6 papers
Agents' Last Exam
Yiyou Sun, Xinyang Han, Weichen Zhang +306
Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional d…
FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale
Runyuan He, Qiuyang Mang, Shang Zhou +14
Many real-world coding challenges are open-ended and admit no known optimal solution. Yet, recent progress in LLM coding has focused on well-defined tasks such as feature implement…
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
Weian Mao, Xi Lin, Wei Huang +5
Extended reasoning in large language models (LLMs) creates severe KV cache memory bottlenecks. Leading KV cache compression methods estimate KV importance using attention scores fr…
Agent Banana: High-Fidelity Image Editing with Agentic Thinking and Tooling
Ruijie Ye, Jiayi Zhang, Zhuoxin Liu +10
We study instruction-based image editing under professional workflows and identify three persistent challenges: (i) editors often over-edit, modifying content beyond the user's int…
Traversal-as-Policy: Log-Distilled Gated Behavior Trees as Externalized, Verifiable Policies for Safe, Robust, and Efficient Agents
Peiran Li, Jiashuo Sun, Fangzhou Lin +5
Autonomous LLM agents fail because long-horizon policy remains implicit in model weights and transcripts, while safety is retrofitted post hoc. We propose Traversal-as-Policy: dist…
AutoCode: LLMs as Problem Setters for Competitive Programming
Shang Zhou, Zihan Zheng, Kaiyuan Liu +18
Writing competitive programming problems is exacting. Authors must: set constraints, input distributions, and edge cases that rule out shortcuts; target specific algorithms (e.g.,…