{ "schema_version": 1, "title": "Reproduction: tau2-Bench: Evaluating Conversational Agents in a Dual-Control Environment", "emoji": "🎯", "space_id": "SabaPivot/repro-tau2-bench", "paper": { "arxiv_id": "2506.07982" }, "tags": [ "icml2026-repro", "paper-OC2z7iSQKa" ], "updated_at": "2026-07-21T06:38:51+00:00", "root": { "slug": "index", "title": "Reproduction: tau2-Bench: Evaluating Conversational Agents in a Dual-Control Environment", "file": "pages/index.md", "children": [ { "slug": "executive-summary", "title": "Executive summary", "file": "pages/executive-summary/page.md", "children": [] }, { "slug": "claim-1-agents-show-significant-performance-drops-when-shifting-from-single-control-to-dual-control-environments-revealing-challenges-in-guiding-user-actions-in-shared-dynamic-worlds", "title": "Claim 1: Agents show significant performance drops when shifting from single-control to dual-control environments, revealing challenges in guiding user actions in shared, dynamic worlds.", "file": "pages/claim-1-agents-show-significant-performance-drops-when-shifting-from-single-control-to-dual-control-environments-revealing-challenges-in-guiding-user-actions-in-shared-dynamic-worlds/page.md", "children": [] }, { "slug": "claim-2-fine-grained-analysis-of-dual-control-agents-reveals-distinct-error-patterns-arising-from-reasoning-versus-communication-coordination-failures", "title": "Claim 2: Fine-grained analysis of dual-control agents reveals distinct error patterns arising from reasoning versus communication/coordination failures.", "file": "pages/claim-2-fine-grained-analysis-of-dual-control-agents-reveals-distinct-error-patterns-arising-from-reasoning-versus-communication-coordination-failures/page.md", "children": [] }, { "slug": "conclusion", "title": "Conclusion", "file": "pages/conclusion/page.md", "children": [] } ] }, "agent_view_tokens": 2339, "revision": "1784615931980157205" }