11 papers · 1 filter
Judged Useless, Queried Anyway: Tool-Using Agents Rarely Turn Their Own Evidence Judgments into Stopping Decisions
Chubin Zhang, Zhenglin Wan, Xingrui Yu +4
An agent whose tool keeps returning nothing useful should stop relying on it. In a retrieval environment with controlled source failures, we separate how agents judge results from…
CUA-Sandbox: Efficient Environments for Computer-Use Agent Reinforcement Learning
Xin Yan, Zhengbo Jiao, Jiaqi Liu +11
Reinforcement learning enables computer-use agents to improve through interaction with real software environments, including websites and desktop applications. However, conventiona…
SpikeOPD: Stable On-Policy Distillation for Autoregressive Spiking Language Models
Enqiao Lu, Xingrui Yu, Yiwei Fu +7
Spiking neural networks (SNNs) offer a path to energy-efficient language modeling through sparse encoding and event-driven computation, but training capable spiking language models…
Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models
Pengfei Zhou, Hexin Wang, Zhengfeiyang Zhang +5
A common strategy for scaling world models is to train on more crawled video with more compute. We argue that this strategy is inefficient: scaling world models also requires a rec…
Improving Generalization Robustness of Multimodal RLVR
Pengfei Zhou, Zhiwei Tang, Xiaopeng Peng +11
Reinforcement Learning with Verifiable Rewards (RLVR) makes Multimodal Large Language Models more accurate, but the gains are brittle: simply paraphrasing a question or changing th…
SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale
Tong Bai, Zhenglin Wan, Pengfei Zhou +3
Large skill libraries are now standard equipment for LLM agents, and which subset reaches the prompt decides what the agent can do. Enumeration and top- embedding retrieval both…
Agent-as-a-Router: Agentic Model Routing for Coding Tasks
Pengfei Zhou, Zhiwei Tang, Yixing Ma +8
Real-world users typically have access to multiple Large Language Models (LLMs) from different providers, and these LLMs often excel at distinct domains, yet none dominate all. Con…
Don't Blindly Trust It: How Unreliable Feedback Breaks Tool-Using LLM Agents
Chubin Zhang, Zhenglin Wan, Xingrui Yu +5
Tool-augmented agents are typically evaluated by their gains under reliable external feedback. Yet these gains leave open a key counterfactual: when feedback is unreliable, would t…
Calibration Is Not Control: Intervention Value for LLM-Agent Oversight
Chubin Zhang, Zhenglin Wan, Xingrui Yu +5
Runtime oversight often intervenes when an LLM agent's calibrated failure score crosses a threshold. Yet states with the same failure risk can differ in whether intervention helps.…
ANO: Robust Policy Optimization via Bounded, Redescending Gain Fields
Yiheng Zhang, Yiming Wang, Kaiyan Zhao +3
Proximal Policy Optimization (PPO) dominates reinforcement learning and LLM alignment, yet its hard-clipping mechanism and unconstrained alternatives (e.g., SPO) sit at two extreme…
Letting Trajectories Spread: Quality-Preserving Control for Diverse Flow Matching
Jingxuan Wu, Zhenglin Wan, Xingrui Yu +4
Flow-based text-to-image models follow deterministic trajectories, making it costly to explore diverse modes under limited sampling budgets. Existing approaches to improving divers…