remains a challenge for large language models (LLMs). Standard retrieval methods are inherently reactive, bottlenecking agents with complex, c…
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses
Peng Xia, Rujun Han, Zifeng Wang +11
An LLM agent's capability is largely magnified by its harness, namely the prompts, control flow, tooling, memory, and context management surrounding the frozen backbone model. Rece…
WHALE: A Simple Recipe for Joint Harness-Weight Optimization
Haechan Kim, Yoonho Lee, Gisang Lee +2
Agent performance depends jointly on the model parameters and the executable harness code that manages context and control flow. Optimizing either component in isolation can leave…
SPIRAL: Learning to Search and Aggregate
Jubayer Ibn Hamid, Ifdita Hasan Orney, Michael Y. Li +5
Language model reasoning can be substantially improved at test time via scaffolds that scale inference compute across different primitives -- sequential reasoning within a trace, i…
Meta-Harness: End-to-End Optimization of Model Harnesses
Yoonho Lee, Roshen Nair, Qizheng Zhang +3
The performance of large language model (LLM) systems depends not only on model weights, but also on their harness: the code that determines what information to store, retrieve, an…
Feedback Descent: Open-Ended Text Optimization via Pairwise Comparison
Yoonho Lee, Joseph Boen, Chelsea Finn
We introduce \textit{Feedback Descent}, a framework that optimizes text artifacts -- prompts, code, and molecules -- through structured textual feedback, rather than relying solely…
RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems
Yuxiao Qu, Anikait Singh, Yoonho Lee +4
Reasoning requires going beyond pattern matching or memorization of solutions to identify and implement "algorithmic procedures" that can be used to deduce answers to hard problems…
Test-Time Alignment via Hypothesis Reweighting
Yoonho Lee, Jonathan Williams, Henrik Marklund +4
Reward models trained on aggregate preferences often fail to capture individual users' values, but existing adaptation methods such as fine-tuning or long-context conditioning are…
Calibrating Language Models with Adaptive Temperature Scaling
Johnathan Xie, Annie S. Chen, Yoonho Lee +2
The effectiveness of large language models (LLMs) is not only measured by their ability to generate accurate outputs but also by their calibration-how well their confidence scores…
Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling
Yuejiang Liu, Jubayer Ibn Hamid, Annie Xie +3
Predicting and executing a sequence of actions without intermediate replanning, known as action chunking, is increasingly used in robot learning from human demonstrations. Yet, its…
Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning
Johnathan Xie, Yoonho Lee, Annie S. Chen +1
Self-supervised learning excels in learning representations from large amounts of unlabeled data, demonstrating success across multiple data modalities. Yet, extending self-supervi…
Clarify: Improving Model Robustness With Natural Language Corrections
Yoonho Lee, Michelle S. Lam, Helena Vasconcelos +2
The standard way to teach models is by feeding them lots of data. However, this approach often teaches models incorrect ideas because they pick up on misleading signals in the data…
AutoFT: Learning an Objective for Robust Fine-Tuning
Caroline Choi, Yoonho Lee, Annie Chen +3
Foundation models encode rich representations that can be adapted to downstream tasks by fine-tuning. However, fine-tuning a model on one data distribution often degrades performan…