AI Coding2026
Acts as a proxy that incrementally compresses LLM conversation history for coding agents so a single session can run for months while using far fewer tokens. Compression is model-driven, reversible, and designed to preserve a stable KV-cache prefix so attention and billing remain efficient.
Tao Feng, Fangxu Yu +10University of Illinois Urbana-Champaign, University of Maryland, College Park +3
Frames LLM routing as a sequential decision process and introduces LLMRouter plus the xRouteBench benchmark to develop, evaluate, and deploy learned routing policies across heterogeneous LLMs, optimizing response quality versus inference cost.
Enables interactive serving of large Mixture-of-Experts (MoE) models on personal machines by adapting offload and execution to measured device bandwidth and agentic workload patterns. Key features include bandwidth-adaptive execution, semantic-aware caching of recurrent state, and an elastic GPU expert cache; supports 20+ MoE models and runs models from ~35B to 753B on consumer/workstation GPUs.
AI Agent Papers2026
Chengyi Yang, Renxu Bao +11Affiliation: Xiamen University, Affiliation: Washington University in St. Louis +2
Converts real repositories into verifiable, sandboxed training environments with black-box tests to train coding agents on long-horizon program reproduction. Provides Program-Env for automated environment construction and Program-Agent for a role-isolated development workflow, yielding 1,648 C/C++/Go/Rust tasks and improving benchmark performance.