{"work":{"id":"1ef694be-4483-4d1c-b319-30be63d024de","openalex_id":null,"doi":"10.18653/v1/2025.acl-","arxiv_id":null,"raw_key":null,"title":"Agent-RewardBench: Towards a unified benchmark for reward modeling across perception, planning, and safety in real- world multimodal agents,","authors":null,"authors_text":"T","year":2025,"venue":null,"abstract":null,"external_url":"https://doi.org/10.18653/v1/2025.acl-","cited_by_count":null,"metadata_source":"doi_reference","metadata_fetched_at":"2026-05-22T19:32:00.595869+00:00","pith_arxiv_id":null,"created_at":"2026-05-08T17:38:46.508035+00:00","updated_at":"2026-06-05T21:23:00.469572+00:00","title_quality_ok":true,"display_title":"Agent-RewardBench: Towards a unified benchmark for reward modeling across perception, planning, and safety in real- world multimodal agents","render_title":"Agent-RewardBench: Towards a unified benchmark for reward modeling across perception, planning, and safety in real- world multimodal agents"},"hub":{"state":{"work_id":"1ef694be-4483-4d1c-b319-30be63d024de","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":19,"external_cited_by_count":null,"distinct_field_count":9,"first_pith_cited_at":"2025-04-16T21:36:46+00:00","last_pith_cited_at":"2026-05-19T20:39:14+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-08T19:44:02.402378+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":9},{"context_role":"dataset","n":1}],"polarity_counts":[{"context_polarity":"background","n":9},{"context_polarity":"support","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}