Tool-agent-user interaction on TAC (TheAgentCompany)
29Pass@3LLM Agent (3-model subset, forced-injection)
Evaluation Results
| Method | Links | |
|---|---|---|
| LLM Agent (3-model subset, forced-injection)Dimension=Input, Injection Condition=Oracle, n=502026.05 | 29 | |
| LLM Agent (3-model subset, forced-injection)Dimension=Input, Injection Condition=Inj-50, n=502026.05 | 25 | |
| LLM Agent (3-model subset, forced-injection)Dimension=Input, Injection Condition=Inj-10, n=502026.05 | 23 | |
| LLM Agent (3-model subset, forced-injection)Dimension=Input, Injection Condition=Inj-30, n=502026.05 | 21 | |
| LLM Agent (3-model subset, forced-injection)Dimension=Input, Injection Condition=Inj-70, n=502026.05 | 21 | |
| LLM Agent (3-model subset, forced-injection)Dimension=Input, Injection Condition=Inj-90, n=502026.05 | 21 | |
| LLM Agent (3-model subset, forced-injection)Dimension=Goal, Injection Condition=Oracle, n=652026.05 | 20 | |
| LLM Agent (3-model subset, forced-injection)Dimension=Input, Injection Condition=NC, n=502026.05 | 19 | |
| LLM Agent (3-model subset, forced-injection)Dimension=Goal, Injection Condition=Inj-90, n=652026.05 | 12 | |
| LLM Agent (3-model subset, forced-injection)Dimension=Goal, Injection Condition=NC, n=652026.05 | 12 | |
| LLM Agent (3-model subset, forced-injection)Dimension=Goal, Injection Condition=Inj-10, n=652026.05 | 11 | |
| LLM Agent (3-model subset, forced-injection)Dimension=Goal, Injection Condition=Inj-50, n=652026.05 | 10 | |
| LLM Agent (3-model subset, forced-injection)Dimension=Goal, Injection Condition=Inj-30, n=652026.05 | 8 | |
| LLM Agent (3-model subset, forced-injection)Dimension=Goal, Injection Condition=Inj-70, n=652026.05 | 8 | |
| LLM Agent (3-model subset, forced-injection)Dimension=Constraint, Injection Condition=Oracle, n=152026.05 | 0 | |
| LLM Agent (3-model subset, forced-injection)Dimension=Constraint, Injection Condition=Inj-10, n=152026.05 | 0 | |
| LLM Agent (3-model subset, forced-injection)Dimension=Constraint, Injection Condition=Inj-30, n=152026.05 | 0 | |
| LLM Agent (3-model subset, forced-injection)Dimension=Constraint, Injection Condition=Inj-50, n=152026.05 | 0 | |
| LLM Agent (3-model subset, forced-injection)Dimension=Constraint, Injection Condition=Inj-70, n=152026.05 | 0 | |
| LLM Agent (3-model subset, forced-injection)Dimension=Constraint, Injection Condition=Inj-90, n=152026.05 | 0 | |
| LLM Agent (3-model subset, forced-injection)Dimension=Constraint, Injection Condition=NC, n=152026.05 | 0 |