18 papers
Recursive Harness Self-Improvement
Hyunin Lee, Jinglue Xu, Jeffrey Seely +3
Under model--harness co-evolution, harnesses are not merely inference-time scaffolds but data-generating components whose execution traces can shape future foundation models. This…
RHO: Your Coding Agent is Secretly a Roboticist
Karim Elmaaroufi, Justin Svegliato, Sarunas Kalade +3
Code-as-Policies (CaP) has shown that large language models (LLMs) can write code to solve robotics tasks by composing perception, planning, and control primitives. Recent CaP syst…
RAG over Thinking Traces Can Improve Reasoning Tasks
Negar Arabzadeh, Wenjie Ma, Sewon Min +1
Retrieval-augmented generation (RAG) has proven effective for knowledge-intensive tasks, but is widely believed to offer limited benefit for reasoning-intensive problems such as ma…
Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments
Parth Asawa, Christopher M. Glaze, Gabriel Orlanski +7
Continual learning, the ability of AI systems to improve through sequential experience, has attracted substantial interest, but no high-quality benchmark exists to evaluate it. We…
PIXELRAG: Web Screenshots Beat Text for Retrieval-Augmented Generation
Yichuan Wang, Zhifei Li, Zirui Wang +5
Augmenting large language models (LLMs) with retrieved web text has become a dominant paradigm, yet the web is not natively textual: existing systems depend on complex parsing pipe…
The Price Reversal Phenomenon: When Cheaper Reasoning Models Cost More
Lingjiao Chen, Chi Zhang, Yeye He +3
Developers and consumers increasingly choose reasoning models (RMs) based on their listed API prices. However, how accurately do these prices reflect actual inference costs? We con…