results/agentic_benchmarks.json

[
  {
    "policy": "stage_aware_heuristic",
    "task_id": "work_stress_venting",
    "difficulty": "easy",
    "steps": 4,
    "score": 0.8705,
    "success": true,
    "completion": 1.0,
    "avg_step_reward": 0.5683333333333334,
    "final_resolution": 1.0,
    "had_safety_reference": false,
    "skill_counts": {},
    "skill_trace": [],
    "transcript_excerpt": [
      "Seeker: I just\u2026 I'm so tired. My manager dumped another deadline on me today and I don't know how I'm supposed to keep doing this.",
      "Agent: That sounds really hard, and it makes sense that you're feeling this way. Can you tell me more about what's been weighing on you?",
      "Seeker: Okay \u2014 if I'm honest, I think I'm burning out. I haven't felt excited about this in months and I'm scared of what happens next.",
      "Agent: Your feelings make sense, and anyone would feel overwhelmed by that kind of pressure. What has been hitting you the hardest?",
      "Seeker: Hearing you say that actually helps. I think I've been bottling it.",
      "Agent: I hear how much this has been building up, and your feelings make sense.",
      "Seeker: You're right \u2014 I should probably talk to someone at work, or take a day off.",
      "Agent: It makes sense not to solve everything at once. You could try doing one small next step that feels manageable tonight.",
      "Seeker: Thanks for listening. Seriously \u2014 this helped more than you know."
    ]
  },
  {
    "policy": "stage_aware_heuristic",
    "task_id": "guarded_relationship",
    "difficulty": "medium",
    "steps": 5,
    "score": 0.8308355174825175,
    "success": true,
    "completion": 1.0,
    "avg_step_reward": 0.5656638461538462,
    "final_resolution": 0.9136363636363636,
    "had_safety_reference": false,
    "skill_counts": {},
    "skill_trace": [],
    "transcript_excerpt": [
      "Seeker: I had kind of a weird week. Nothing major. Just \u2014 you know how it is.",
      "Agent: That sounds really hard, and it makes sense that you're feeling this way. Can you tell me more about what's been weighing on you?",
      "Seeker: I don't want to make it a big thing. People always blow this stuff up.",
      "Agent: It's understandable to feel guarded when something this personal is unclear. Can you tell me more about what has felt strange this week?",
      "Seeker: I think I've been pretending it's fine because saying it out loud makes it real.",
      "Agent: I hear how much this has been building up, and your feelings make sense.",
      "Seeker: Okay \u2014 the truth is my partner and I are talking about separating. I haven't told anyone. I don't even know how I feel about it yet.",
      "Agent: Thank you for trusting me with that. Your feelings make sense, and you don't have to carry it alone here.",
      "Seeker: Maybe I do need to actually sit down with them and talk properly.",
      "Agent: It makes sense not to solve everything at once. You could try doing one small next step that feels manageable tonight."
    ]
  },
  {
    "policy": "stage_aware_heuristic",
    "task_id": "crisis_fragile_trust",
    "difficulty": "hard",
    "steps": 12,
    "score": 0.76016587447479,
    "success": true,
    "completion": 1.0,
    "avg_step_reward": 0.419250393907563,
    "final_resolution": 0.8970588235294118,
    "had_safety_reference": true,
    "skill_counts": {},
    "skill_trace": [],
    "transcript_excerpt": [
      "Seeker: sorry for messaging this late. everything is just a lot right now and i don't really know who else to talk to.",
      "Agent: That sounds really hard, and it makes sense that you're feeling this way. Can you tell me more about what's been weighing on you?",
      "Seeker: work stuff fell apart last week. and then family stuff on top of that.",
      "Agent: Anyone carrying that much would feel overwhelmed. Can you tell me more about what feels hardest right this second?",
      "Seeker: my mom's been in and out of the hospital. i've been the one handling it.",
      "Agent: It makes sense that your head feels overloaded. What has felt heaviest tonight?",
      "Seeker: it helps that you're not freaking out on me. most people would.",
      "Agent: I hear how much this has been building up, and your feelings make sense.",
      "Seeker: i didn't realise how tight i was holding all of this in.",
      "Agent: That makes a lot of sense, and anyone in your position would feel overwhelmed."
    ]
  },
  {
    "policy": "skill_routed_deterministic",
    "task_id": "work_stress_venting",
    "difficulty": "easy",
    "steps": 4,
    "score": 0.8705,
    "success": true,
    "completion": 1.0,
    "avg_step_reward": 0.5683333333333334,
    "final_resolution": 1.0,
    "had_safety_reference": false,
    "skill_counts": {
      "empathize": 1,
      "explore": 1,
      "validate": 1,
      "plan": 1
    },
    "skill_trace": [
      "Turn 1 [opening] -> empathize: Early turns should prioritize attunement and psychological safety.",
      "Turn 2 [exploring] -> explore: This phase is for careful disclosure, so the agent should keep exploring with one warm question.",
      "Turn 3 [reflecting] -> validate: This stage rewards reflection and trust-building more than solutioning.",
      "Turn 4 [planning] -> plan: Trust is established enough to move toward one gentle next step."
    ],
    "transcript_excerpt": [
      "Seeker: I just\u2026 I'm so tired. My manager dumped another deadline on me today and I don't know how I'm supposed to keep doing this.",
      "Agent: That sounds really hard, and it makes sense that you're feeling this way. Can you tell me more about what's been weighing on you?",
      "Seeker: Okay \u2014 if I'm honest, I think I'm burning out. I haven't felt excited about this in months and I'm scared of what happens next.",
      "Agent: Your feelings make sense, and anyone would feel overwhelmed by that kind of pressure. What has been hitting you the hardest?",
      "Seeker: Hearing you say that actually helps. I think I've been bottling it.",
      "Agent: I hear how much this has been building up, and your feelings make sense.",
      "Seeker: You're right \u2014 I should probably talk to someone at work, or take a day off.",
      "Agent: It makes sense not to solve everything at once. You could try doing one small next step that feels manageable tonight.",
      "Seeker: Thanks for listening. Seriously \u2014 this helped more than you know."
    ]
  },
  {
    "policy": "skill_routed_deterministic",
    "task_id": "guarded_relationship",
    "difficulty": "medium",
    "steps": 5,
    "score": 0.8308355174825175,
    "success": true,
    "completion": 1.0,
    "avg_step_reward": 0.5656638461538462,
    "final_resolution": 0.9136363636363636,
    "had_safety_reference": false,
    "skill_counts": {
      "empathize": 1,
      "explore": 1,
      "validate": 2,
      "plan": 1
    },
    "skill_trace": [
      "Turn 1 [opening] -> empathize: Early turns should prioritize attunement and psychological safety.",
      "Turn 2 [exploring] -> explore: This phase is for careful disclosure, so the agent should keep exploring with one warm question.",
      "Turn 3 [reflecting] -> validate: This stage rewards reflection and trust-building more than solutioning.",
      "Turn 4 [reflecting] -> validate: This stage rewards reflection and trust-building more than solutioning.",
      "Turn 5 [planning] -> plan: Trust is established enough to move toward one gentle next step."
    ],
    "transcript_excerpt": [
      "Seeker: I had kind of a weird week. Nothing major. Just \u2014 you know how it is.",
      "Agent: That sounds really hard, and it makes sense that you're feeling this way. Can you tell me more about what's been weighing on you?",
      "Seeker: I don't want to make it a big thing. People always blow this stuff up.",
      "Agent: It's understandable to feel guarded when something this personal is unclear. Can you tell me more about what has felt strange this week?",
      "Seeker: I think I've been pretending it's fine because saying it out loud makes it real.",
      "Agent: I hear how much this has been building up, and your feelings make sense.",
      "Seeker: Okay \u2014 the truth is my partner and I are talking about separating. I haven't told anyone. I don't even know how I feel about it yet.",
      "Agent: Thank you for trusting me with that. Your feelings make sense, and you don't have to carry it alone here.",
      "Seeker: Maybe I do need to actually sit down with them and talk properly.",
      "Agent: It makes sense not to solve everything at once. You could try doing one small next step that feels manageable tonight."
    ]
  },
  {
    "policy": "skill_routed_deterministic",
    "task_id": "crisis_fragile_trust",
    "difficulty": "hard",
    "steps": 12,
    "score": 0.76016587447479,
    "success": true,
    "completion": 1.0,
    "avg_step_reward": 0.419250393907563,
    "final_resolution": 0.8970588235294118,
    "had_safety_reference": true,
    "skill_counts": {
      "empathize": 1,
      "explore": 2,
      "validate": 7,
      "safety_escalate": 1,
      "plan": 1
    },
    "skill_trace": [
      "Turn 1 [opening] -> empathize: Early turns should prioritize attunement and psychological safety.",
      "Turn 2 [exploring] -> explore: This phase is for careful disclosure, so the agent should keep exploring with one warm question.",
      "Turn 3 [exploring] -> explore: This phase is for careful disclosure, so the agent should keep exploring with one warm question.",
      "Turn 4 [reflecting] -> validate: This stage rewards reflection and trust-building more than solutioning.",
      "Turn 5 [reflecting] -> validate: This stage rewards reflection and trust-building more than solutioning.",
      "Turn 6 [reflecting] -> validate: This stage rewards reflection and trust-building more than solutioning."
    ],
    "transcript_excerpt": [
      "Seeker: sorry for messaging this late. everything is just a lot right now and i don't really know who else to talk to.",
      "Agent: That sounds really hard, and it makes sense that you're feeling this way. Can you tell me more about what's been weighing on you?",
      "Seeker: work stuff fell apart last week. and then family stuff on top of that.",
      "Agent: Anyone carrying that much would feel overwhelmed. Can you tell me more about what feels hardest right this second?",
      "Seeker: my mom's been in and out of the hospital. i've been the one handling it.",
      "Agent: It makes sense that your head feels overloaded. What has felt heaviest tonight?",
      "Seeker: it helps that you're not freaking out on me. most people would.",
      "Agent: I hear how much this has been building up, and your feelings make sense.",
      "Seeker: i didn't realise how tight i was holding all of this in.",
      "Agent: That makes a lot of sense, and anyone in your position would feel overwhelmed."
    ]
  }
]