activity
20242026
collaborators
Showing cs.CLShow all

11 papers · 1 filter

cs.CL2026

External Experience Serving in Production LLM Systems: A Deployment-Oriented Study of Quality-Cost Trade-offs

Lin Sun, Heming Zhang, Xiangzheng Zhang

Production LLM systems accumulate reusable operational experience, but the practical deployment issue is not merely whether such experience can help. It is how different serving st…

cs.CL2026

RealClawBench: Live OpenClaw Benchmarks from Real Developer-Agent Sessions

Zongwei Lv, Zhewen Tan, Yaoming Li +7

Agent benchmarks should reflect what users actually ask deployed agents to do, yet existing benchmarks often miss key realism properties of real developer-agent sessions. We introd…

cs.CL2026

A Primer in Post-Training Reasoning Data: What We Know About How It Works

Yaoming Li, Guangxiang Zhao, Qilong Shi +3

Post-training has become a primary driver of recent progress in large reasoning models, and reasoning data are often the key variable determining whether this stage succeeds. Work…

cs.CL2026

BEAR: Budgeted Evidence Allocation for Multi-Document Reasoning

Lin Sun, Linglin Zhang, Jingang Huang +3

We argue that multi-document reasoning is constrained not only by how much text a model can read, but also by how limited query-time evidence budget is allocated across documents a…

cs.CL2026

TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation

Lin Sun, Guangxiang Zhao, Xiaoqi Jian +18

The challenge of reducing the size of Large Language Models (LLMs) while maintaining their performance has gained significant attention. However, existing methods, such as model di…

cs.CL2026

Beyond Static Alignment: Hierarchical Policy Control for LLM Safety via Risk-Aware Chain-of-Thought

Jianfeng Si, Lin Sun, Weihong Lin +1

Large Language Models (LLMs) face a fundamental safety-helpfulness trade-off due to static, one-size-fits-all safety policies that lack runtime controllabilityxf, making it difficu…