Recursive Synthesis for Long-Horizon Terminal Tasks

• URL: http://arxiv.org/abs/2608.05466v3
• Date: Wed, 12 Aug 2026 19:28:42 GMT
• Title: Recursive Synthesis for Long-Horizon Terminal Tasks
• Abstract summary: Recursive Synthetic Terminal Tasks (RST) is a framework for constructing long-horizon terminal-agent tasks at scale.<n>RST produces 37,484 synthesized terminal-agent tasks at roughly $0.05 per task.<n>Fine-tuning on trajectories improves Qwen3.5-27B and Qwen3.5-122B-A10B by up to 10 points on Terminal-Bench 2, Terminal-Bench Hard, and Long-Horizon Terminal Bench.
• Score: 50.39352383646813
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: High-quality long-horizon training data for terminal agents is expensive to produce, often costing hundreds to thousands of dollars per task, because each task must keep the instruction, environment, reference solution, and verifier mutually consistent. Human authoring does not scale, and direct generation with large language models (LLMs) often breaks these dependencies. We present Recursive Synthetic Terminal Tasks (RST), a recursive verified synthesis framework for constructing long-horizon terminal-agent tasks at scale. Starting from verified seed tasks, RST extends the reference solution, realigns the verifier and instruction to the new workflow, validates the result in a fresh sandbox, and reuses accepted tasks as seeds for subsequent rounds. Across fifteen recursive rounds, RST produces 37,484 synthesized terminal-agent tasks at roughly $0.05 per task. Task difficulty increases substantially over rounds: the median reference solution grows from 67 to 374 lines, the median number of executed commands grows from 40 to 244, and DeepSeek-V4-Pro pass@4 drops from 90% at R1 to 2.5% at R15. To demonstrate training utility, we collect rejection-sampled Qwen3.5 trajectories on the synthesized tasks and use them for supervised fine-tuning. Fine-tuning on these trajectories improves Qwen3.5-27B and Qwen3.5-122B-A10B by up to 10 points on Terminal-Bench 2, Terminal-Bench Hard, and Long-Horizon Terminal Bench, while agentic PPO lifts Qwen3.5-27B to 49.44%, 32.00%, and 22.07% on the three benchmarks, corresponding to relative gains of 20.0%, 41.2%, and 21.9% over the base model. Moreover, after 15 rounds, the recursion shows no ceiling: synthesis yield and validation rates remain stable as difficulty keeps climbing, indicating that the process can continue well beyond the scale reported here.

Related papers

• T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks [27.750923745153145]
  T1 is a Mixture-of-Experts model of 122B total trained with reinforcement learning.<n>It operates a real shell in a cloud sandbox for up to 300+ tool-call turns per task, rewarded by executing each task's own verifier.<n>On Terminal-Bench 2.1, our post-train pipeline raises initial base model from 43.8% to T1 with 64.0% resolved.
  arXiv  Detail & Related papers  (2026-09-10T03:42:01Z)
• Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments [89.86581796261123]
  We introduce Terminal-Universe, a framework which turns each trajectory into a reusable environment.<n>Terminal-Universe replays the file operations recorded in a trajectory to restore each file before the agent modified it, yielding a partial workspace.<n>We also scale the tasks along two axes: breadth and depth.
  arXiv  Detail & Related papers  (2026-09-03T17:41:05Z)
• AgentOmnia: Scaling Agentic Models for Full-Scenario Applications [36.656762500581216]
  Large language model agents have advanced rapidly, yet progress remains fragmented across domains, capabilities, task difficulty, and interaction settings.<n>We frame this as full-scenario agentic scaling and present Agent Omnia, a framework coordinating task-space definition, data synthesis, post-training, evaluation, and improvement across To-Consumer (ToC), To-Business (ToB), and To-Employee (ToE) applications.
  arXiv  Detail & Related papers  (2026-07-25T09:58:24Z)
• SETA: Scaling Environments for Terminal Agents [49.686781072283814]
  We propose SETA, a scalable framework for generating verifiable terminal environments for reinforcement learning.<n>We release SETA-Env, the largest open-source verifiable terminal RL dataset to date, containing over 4,500 environments.
  arXiv  Detail & Related papers  (2026-07-12T19:40:27Z)
• Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading [46.911171278867585]
  Long-Horizon-Terminal-Bench is a terminal benchmark of 46 long-horizon tasks spanning nine categories.<n>Each task follows a Terminal-Bench-style setup with a reference solution or simulation engine, but is further graded into fine-grained sub-tasks.<n>We evaluate 15 frontier models and find that agents consume on average 9.9M tokens per task, with roughly 231 episodes and 85.3 minutes of execution time per run.
  arXiv  Detail & Related papers  (2026-07-09T21:56:37Z)
• SPOQ: Specialist Orchestrated Queuing for Multi-Agent Software Engineering [2.0769172070951067]
  Multi-agent AI systems show promise for automating software engineering tasks.<n>Existing approaches suffer from coordination overhead, quality control gaps, and limited human oversight.<n>We introduce SPOQ (Specialist Orchestrated Queuing), a methodology combining three innovations.
  arXiv  Detail & Related papers  (2026-06-02T03:59:56Z)
• Terminal-World: Scaling Terminal-Agent Environments via Agent Skills [52.39713754337834]
  We introduce Terminal-World, a fully automated pipeline that uses agent skills as the central synthesis primitive.<n>We construct 5,723 training environments and train Terminal-World-8B/14B/32B, evaluated across 6 benchmarks.<n>Terminal-World-32B surpasses Nemotron-Terminal-32B on Terminal-Bench 2.0 by +4.5 Pass@1 (31.5) and achieves 43.8 Pass@3.
  arXiv  Detail & Related papers  (2026-05-20T08:14:51Z)
• On Data Engineering for Scaling LLM Terminal Capabilities [62.14352406328365]
  Training data strategies behind state-of-the-art terminal agents remain largely undisclosed.<n>We address this gap through a systematic study of data engineering practices for terminal agents.<n>Our pipeline yields Terminal-Corpus, a large-scale open-source dataset for terminal tasks.
  arXiv  Detail & Related papers  (2026-02-24T18:51:04Z)
• Large-Scale Terminal Agentic Trajectory Generation from Dockerized Environments [36.81059045059001]
  Training agentic models for terminal-based tasks depend on high-quality terminal trajectories that capture realistic long-horizon interactions.<n>We propose textbfTerminalTraj, a scalable pipeline that generates Docker-aligned task instances and synthesizes agent trajectories with executable validation code.<n>Using TerminalTraj, we curate 32K Docker images and generate 50,733 verified terminal trajectories across eight domains.
  arXiv  Detail & Related papers  (2026-02-01T14:09:23Z)
• Endless Terminals: Scaling RL Environments for Terminal Agents [39.60665149203152]
  Endless Terminals is a fully autonomous pipeline that procedurally generates terminal-use tasks without human annotation.<n>We train agents using vanilla PPO with binary episode level rewards and a minimal interaction loop.<n>These improvements transfer to human-curated benchmarks.
  arXiv  Detail & Related papers  (2026-01-23T04:39:55Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents [60.881609323604685]
  Agent Synth is a scalable and cost-efficient pipeline for automatically synthesizing high-quality tasks and trajectory datasets.<n>Our pipeline achieves a low average cost of $0.60 per trajectory, orders of magnitude cheaper than human annotations.
  arXiv  Detail & Related papers  (2025-06-17T05:46:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.