Skip to content

Pull requests: sierra-research/tau2-bench

New pull request New
80 Open 212 Closed
80 Open 212 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Website: split leaderboard into Core / Knowledge / Voice buckets
#426 opened Jul 18, 2026 by keshav-sierra Contributor Loading…
3 of 4 tasks
fix: retry transient transcription failures
#418 opened Jul 17, 2026 by Sanjays2402 Loading…
3 of 4 tasks
1
fix(data): validate reward criteria gates
#411 opened Jul 16, 2026 by EnesYilmazcode Loading…
feat: add gptlive audio-native provider (GPT-Live API alpha)
#409 opened Jul 15, 2026 by keshav-sierra Contributor Loading…
4 tasks done
docs: add Qwen3.5-4B Retail baseline submission
#404 opened Jul 15, 2026 by keepkeen Loading…
fix(banking_knowledge): normalize nested JSON strings in action grader comparisons
#401 opened Jul 14, 2026 by lugmanhussainkhan Loading…
Add voice-banking track (voice + knowledge): gpt-realtime-2 & gemini-3.1-flash-live on banking_knowledge
#395 opened Jul 13, 2026 by soham-sierra Contributor Loading…
Add voice submission: Humains Cascaded Voice Agent — airline (humains.com)
#394 opened Jul 13, 2026 by Nisyron Loading…
4
fix(evaluator): don't let one simulation's error abort a batch run (#387)
#393 opened Jul 12, 2026 by samarth70 Loading…
1
2
Improving user simulator fidelity in tau2-bench
#392 opened Jul 9, 2026 by pruksmhc Loading…
test: cover text imports without optional dependencies
#391 opened Jul 9, 2026 by paulchum Loading…
Include reasoning content in message formatting
#389 opened Jul 9, 2026 by yang-su2000 Loading…
Add voice submission: grok-voice-think-fast-1.0 + tool-mentor (custom, Pickle)
#386 opened Jul 7, 2026 by samtiz Loading…
1
Add ByteVerity custom banking n=4 submission
#385 opened Jul 6, 2026 by mohitunplugged Loading…
@benshi34
2
fix: secure second debit card in task 82
#382 opened Jul 2, 2026 by Sehlani042 Loading…
1
Add ByteVerity airline custom submission
#376 opened Jun 29, 2026 by mohitunplugged Loading…
1
Submission: Add DRQ-27B core-domain leaderboard results
#375 opened Jun 28, 2026 by AiObserver Loading…
2
Add submission: Humains Nemotron-ultra Agent — airline (humains.com)
#368 opened Jun 23, 2026 by Nisyron Loading…
5
Add DRQ-9B leaderboard submission
#367 opened Jun 23, 2026 by AiObserver Loading…
Submission: Add evaluation result of RAFT-27B on retail domain
#366 opened Jun 23, 2026 by Ziyiii0-0 Contributor Loading…
1
feat: Return-and-Exchange agent eval with cost-per-resolution tracking
#364 opened Jun 19, 2026 by annagibaeva Loading…
1 of 3 tasks
2
fix: drain buffered full-duplex agent audio
#363 opened Jun 18, 2026 by JaeCoding Loading…
fix: release airline seats on cancellation
#362 opened Jun 18, 2026 by JaeCoding Loading…
4 tasks done
1
fix: preserve user tool calls in LiteLLM messages
#361 opened Jun 18, 2026 by JaeCoding Loading…
1
fix: classify context-window failures instead of retrying them as infra errors
#360 opened Jun 15, 2026 by EnesYilmazcode Loading…
1
1
ProTip! Add no:assignee to see everything that’s not assigned.