Post-Training on Office Work Improves Software Engineering: A Behavioral Account of Cross-Domain Transfer

• URL: http://arxiv.org/abs/2608.01604v1
• Date: Mon, 03 Aug 2026 02:22:02 GMT
• Title: Post-Training on Office Work Improves Software Engineering: A Behavioral Account of Cross-Domain Transfer
• Abstract summary: Long-horizon tasks require agents to maintain coherent state and goals across nested and branching work.<n>We call this capability goal execution (GDE): the repeated application of four behaviors, namely selecting goals, constructing task-relevant state, maintaining fidelity to higher-level objectives, and verifying completion against the environment.<n>We test this by post-training Qwen3.5-122B-A10B on 363 Long-Horizon Multi-Tool Agent (LHMTA) tasks drawn from office. The collection contained no software-directed tasks, yet the model's pass@1 improved by 5.8 points on SWE-Bench Pro.
• Score: 1.0742728354283815
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Long-horizon tasks require agents to maintain coherent state and goals across nested and branching work. We call this capability goal-directed execution (GDE): the repeated application of four behaviors, namely selecting goals, constructing task-relevant state, maintaining fidelity to higher-level objectives, and verifying completion against the environment. We hypothesize that long-horizon post-training strengthens these behaviors across domains. We test this by post-training Qwen3.5-122B-A10B on 363 Long-Horizon Multi-Tool Agent (LHMTA) tasks drawn from office workflows. The collection contained no software-engineering tasks, yet the model's pass@1 improved by 5.8 points on SWE-Bench Pro. Matched trajectory analysis shows gains in all four GDE behaviors in both office workflows and software repositories. Aggregate SWE-Bench Pro statistics showed related changes in information gathering, implementation, and verification. Together, the results support a behavioral interpretation in which long-horizon post-training changed how the model organized and applied knowledge across tasks, with effects extending beyond the training domain.

Related papers

• Out-of-Distribution Generalisation with Sequence Models in Offline Multi-Agent Reinforcement Learning [4.227963374833712]
  Generalising to unseen tasks remains a fundamental challenge in offline multi-agent reinforcement learning.<n>We show that scaling task diversity is the dominant factor in achieving robust zero-shot transfer.
  arXiv  Detail & Related papers  (2026-09-03T11:04:23Z)
• Cross-Benchmark Generalization in Long-Horizon Agents [1.0742728354283815]
  We post-train an open-weight mixture-of-experts model on 363 long-horizon Model Context Protocol (MCP) tasks across 27 categories.<n>No externalbenchmark task or grader entered training and no external score informed the reward, training hyper parameters, trained-checkpoint selection, or stopping.<n>Both software benchmarks improve despite the training collection containing no software-engineering tasks.
  arXiv  Detail & Related papers  (2026-07-31T18:05:36Z)
• Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement Learning [82.3676770818744]
  We present a framework for training large language models (LLMs) to "Connect the Dots" (CoD)<n>As an LLM-based AI agent gets deployed in an environment, it solves a long sequence of tasks while continuously exploring the environment.<n>We present proof-of-concept implementations of the CoD framework, including a GRPO-style RL algorithm with fine-grained credit assignment.
  arXiv  Detail & Related papers  (2026-06-18T09:38:45Z)
• From Question Answering to Task Completion: A Survey on Agent System and Harness Design [67.8241530947325]
  This survey examines LLM-based agents through a model-harness lens.<n>We first clarify the functional definition of agents and the implementation view of an LLM-based agent as a foundation model and an execution harness.<n>We then analyze the limits of model-centric scaling, trace four paradigms of agent engineering, and decompose the execution harness into six coupled runtime responsibilities.
  arXiv  Detail & Related papers  (2026-06-14T05:40:16Z)
• When LLMs Team Up: A Coordinated Attack Framework for Automated Cyber Intrusions [27.62993988829038]
  This paper presents CAESAR, a coordinated multi-agent framework for analysis of intrusion-style tasks.<n>CAESAR decomposes the workflow into five typed roles and coordinates them through a bounded protocol.<n>Compared with a single-agent baseline under matched budgets and tool access, CAESAR improves task success and reduces performance variance.
  arXiv  Detail & Related papers  (2026-05-09T07:47:42Z)
• Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows [67.92316850084575]
  We introduce Claw-Eval-Live, a live benchmark for workflow agents.<n>Each release is constructed from public workflow-demand signals.<n>Claw-Eval-Live records execution traces, audit logs, service state, and post-run workspace artifacts.
  arXiv  Detail & Related papers  (2026-04-30T17:23:19Z)
• LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces [65.11019654023978]
  LongCLI-Bench is a benchmark designed to evaluate agentic capabilities across long-horizon, realistic tasks.<n>We curated 20 high-quality, long-horizon tasks from over 1,000 computer science assignments and real-world tasks.<n>Experiments reveal that even state-of-the-art agents achieve pass rates below 20% in LongCLI-Bench.
  arXiv  Detail & Related papers  (2026-02-15T23:12:57Z)
• CORPGEN: Simulating Corporate Environments with Autonomous Digital Employees in Multi-Horizon Task Environments [1.6153514666902042]
  Real organizational work requires managing many concurrent long-horizon tasks with interleaving, dependencies, and reprioritization.<n>We introduce Multi-Horizon Task Environments (MHTEs): a distinct problem class requiring coherent execution across dozens of interleaved tasks.<n>We identify four failure modes that cause baseline CUAs to degrade from 16.7% to 8.7% completion as load scales 25% to 100%.<n>We present CorpGen, an architecture-agnostic framework addressing these failures via hierarchical planning for multi-horizon goal alignment.
  arXiv  Detail & Related papers  (2026-02-15T16:54:34Z)
• ANCHOR: Branch-Point Data Generation for GUI Agents [52.22377425487]
  End-to-end GUI agents for real desktop environments require large amounts of high-quality interaction data.<n>We present a trajectory expansion framework Anchor that bootstraps scalable desktop supervision from a small set of verified seed demonstrations.<n>Experiments on standard desktop benchmarks, OSWorld and WindowsAgentArena, show that models fine-tuned on our expanded corpus achieve consistent improvements.
  arXiv  Detail & Related papers  (2026-02-06T19:55:26Z)
• Unified Work Embeddings: Contrastive Learning of a Bidirectional Multi-task Ranker [3.4204762278595346]
  We introduce WorkBench, the first unified evaluation suite spanning six work-related tasks formulated explicitly as ranking problems.<n>We use this insight to compose task-specific bipartite graphs from real-world data, synthetically enriched through grounding.<n>This leads to Unified Work Embeddings (UWE), a task-agnostic bi-encoder that exploits our training-data structure with a many-to-many InfoNCE objective.
  arXiv  Detail & Related papers  (2025-11-11T08:28:26Z)
• OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation [65.15955645757705]
  We introduce Workforce, a hierarchical multi-agent framework that decouples strategic planning from specialized execution.<n>During inference, Workforce seamlessly adapts to new domains by adding or modifying worker agents.<n>For training, we introduce optimized Workforce Learning (OWL), which improves generalization across domains.
  arXiv  Detail & Related papers  (2025-05-29T17:51:58Z)
• Spatial Reasoning and Planning for Deep Embodied Agents [2.7195102129095003]
  This thesis explores the development of data-driven techniques for spatial reasoning and planning tasks. It focuses on enhancing learning efficiency, interpretability, and transferability across novel scenarios.
  arXiv  Detail & Related papers  (2024-09-28T23:05:56Z)

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.