arXiv AI
SkillHorizon: Constructing Long-Horizon Agent Tasks through Skill Composition
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computation and Language
1d ago
Interlock: From Local Correctness to Task Completion in Long-Horizon Agents
Interlock is a framework that transforms long‑horizon tasks into typed completion graphs, linking evidence, decisions, and required effects through grounding, coupling, and realization edges. It compiles these graphs into a resettable workspace, a public request, and an evaluation rubric, and uses source‑coverage, public‑input, and agent‑as‑judge reviews to ensure that all mandatory requirements are met. Fine‑tuning Qwen3.6 backbones on Interlock‑generated trajectories improves pass rates on AutomationBench, JobBench, and Harvey LAB, showing that the synthesized experience benefits external task environments.
arXiv AI
Jul 28
SQBench: A Benchmark for Evaluating Task Delivery by Language-Model Agents in Production-Oriented Workflows
arXiv:2607. 23123v1 Announce Type: new Abstract: Existing evaluations of large language models cover knowledge, reasoning, coding, and tool use, but they rarely treat a verifiable deliverable produced within a constrained workflow as the unit of evaluation.
arXiv AI
1d ago
Long-Horizon-Terminal-Bench 2.0: Automating Diverse Task Construction and Measuring Sustained Agent Progress
arXiv:2610.14146v1 Announce Type: new Abstract: Long-horizon terminal benchmarks measure whether an agent can sustain progress through extended workflows with process rewards, not only whether its fi...
arXiv AI
1d ago
SkillForgeBench: Evaluating Agent Reliability Grounded in Agent Skill Specifications
arXiv:2610.14918v1 Announce Type: new Abstract: Evaluating an agent's ability to strictly satisfy diverse and procedurally complex requirements is essential to determining its practical reliability....
arXiv Computation and Language
Sep 24
SkillGym: Internalizing Human Skills into LLMs for Real-World Problem Solving
arXiv:2609.27717v1 Announce Type: new Abstract: Human-written agent skills encode rich workflows for real-world problem solving, but are typically used as external inference-time instructions rather...
arXiv AI
Jun 9
SKILL.nb: Selective Formalization and Gated Execution for Durable Agent Workflows
arXiv:2606. 08049v1 Announce Type: new Abstract: AI agents increasingly turn past experience into reusable artifacts such as code, workflows, and procedural memories.