11 papers
Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning
Heng Wang, Jielin Qiu, Wenting Zhao +8
Large language models achieve superior performance on tasks that require extended reasoning, but long chains of thought make the KV cache a severe memory bottleneck. Existing KV ca…
AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses
Cheng Qian, Wenting Zhao, Liangwei Yang +6
Recent work on distillation transfers the capabilities of large models to smaller ones often by updating the latter's parameters, through teacher forcing, on-policy distillation, a…
PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems
Jiayu Liu, Qihan Lin, Cheng Qian +8
LLM agents increasingly operate in large tool ecosystems, where real-world tasks require discovering relevant tools, inferring implicit sub-goals, and adapting to dynamic environme…
OctoNest: Adaptive Cross-Device Execution through Stateful Control
Shu Yao, Yuhua Luo, Qian Long +7
Computer use agents are expanding from single-device operation toward cross-device systems that coordinate tasks across heterogeneous environments. Execution conditions are often o…
ACCORD: Action-Conditioned Contextual Grounding for Language Agents
Lai Jiang, Cheng Qian, Zhenhailong Wang +3
User instructions are often underspecified because humans rely on implicit assumptions about the surrounding environment. For large language model (LLM) agents operating in informa…
Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale
Ang Li, Ben Liu, Bin Han +215
Efficient and scalable agentic intelligence requires models that can deliver both low-latency responses and strong reasoning capabilities while remaining practical to train, serve,…
On Effectiveness and Efficiency of Agentic Tool-calling and RL Training
Tong Liu, Cheng Qian, Matej Cief +4
Tool-calling is a central component of modern large language model (LLM) agents, equipping them with skills beyond their parametric knowledge. This paper studies tool-calling along…
LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering
Jielin Qiu, Zuxin Liu, Zhiwei Liu +18
As large language models (LLMs) evolve into sophisticated autonomous agents capable of complex software development tasks, evaluating their real-world capabilities becomes critical…
xRouter: Training Cost-Aware LLMs Orchestration System via Reinforcement Learning
Cheng Qian, Zuxin Liu, Shirley Kokane +10
Modern LLM deployments confront a widening cost-performance spectrum: premium models deliver strong reasoning but are expensive, while lightweight models are economical yet brittle…
UserRL: Training Interactive User-Centric Agent via Reinforcement Learning
Cheng Qian, Zuxin Liu, Akshara Prabhakar +10
Reinforcement learning (RL) has shown promise in training agentic models that move beyond static benchmarks to engage in dynamic, multi-turn interactions. Yet, the ultimate value o…
LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering
Jielin Qiu, Zuxin Liu, Zhiwei Liu +14
The emergence of long-context language models with context windows extending to millions of tokens has created new opportunities for sophisticated code understanding and software d…