Correct is the
correctness-filtered arm of a four-arm controlled study of training-data interventions against
over-reflection in web-search agents. It is a supervised fine-tune of
Qwen/Qwen3.5-35B-A3B on the subset of the in-house web-search agent trajectory corpus (shared with the
Asis baseline) whose
final answers match the reference under deterministic answer matching. No trajectory editing is performed — selection is purely by outcome.
Full-parameter supervised fine-tuning on a Megatron-based distributed training stack. Identical recipe to the sibling arms; only the data intervention differs.
Each trajectory's final answer is checked against its reference answer with a deterministic matching rule (no model-based judging), and only trajectories that pass are kept. This is the classic
rejection-sampling-style selection baseline of the study: it conditions on
outcome only, and is agnostic to how the agent behaved along the way. In particular, a correct-but-wasteful trajectory (one that reaches the right answer and then keeps searching) survives this filter — which is exactly the contrast the four-arm design probes against the process-conditioned
Drop and
Repair arms and their
A–G over-reflection taxonomy (post-answer verification loops, redundant re-search after sufficient evidence, ungrounded reasoning).
An RL continuation of this arm is released as
Qwen3.5-35B-A3B-Correct-GRPO.
Research artifact. Intended for studying outcome-conditioned data selection as a baseline against process-conditioned interventions for over-reflection, stopping behavior, and search efficiency in tool-using web agents, and as an RL initialization. It expects a browsing-agent tool surface compatible with its training format (function-calling tools for web search, page opening, and in-page lookup).
