Scaling Verifiable Environments for Long-horizon Work Agents
cs.CL, cs.AI
Submitted: 2026-10-04
Updated: 2026-10-13
Sources
- DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use
- Terminal-World: Scaling Terminal-Agent Environments via Agent Skills
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
- Toward Scalable Terminal Task Synthesis via Skill Graphs
- Kimi K2.5: Visual Agentic Intelligence
- Scaling Synthetic Task Generation for Agents via Exploration
- OpenThoughts-Agent: Data Recipes for Agentic Models
- TaskCraft: Automated Generation of Agentic Tasks
- EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis
- PaperBench: Evaluating AI's Ability to Replicate AI Research
- Agents' Last Exam
- Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies
- ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Training
- Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning
- AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents
- TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments
- Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment
- Entropy Polarity in Reinforcement Fine-Tuning: Direction, Asymmetry, and Control
- NexForge: Scaling Agent Capabilities through Requirement-Driven Task Synthesis for LLMs
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering