Interlock: From Local Correctness to Task Completion in Long-Horizon Agents
cs.CL, cs.AI
Submitted: 2026-10-14
Updated: 2026-10-14
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- ClawGym: A Scalable Framework for Building Effective Claw Agents
- AutoForge: Automated Environment Synthesis for Agentic Reinforcement Learning
- M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
- Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
- Toward Scalable Terminal Task Synthesis via Skill Graphs
- Endless Terminals: Scaling RL Environments for Terminal Agents
- Anchor: Mitigating Artifact Drift in Agent Benchmark Generation
- JobBench: Aligning Agent Work With Human Will
- Recursive Synthesis for Long-Horizon Terminal Tasks
- Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
- ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases
- ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Training
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL
- CodeMidas: Scaling Agentic Coding RL Environments from Code Itself
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