5 papers
Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
Mike A. Merrill, Alexander G. Shaw, Nicholas Carlini +82
AI agents may soon become capable of autonomously completing valuable, long-horizon tasks in diverse domains. Current benchmarks either do not measure real-world tasks, or are not…
RECODE: Reasoning Through Code Generation for Visual Question Answering
Junhong Shen, Mu Cai, Bo Hu +4
Multimodal Large Language Models (MLLMs) struggle with precise reasoning for structured visuals like charts and diagrams, as pixel-based perception lacks a mechanism for verificati…
Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction
Junhong Shen, Hao Bai, Lunjun Zhang +8
The current paradigm of test-time scaling relies on generating long reasoning traces ("thinking" more) before producing a response. In agent problems that require interaction, this…
CodePDE: An Inference Framework for LLM-driven PDE Solver Generation
Shanda Li, Tanya Marwah, Junhong Shen +4
Partial differential equations (PDEs) are fundamental to modeling physical systems, yet solving them remains a complex challenge. Traditional numerical solvers rely on expert knowl…
Specialized Foundation Models Struggle to Beat Supervised Baselines
Zongzhe Xu, Ritvik Gupta, Wenduo Cheng +4
Following its success for vision and text, the "foundation model" (FM) paradigm -- pretraining large models on massive data, then fine-tuning on target tasks -- has rapidly expande…