Search papers, labs, and topics across Lattice.
This study analyzes 3,553 software engineering chat sessions to identify the emergence of late requirements and their impact on code invalidation during coding-agent interactions. The findings reveal that the arrival of new requirements leads to approximately twice as much code invalidation compared to non-requirement edits, indicating a significant burden on development processes. Furthermore, the research highlights that this issue persists throughout the session without any observable decline, suggesting that late requirement emergence is a critical factor in project management and software development efficiency.
Late requirements can double code invalidation, revealing a hidden cost in coding-agent sessions that could derail project timelines and budgets.
Coding agents often implement changes before users have fully articulated their requirements, echoing a pattern from requirements engineering: stakeholders cannot express a constraint until part of the system exists to react to. This volatility is associated with schedule and budget overruns in traditional projects, but only at release-cycle granularity. Existing work on coding agents narrows this gap only partway: curated benchmarks fix requirements before implementation by design, and observational studies report pushback frequency without linking arrivals to the code invalidation they cause. We address this using 3,553 eligible SWE-chat sessions, coding post-implementation requirement arrivals along three dimensions and, where repository state can be replayed, linking each arrival to a proxy: deletion or replacement of prior agent-authored lines. A requirement's arrival is followed by roughly twice as much invalidation as matched non-requirement edits, robust to user-turn and net-deletion checks, though not demonstrated as causal. This burden shows no detectable decline over a session and no detected association with operation type once multiplicity is accounted for; several intervals remain wide. A controlled experiment shows delayed disclosure relocates implementation post-reveal, while advance warning produces no detected effect on overwriting. These results establish late requirement emergence as a measurable source of code invalidation.
