DETOUR: An Interactive Benchmark for Dual-Agent Search and Reasoning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917236834304000 |
|---|---|
| author | Siyan, Li Deshpande, Darshan Kannappan, Anand Qian, Rebecca |
| author_facet | Siyan, Li Deshpande, Darshan Kannappan, Anand Qian, Rebecca |
| contents | When recalling information in conversation, people often arrive at the recollection after multiple turns. However, existing benchmarks for evaluating agent capabilities in such tip-of-the-tongue search processes are restricted to single-turn settings. To more realistically simulate tip-of-the-tongue search, we introduce Dual-agent based Evaluation Through Obscure Under-specified Retrieval (DETOUR), a dual-agent evaluation benchmark containing 1,011 prompts. The benchmark design involves a Primary Agent, which is the subject of evaluation, tasked with identifying the recollected entity through querying a Memory Agent that is held consistent across evaluations. Our results indicate that current state-of-the-art models still struggle with our benchmark, only achieving 36% accuracy when evaluated on all modalities (text, image, audio, and video), highlighting the importance of enhancing capabilities in underspecified scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_00352 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DETOUR: An Interactive Benchmark for Dual-Agent Search and Reasoning Siyan, Li Deshpande, Darshan Kannappan, Anand Qian, Rebecca Computation and Language When recalling information in conversation, people often arrive at the recollection after multiple turns. However, existing benchmarks for evaluating agent capabilities in such tip-of-the-tongue search processes are restricted to single-turn settings. To more realistically simulate tip-of-the-tongue search, we introduce Dual-agent based Evaluation Through Obscure Under-specified Retrieval (DETOUR), a dual-agent evaluation benchmark containing 1,011 prompts. The benchmark design involves a Primary Agent, which is the subject of evaluation, tasked with identifying the recollected entity through querying a Memory Agent that is held consistent across evaluations. Our results indicate that current state-of-the-art models still struggle with our benchmark, only achieving 36% accuracy when evaluated on all modalities (text, image, audio, and video), highlighting the importance of enhancing capabilities in underspecified scenarios. |
| title | DETOUR: An Interactive Benchmark for Dual-Agent Search and Reasoning |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2602.00352 |