5 citations · 10 across the 32 of their papers we have counts for
24 papers · 1 filter
How Data Scales in Agentic Reinforcement Learning: Laws and Synthesis Strategies
Bowei He, Yankai Chen, Xiaokun Zhang +4
Pretraining scaling laws treat training data as a one-dimensional quantity: a token count. Agentic reinforcement learning (RL) inherits this scalar abstraction, but modern synthesi…
Beneath the Diff: Diagnosing and Mitigating Algorithmic Mode Collapse in Code-Level Autonomous Research Loops
Bowei He, Weixu Zhang, Yili Jin +1
Code-level autonomous research loops (ARLs) have recently emerged as a concrete object of study in automated machine learning research. In such loops, an LLM agent proposes modific…
Discrete Diffusion Models: A Unified Framework from Tokenization to Generation
Ye Yuan, Weien Li, Rui Song +20
Discrete denoising diffusion models (DDMs) have recently emerged as a compelling alternative to autoregressive (AR) modeling for discrete data, offering parallel generation and ite…
Branching Policy Optimization: Sandbox-Native Language Agent Reinforcement Learning
Bowei He, Yankai Chen, Xiaokun Zhang +1
Reinforcement learning has emerged as the dominant paradigm for training large language model (LLM) agents that interact with executable sandboxes. State-of-the-art algorithms such…
Beyond Document Grounding: Span-Level Hallucination Detection over Code, Tool Output, and Documents
Ádám Kovács, Bowei He, Xue Liu +3
Hallucination detection for retrieval-augmented generation (RAG) is usually evaluated on natural-language document evidence. However, grounded generation systems increasingly rely…
Distributionally Robust Set Representation Learning Under Inference-Time Element Corruption
Yankai Chen, Hanrong Zhang, Bowei He +2
Standard Set Representation Learning methods typically excel on curated data but often overlook the challenge of inference-time element corruption. This refers to scenarios where d…
Support-Proximity Augmented Diffusion Estimation for Offline Black-Box Optimization
Yonghan Yang, Ye Yuan, Zipeng Sun +5
Offline black-box optimization aims to discover novel designs with high property scores using only a static dataset, a task fundamentally challenged by the out-of-distribution (OOD…
MINER: Mining Multimodal Internal Representation for Efficient Retrieval
Weien Li, Rui Song, Zeyu Li +8
Visual document retrieval has become essential for accessing information in visually rich documents. Existing approaches fall into two camps. Late-interaction retrievers achieve st…
QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents
Ye Yuan, Rui Song, Weien Li +12
Social deduction games have become a popular testbed for probing reasoning, deception, coordination, and belief modeling in Large Language Model (LLM) agents. However, most environ…
Scaling Mobile Agent Systems: From Capability Density to Collective Intelligence
Bowei He
Mobile agent systems are emerging as a key paradigm for enabling intelligent applications on edge devices and in AIoT ecosystems. However, their scalability is fundamentally constr…
Token-Budget-Aware Pool Routing for Cost-Efficient LLM Inference
Huamin Chen, Xunzhuo Liu, Junchen Jiang +2
Production vLLM fleets provision every instance for worst-case context length, wasting 4-8x concurrency on the 80-95% of requests that are short and simultaneously triggering KV-ca…
Beyond Message Passing: A Semantic View of Agent Communication Protocols
Dun Yuan, Fuyuan Lyu, Ye Yuan +11
Agent communication protocols are becoming critical infrastructure for large language model (LLM) systems that must use tools, coordinate with other agents, and operate across hete…
Dual-Pool Token-Budget Routing for Cost-Efficient and Reliable LLM Serving
Xunzhuo Liu, Bowei He, Xue Liu +3
Production vLLM fleets typically provision each instance for the worst-case context length, leading to substantial KV-cache over-allocation and under-utilized concurrency. In pract…
The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project
Huamin Chen, Xunzhuo Liu, Bowei He +5
Over the past year, the vLLM Semantic Router project has released a series of work spanning: (1) core routing mechanisms -- signal-driven routing, context-length pool routing, rout…
From Inference Routing to Agent Orchestration: Declarative Policy Compilation with Cross-Layer Verification
Huamin Chen, Xunzhuo Liu, Bowei He +1
The Semantic Router DSL is a non-Turing-complete policy language deployed in production for per-request LLM inference routing: content signals (embedding similarity, PII detection,…
Knowledge Access Beats Model Size: Memory Augmented Routing for Persistent AI Agents
Xunzhuo Liu, Bowei He, Xue Liu +3
Production AI agents frequently receive user-specific queries that are highly repetitive, with up to 47\% being semantically similar to prior interactions, yet each query is typica…
Conflict-Free Policy Languages for Probabilistic ML Predicates: A Framework and Case Study with the Semantic Router DSL
Xunzhuo Liu, Hao Wu, Huamin Chen +2
Conflict detection in policy languages is a solved problem -- as long as every rule condition is a crisp Boolean predicate. BDDs, SMT solvers, and NetKAT all exploit that assumptio…
FleetOpt: Analytical Fleet Provisioning for LLM Inference with Compress-and-Route as Implementation Mechanism
Huamin Chen, Xunzhuo Liu, Yuhan Liu +3
Modern LLM GPU fleets are provisioned for worst-case context lengths that the vast majority of requests never approach, wasting GPU capacity on idle KV-cache slots. We present Flee…
inference-fleet-sim: A Queueing-Theory-Grounded Fleet Capacity Planner for LLM Inference
Huamin Chen, Xunzhuo Liu, Yuhan Liu +3
Sizing a GPU fleet for LLM inference is harder than it looks. The obvious questions -- how many GPUs, which type, where to split a two-pool fleet -- have no closed-form answers. Th…
Visual Confused Deputy: Exploiting and Defending Perception Failures in Computer-Using Agents
Xunzhuo Liu, Bowei He, Xue Liu +3
Computer-using agents (CUAs) act directly on graphical user interfaces, yet their perception of the screen is often unreliable. Existing work largely treats these failures as perfo…
Outcome-Aware Tool Selection for Semantic Routers: Latency-Constrained Learning Without LLM Inference
Huamin Chen, Xunzhuo Liu, Junchen Jiang +2
Semantic routers in LLM inference gateways select tools in the critical request path, where every millisecond of added latency compounds across millions of requests. We propose Out…
Adaptive Vision-Language Model Routing for Computer Use Agents
Xunzhuo Liu, Bowei He, Xue Liu +3
Computer Use Agents (CUAs) translate natural-language instructions into Graphical User Interface (GUI) actions such as clicks, keystrokes, and scrolls by relying on a Vision-Langua…
98 Faster LLM Routing Without a Dedicated GPU: Flash Attention, Prompt Compression, and Near-Streaming for the vLLM Semantic Router
Xunzhuo Liu, Bowei He, Xue Liu +3
System-level routers that intercept LLM requests for safety classification, domain routing, and PII detection must be both fast and operationally lightweight: they should add minim…
Fast and Faithful: Real-Time Verification for Long-Document Retrieval-Augmented Generation Systems
Xunzhuo Liu, Bowei He, Xue Liu +2
Retrieval-augmented generation (RAG) is increasingly deployed in enterprise search and document-centric assistants, where responses must be grounded in long and complex source mate…