Owner
sierra-research
1 indexed repository · View on GitHub
-
tau2-bench
τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
Python · 2189 stars
Issues somebody may already be working on are listed last. List everything by date
-
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
sierra-research/tau2-bench#635 ·
Maintainers usually reply within 1 day
-
Difficulty 5/5 Over a week Newbie friendliness 15/100
sierra-research/tau2-bench#628 ·
Maintainers usually reply within 1 day
-
Difficulty 1/5 Under an hour Newbie friendliness 15/100
sierra-research/tau2-bench#612 ·
Maintainers usually reply within 1 day
-
[banking_knowledge] task_086: gold liability amounts need a statement date that the task never givesOpen
Difficulty 3/5 1-2 days Newbie friendliness 53/100
sierra-research/tau2-bench#592 · 1 comment ·
Maintainers usually reply within 1 day
-
Difficulty 4/5 3-5 days Newbie friendliness 55/100
sierra-research/tau2-bench#587 ·
Maintainers usually reply within 1 day
-
Difficulty 5/5 Over a week Newbie friendliness 25/100
sierra-research/tau2-bench#579 ·
Maintainers usually reply within 1 day
-
Difficulty 4/5 3-5 days Newbie friendliness 49/100
sierra-research/tau2-bench#574 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
sierra-research/tau2-bench#560 ·
Maintainers usually reply within 1 day
-
Difficulty 4/5 3-5 days Newbie friendliness 54/100
sierra-research/tau2-bench#559 ·
Maintainers usually reply within 1 day
-
Difficulty 4/5 3-5 days Newbie friendliness 54/100
sierra-research/tau2-bench#545 ·
Maintainers usually reply within 1 day
-
Difficulty 4/5 3-5 days Newbie friendliness 35/100
sierra-research/tau2-bench#543 ·
Maintainers usually reply within 1 day
-
Difficulty 4/5 3-5 days Newbie friendliness 35/100
sierra-research/tau2-bench#541 ·
Maintainers usually reply within 1 day
-
Run-to-run noise floor of the published baselines and leaderboard submissions, computed from the released trajectory filesMay be free again @Universeyi claimed this 25 days ago, and no pull request is open. Open
Difficulty 5/5 Over a week Newbie friendliness 35/100
sierra-research/tau2-bench#540 · 5 comments ·
Maintainers usually reply within 1 day
-
Difficulty 3/5 1-2 days Newbie friendliness 42/100
sierra-research/tau2-bench#530 ·
Maintainers usually reply within 1 day
-
Difficulty 5/5 Over a week Newbie friendliness 20/100
sierra-research/tau2-bench#497 ·
Maintainers usually reply within 1 day
-
Difficulty 4/5 3-5 days Newbie friendliness 48/100
sierra-research/tau2-bench#496 ·
Maintainers usually reply within 1 day
-
Difficulty 3/5 1-2 days Newbie friendliness 55/100
sierra-research/tau2-bench#495 ·
Maintainers usually reply within 1 day
-
Difficulty 4/5 3-5 days Newbie friendliness 49/100
sierra-research/tau2-bench#494 ·
Maintainers usually reply within 1 day
-
[telecom] Fixed persona ages conflict with customer DOB and can induce fabricated identity dataOpen
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
sierra-research/tau2-bench#492 ·
Maintainers usually reply within 1 day
-
Difficulty 5/5 Over a week Newbie friendliness 20/100
sierra-research/tau2-bench#490 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
sierra-research/tau2-bench#487 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 55/100
sierra-research/tau2-bench#472 · 1 comment · 1 reaction ·
Maintainers usually reply within 1 day
-
Telecom scores 1.0 for a run that suspends an uninvolved customer's lineMay be free again A pull request for this issue was closed without being merged. Open
Difficulty 5/5 Over a week Newbie friendliness 35/100
sierra-research/tau2-bench#459 ·
Maintainers usually reply within 1 day
-
Difficulty 5/5 Over a week Newbie friendliness 35/100
sierra-research/tau2-bench#439 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 62/100
sierra-research/tau2-bench#438 · 1 comment ·
Maintainers usually reply within 1 day
-
Difficulty 4/5 3-5 days Newbie friendliness 48/100
sierra-research/tau2-bench#436 ·
Maintainers usually reply within 1 day
-
Difficulty 1/5 1-3 hours Newbie friendliness 72/100
sierra-research/tau2-bench#435 ·
Maintainers usually reply within 1 day
-
Difficulty 4/5 3-5 days Newbie friendliness 48/100
sierra-research/tau2-bench#432 ·
Maintainers usually reply within 1 day
-
Fix Mei Kovacs known_info to use name instead of user_id in retail tasksMay be free again A pull request for this issue was closed without being merged. Open
Difficulty 1/5 Under an hour Newbie friendliness 35/100
sierra-research/tau2-bench#337 · 1 comment ·
Maintainers usually reply within 1 day
-
Difficulty 4/5 3-5 days Newbie friendliness 45/100
sierra-research/tau2-bench#327 · 1 comment ·
Maintainers usually reply within 1 day
-
Several retail tasks may have an unclear contract around helper read actions and rewarded successOpen
Difficulty 4/5 1-2 days Newbie friendliness 38/100
sierra-research/tau2-bench#326 · 1 comment ·
Maintainers usually reply within 1 day
-
Difficulty 4/5 1-2 days Newbie friendliness 46/100
sierra-research/tau2-bench#325 · 1 comment ·
Maintainers usually reply within 1 day
-
Difficulty 4/5 3-5 days Newbie friendliness 48/100
sierra-research/tau2-bench#321 · 1 comment ·
Maintainers usually reply within 1 day
-
Difficulty 4/5 1-2 days Newbie friendliness 48/100
sierra-research/tau2-bench#320 · 1 comment ·
Maintainers usually reply within 1 day
-
Retail task 41 / T41: DB oracle hardcodes PayPal even though the user selected credit_card_9503061Open
Difficulty 4/5 3-5 days Newbie friendliness 47/100
sierra-research/tau2-bench#319 · 1 comment ·
Maintainers usually reply within 1 day
-
Difficulty 3/5 1-2 days Newbie friendliness 55/100
sierra-research/tau2-bench#316 · 2 comments ·
Maintainers usually reply within 1 day
-
Difficulty 4/5 1-2 days Newbie friendliness 48/100
sierra-research/tau2-bench#298 ·
Maintainers usually reply within 1 day
-
Difficulty 4/5 3-5 days Newbie friendliness 54/100
sierra-research/tau2-bench#241 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 70/100
sierra-research/tau2-bench#237 · 2 comments ·
Maintainers usually reply within 1 day
-
Difficulty 4/5 3-5 days Newbie friendliness 35/100
sierra-research/tau2-bench#224 · 5 comments ·
Maintainers usually reply within 1 day
-
Difficulty 4/5 1-2 days Newbie friendliness 35/100
sierra-research/tau2-bench#211 · 1 comment ·
Maintainers usually reply within 1 day
-
Difficulty 1/5 1-3 hours Newbie friendliness 55/100
sierra-research/tau2-bench#182 · 1 reaction ·
Maintainers usually reply within 1 day
-
[Bug Report] Task 35 airline: User simulator introduces extra passenger not in task instructionsMay be free again A pull request for this issue was closed without being merged. Open
Difficulty 3/5 1-2 days Newbie friendliness 35/100
sierra-research/tau2-bench#172 · 1 comment ·
Maintainers usually reply within 1 day
-
Difficulty 5/5 Over a week Newbie friendliness 20/100
sierra-research/tau2-bench#167 · 1 comment · 1 reaction ·
Maintainers usually reply within 1 day
-
Difficulty 3/5 1-2 days Newbie friendliness 48/100
sierra-research/tau2-bench#156 · 2 reactions ·
Maintainers usually reply within 1 day
-
Difficulty 5/5 Over a week Newbie friendliness 25/100
sierra-research/tau2-bench#150 · 2 reactions ·
Maintainers usually reply within 1 day
-
RFC #2: Task Semantics & Evaluation for Tau3May be free again @victorbarres claimed this 285 days ago, and no pull request is open. Opendesign rfc
sierra-research/tau2-bench#129 · 1 assignee ·
Maintainers usually reply within 1 day
-
enhancement good first issue
Difficulty 5/5 Over a week Newbie friendliness 20/100
sierra-research/tau2-bench#127 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 55/100
sierra-research/tau2-bench#123 ·
Maintainers usually reply within 1 day
-
Retail domain evaluation crashMay be free again A pull request for this issue was closed without being merged. Openenhancement question
Difficulty 4/5 3-5 days Newbie friendliness 35/100
sierra-research/tau2-bench#115 ·
Maintainers usually reply within 1 day
Showing the newest 100
This page lists what was indexed most recently. Advanced filter has the whole inventory, narrowed by language, difficulty and how long a task takes.