Spaces:
Running
Running
| { | |
| "schema_version": 1, | |
| "title": "Repro - $\\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment", | |
| "emoji": "\ud83d\udd2c", | |
| "space_id": "bertfil/OC2z7iSQKa", | |
| "paper": { | |
| "arxiv_id": "2506.07982", | |
| "openreview_id": "OC2z7iSQKa", | |
| "title": "$\\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment", | |
| "url": "https://arxiv.org/abs/2506.07982" | |
| }, | |
| "tags": [ | |
| "icml2026-repro", | |
| "paper-OC2z7iSQKa" | |
| ], | |
| "updated_at": "2026-07-20T03:52:39+00:00", | |
| "root": { | |
| "slug": "index", | |
| "title": "Repro - $\\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment", | |
| "file": "pages/index.md", | |
| "children": [ | |
| { | |
| "slug": "00-scored-evidence-summary", | |
| "title": "00 - Scored evidence summary", | |
| "file": "pages/00-scored-evidence-summary/page.md", | |
| "children": [] | |
| }, | |
| { | |
| "slug": "claim-1-tau2-bench-introduces-a-telecom-dual-control-envir", | |
| "title": "Claim 1 - tau2-bench introduces a telecom dual-control environment whe\u2026", | |
| "file": "pages/claim-1-tau2-bench-introduces-a-telecom-dual-control-envir/page.md", | |
| "children": [] | |
| }, | |
| { | |
| "slug": "claim-2-the-telecom-domain-is-modeled-with-separate-agent", | |
| "title": "Claim 2 - The telecom domain is modeled with separate agent and user d\u2026", | |
| "file": "pages/claim-2-the-telecom-domain-is-modeled-with-separate-agent/page.md", | |
| "children": [] | |
| }, | |
| { | |
| "slug": "claim-3-the-benchmark-uses-a-compositional-task-generator", | |
| "title": "Claim 3 - The benchmark uses a compositional task generator that creat\u2026", | |
| "file": "pages/claim-3-the-benchmark-uses-a-compositional-task-generator/page.md", | |
| "children": [] | |
| }, | |
| { | |
| "slug": "claim-4-agents-show-lower-pass-1-in-default-dual-control-t", | |
| "title": "Claim 4 - Agents show lower pass@1 in default dual-control telecom ope\u2026", | |
| "file": "pages/claim-4-agents-show-lower-pass-1-in-default-dual-control-t/page.md", | |
| "children": [] | |
| }, | |
| { | |
| "slug": "claim-5-telecom-performance-declines-as-the-number-of-requ", | |
| "title": "Claim 5 - Telecom performance declines as the number of required actio\u2026", | |
| "file": "pages/claim-5-telecom-performance-declines-as-the-number-of-requ/page.md", | |
| "children": [] | |
| }, | |
| { | |
| "slug": "reproduction-protocol-and-provenance", | |
| "title": "Reproduction protocol and provenance", | |
| "file": "pages/reproduction-protocol-and-provenance/page.md", | |
| "children": [] | |
| }, | |
| { | |
| "slug": "conclusion", | |
| "title": "Conclusion", | |
| "file": "pages/conclusion/page.md", | |
| "children": [] | |
| } | |
| ] | |
| }, | |
| "agent_view_tokens": 5845, | |
| "revision": "1784519559735129100" | |
| } |