Problem
Research questions and friction points this paper is trying to address.
goal-directed execution
cross-domain transfer
long-horizon tasks
post-training
behavioral generalization
Post-Training on Office Work Improves Software Engineering: A Behavioral Account of Cross-Domain Transfer
🤖 AI Summary
This work addresses the limited goal-directed execution capability of large language models in long-horizon tasks by introducing a Goal-Directed Execution (GDE) behavioral framework. The authors conduct post-training on the Qwen3.5-122B-A10B model using 363 long-horizon, multi-tool agent tasks from office scenarios, without relying on software engineering data. This approach yields a notable improvement on SWE-Bench Pro, increasing pass@1 by 5.8 percentage points. Experimental results demonstrate significant enhancements across four core GDE capabilities: goal selection, state construction, goal consistency maintenance, and environment validation. Furthermore, the model exhibits effective cross-domain transfer between office and software engineering tasks, confirming that long-horizon post-training can successfully drive the transfer of behavioral mechanisms.
📝 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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
goal-directed execution
long-horizon post-training
cross-domain transfer
behavioral account
multi-tool agent
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
