Papers
Deep, long-form breakdowns of recent research in AI, machine learning, security & programming languages.
CliffCompaction: Cost-Efficient Compaction for Long-Horizon Coding Agents
by Trang Nguyen, Eulrang Cho, Bingqing Chen, Tim Dettmers
SWE-Serve: Benchmarking Agentic Engineering For Production Inference Serving
by Jennifer Williams, Dave Farris, Jeff Farris, Jiantao Jiao
SARA: SLO-Aware Resource Allocation for Disaggregated Agentic LLM Services
by Shicong Liu, Xianghao Yu, Zhen Gao, Jun Zhang
A2M: Trace-Optimized Agent Hijacking in the MCP Ecosystem
by Laizhen Li, Xuan Wang, Peicheng Zhao, Juanjuan Zhao, Kejiang Ye, Cheng-zhong Xu, Xitong Gao
Grow the Harness, Not the Context: From Strategy-Free Scaffolds to Reusable Specialist Agents
by Laizhen Li, Jiarui Li, Juanjuan Zhao, Kejiang Ye, Ye Li, Cheng-zhong Xu, Xitong Gao
Type-Safe Is Not Error-Free: A Constrained Decision Head Follows the Option Name, Not the Rubric Bound to It
by Yu Sun, Junhao Xu
EquivSVA: A Formally Verified Dataset of Behavioral Assertions Across Equivalent RTL Implementations
by FNU Aditi
Metrics Failure in LLM-Based Code Vulnerability Repair: An Empirical Study and a Change-Aware Screen
by Om Nepal, Sushant Aryal, Oluseyi Olukola, Nick Rahimi
4-Block Integer Programming is in FPT
by Martin Koutecký, Alexandra Lassota, Koen Ligthart
Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs
by Quan Nguyen-Tri, Mukul Ranjan, Zhiqiang Shen