9 papers
AI Research Preference Models
Thomas Simon Foster, Bassel Al Omari, Tingchen Fu +30
AI research agents (AIRA) can now carry machine learning experiments from proposal through implementation and evaluation. Yet progress on frontier tasks is throttled by the cost of…
AIRA_2: Overcoming Bottlenecks in AI Research Agents
Karen Hambardzumyan, Nicolas Baldwin, Edan Toledo +22
Existing research has identified three structural performance bottlenecks in AI research agents: (1) synchronous single-GPU execution constrains sample throughput, limiting the ben…
Cmprsr: Abstractive Token-Level Question-Agnostic Prompt Compressor
Ivan Zakazov, Berke Argin, Oussama Gabouj +6
Motivated by the high costs of using black-box Large Language Models (LLMs), we introduce a novel prompt compression paradigm, under which we use smaller LLMs to compress inputs fo…
GRAD: Generative Retrieval-Aligned Demonstration Sampler for Efficient Few-Shot Reasoning
Oussama Gabouj, Kamel Charaf, Ivan Zakazov +2
Large Language Models (LLMs) achieve strong performance across diverse tasks, but their effectiveness often depends on the quality of the provided context. Retrieval-Augmented Gene…
Interactive Evaluation of Large Language Models for Multi-Requirement Software Engineering Tasks
Dimitrios Rontogiannis, Maxime Peyrard, Nicolas Baldwin +3
Standard single-turn, static benchmarks fall short in evaluating the nuanced capabilities of Large Language Models (LLMs) on complex tasks such as software engineering. In this wor…
TRPrompt: Bootstrapping Query-Aware Prompt Optimization from Textual Rewards
Andreea Nica, Ivan Zakazov, Nicolas Mario Baldwin +2
Prompt optimization improves the reasoning abilities of large language models (LLMs) without requiring parameter updates to the target model. Following heuristic-based "Think step…
AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench
Edan Toledo, Karen Hambardzumyan, Martin Josifoski +22
AI research agents are demonstrating great potential to accelerate scientific progress by automating the design, implementation, and training of machine learning models. We focus o…
RL for Reasoning by Adaptively Revealing Rationales
Mohammad Hossein Amani, Aryo Lotfi, Nicolas Mario Baldwin +4
Learning in the combinatorially large output space of sequence generation problems is challenging as providing expert demonstrations scales poorly with sequence length, and RL stru…
Symbolic Autoencoding for Self-Supervised Sequence Learning
Mohammad Hossein Amani, Nicolas Mario Baldwin, Amin Mansouri +3
Traditional language models, adept at next-token prediction in text sequences, often struggle with transduction tasks between distinct symbolic systems, particularly when parallel…