Files
liqiang b119135836
Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
ai-agent-book 精选快照(<2MB 代码与文档,来自 github.com/bojieli/ai-agent-book)
2026-08-20 13:12:50 +00:00

100 lines
3.6 KiB
JSON

{
"schema_version": 1,
"experiment": "7-1",
"status": "complete_bounded_campaign",
"generated_at_utc": "2026-08-02T09:15:41.750622Z",
"source": {
"repository": "https://github.com/sierra-research/tau2-bench",
"git_commit": "8d005b0e5b9e4af0bc055886fa7f95fc86d1710e"
},
"configuration": {
"domain": "telecom",
"agent_model": "openrouter/openai/gpt-4.1-mini",
"user_simulator_model": "openrouter/openai/gpt-4.1-mini",
"agent_temperature": 0.0,
"user_simulator_temperature": 0.0,
"seed": 300,
"num_tasks": 5,
"num_trials": 1,
"max_concurrency": 3
},
"summary": {
"tasks_completed": 5,
"tasks_passed": 4,
"tasks_failed": 1,
"average_reward": 0.8,
"pass_at_1": 0.8,
"provider_errors": 0,
"termination_reasons": {
"user_stop": 5
},
"agent_cost_usd": 0.112672,
"user_simulator_cost_usd": 0.0386396,
"total_cost_usd": 0.1513116
},
"task_outcomes": [
{
"task_id": "[mobile_data_issue]airplane_mode_on|user_abroad_roaming_enabled_off[PERSONA:None]",
"reward": 1.0,
"duration_seconds": 45.657303331419826,
"termination_reason": "user_stop"
},
{
"task_id": "[mobile_data_issue]airplane_mode_on|data_mode_off[PERSONA:None]",
"reward": 1.0,
"duration_seconds": 55.878302780911326,
"termination_reason": "user_stop"
},
{
"task_id": "[mobile_data_issue]data_mode_off|data_usage_exceeded[PERSONA:None]",
"reward": 1.0,
"duration_seconds": 64.09661028999835,
"termination_reason": "user_stop"
},
{
"task_id": "[mobile_data_issue]data_usage_exceeded|user_abroad_roaming_enabled_off[PERSONA:Easy]",
"reward": 1.0,
"duration_seconds": 45.86838342156261,
"termination_reason": "user_stop"
},
{
"task_id": "[mobile_data_issue]data_saver_mode_on|data_usage_exceeded[PERSONA:Easy]",
"reward": 0.0,
"duration_seconds": 96.15721444413066,
"termination_reason": "user_stop"
}
],
"failed_task_analysis": {
"task_id": "[mobile_data_issue]data_saver_mode_on|data_usage_exceeded[PERSONA:Easy]",
"messages": 71,
"customer_phone": "555-123-2002",
"incorrect_line_id": "L1001",
"incorrect_line_phone": "555-123-2001",
"required_line_id": "L1002",
"observed_wrong_line_usage_gb": 3.2,
"observed_wrong_line_limit_gb": 5.0,
"required_refuel_gb": 2.0,
"passed_action_checks": [
"toggle_data_saver_mode"
],
"failed_action_checks": [
"refuel_data"
],
"failed_environment_assertions": [
"assert_mobile_data_status",
"assert_internet_speed",
"assert_data_refueling_amount"
],
"root_cause": "The Agent failed to map the supplied phone number to its matching line, continued after tool output exposed the mismatch, and therefore missed the required data-refuel path.",
"secondary_policy_defect": "The Agent emitted get_customer_by_phone and get_customer_by_name in one turn despite the one-tool-call-at-a-time telecom policy."
},
"upstream_public_verification": {
"command": ".venv/bin/tau2 submit verify-trajs ../tau2-bench-eval/validation/runs/exp7-1-openrouter-gpt41mini-telecom-20260802-v1/trajectories.json",
"format_validation": "passed",
"trial_count_validation": "passed",
"task_validation": "failed_expected_bounded_campaign",
"task_validation_reason": "The verifier requires full-domain leaderboard coverage; this manuscript experiment deliberately runs five telecom tasks."
},
"acceptance_boundary": "Complete for the manuscript's bounded five-task Experiment 7-1 campaign; not a full-domain tau2-bench leaderboard submission."
}