会员服务
Greed Is Learned: Visible Incentives as Reward-Hacking Triggers
Arxiv
0+阅读 · 6月15日
TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning
Arxiv
0+阅读 · 5月27日
Context: Proactive Goal-Directed Intelligence via Composable Sandboxed Programs, Declarative Wiring, and Structured Interaction
Arxiv
0+阅读 · 4月21日
YeasierAgent: Agentic Social Sandbox as a Canvas for Intent-Driven Creation of Platform-Agnostic Symbiotic Agent-Native Applications
Arxiv
0+阅读 · 6月11日
Bathtubs, Boundaries, and Sandboxes: AI Regulatory Learning under Legal Uncertainty
Arxiv
0+阅读 · 6月8日
Governed Capability Evolution for Embodied Agents: Safe Upgrade, Compatibility Checking, and Runtime Rollback for Embodied Capability Modules
Arxiv
0+阅读 · 4月9日
ProRL Agent: Rollout-as-a-Service for RL Training of Multi-Turn LLM Agents
Arxiv
0+阅读 · 3月19日
Splits! Flexible Sociocultural Linguistic Investigation at Scale
Arxiv
0+阅读 · 4月9日
Agent-Diff: Benchmarking LLM Agents on Enterprise API Tasks via Code Execution with State-Diff-Based Evaluation
Arxiv
0+阅读 · 2月11日
Among Us: A Sandbox for Measuring and Detecting Agentic Deception
Arxiv
0+阅读 · 2月10日
AgentCgroup: Understanding and Controlling OS Resources of AI Agents
Arxiv
0+阅读 · 2月10日
LLM-in-Sandbox Elicits General Agentic Intelligence
Arxiv
0+阅读 · 2月12日
TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning
Arxiv
0+阅读 · 2月2日
SandCell: Sandboxing Rust Beyond Unsafe Code
Arxiv
0+阅读 · 1月18日
Retrieval-Infused Reasoning Sandbox: A Benchmark for Decoupling Retrieval and Reasoning Capabilities
Arxiv
0+阅读 · 1月29日
参考链接
微信扫码咨询专知VIP会员
Top