Skip to content

fix(search-r1): stop generation at </search> and </answer> #2036

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
zhuzilin merged 1 commit into from
Jun 13, 2026
Merged

fix(search-r1): stop generation at </search> and </answer> #2036

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 15 additions & 0 deletions examples/search-r1/generate_with_search.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -157,6 +157,21 @@ async def generate(args, sample: Sample, sampling_params) -> Sample:
loss_mask = []
rollout_log_probs = [] if SEARCH_R1_CONFIGS["return_logprob"] else None

# BUGFIX: make the inference engine STOP at the tool/answer boundary.
# Without a stop, sglang keeps emitting tokens after </search> / </answer>
# (junk, even fabricated new "Question:"s). The example only trimmed that junk
# via postprocess_responses when return_logprob=False; with return_logprob=True
# (TIS) trimming is disabled to keep token/logp aligned, so the junk stayed in
# the trajectory and got trained on (loss_mask=1) AND broke is_valid_sequence
# (trailing content after </answer> -> format invalid -> lower reward).
# Stopping at the tag avoids all of that and keeps token/logp aligned natively.
# slime already sets no_stop_trim=True, so the closing tag is kept in the output.
_stop_tags = ["</search>", "</answer>"]
_existing_stop = sampling_params.get("stop") or []
if isinstance(_existing_stop, str):
_existing_stop = [_existing_stop]
sampling_params = {**sampling_params, "stop": list(dict.fromkeys([*_existing_stop, *_stop_tags]))}

for _turn_idx in range(SEARCH_R1_CONFIGS["max_turns"]):
payload = {
"text": prompt_text + response,
Expand Down
Loading