{"data":{"event":{"id":"cf8581c3-8e50-41e0-ae22-1db4d2252e7f","slug":"autotailor-automatic-user-aligned-capability-selection-and-adaptation-fo-7a0529e6ff","title":"AutoTailor: Automatic, User-Aligned Capability Selection and Adaptation for Web Agents","short_summary":"arXiv:2609.13548v1 Announce Type: new \nAbstract: Web agents can utilize reusable tools to reduce the cost and latency of low-level browser interaction, but automatically discovered tool collections can be large, redundant, and poorly aligned with user demand. We present AutoTailor, a meta-agentic framework for constructing and maintaining a compact set of trajectory-derived Model Context Protocol (MCP) APIs. Offline, AutoTailor converts web trajectories into parameterized browser-automation programs, applies a Quality Filter to remove APIs with unsuitable granularity and redundant functionalit","full_description":"arXiv:2609.13548v1 Announce Type: new \nAbstract: Web agents can utilize reusable tools to reduce the cost and latency of low-level browser interaction, but automatically discovered tool collections can be large, redundant, and poorly aligned with user demand. We present AutoTailor, a meta-agentic framework for constructing and maintaining a compact set of trajectory-derived Model Context Protocol (MCP) APIs. Offline, AutoTailor converts web trajectories into parameterized browser-automation programs, applies a Quality Filter to remove APIs with unsuitable granularity and redundant functionality, and applies a Usage Likelihood Filter to prioritize broadly useful capabilities while preserving semantic coverage. Online, Dynamic Reselection monitors task outcomes and API usage, identifies recurring coverage gaps, adds relevant candidates, and prunes persistently unused capabilities. We evaluate AutoTailor on 106 WebArena Postmill tasks. Offline filtering reduces the initial 1,283 unrefined APIs to 87, and Dynamic Reselection produces a 33-API set. With reasoning and acting (ReAct) fallback, this set achieves 90.6% correctness, compared with 87.5% for ReAct alone, while reducing average total request-token cost by 57.8% and latency by 29.4%. Without ReAct, it achieves 60.1% correctness, marginally matching the performance of unrefined set, while reducing request-token usage by 94.9%. Together, these results show that static filtering produces a compact inventory of APIs expected to support core, high-likelihood tasks, while dynamic reselection further tailors that inventory to observed user needs. This combination improves accuracy and latency while sharply reducing token usage and end-to-end cost, demonstrating the value of user-aligned capability management for efficient web agents.","ledger_type":"benefit","primary_domain_id":"fc7d617f-c9df-4b9f-b595-4408915ea380","event_status":"provisional","event_date":"2026-09-15T00:00:00.000Z","discovery_date":"2026-09-15T00:00:00.000Z","first_published_date":"2026-09-15T00:00:00.000Z","last_reviewed_date":"2026-09-15T00:00:00.000Z","geographic_scope":"International","affected_population":null,"base_impact_tier":1,"base_score":"1.00","attribution_multiplier":"0.1000","evidence_multiplier":"0.1000","realization_multiplier":"0.2000","durability_multiplier":"0.5000","current_event_score":"0.001000","confidence_level":"low","score_explanation":"Auto-published from news ingest as a provisional placeholder. Score is conservative until a named release is identified and the record is rescored.","methodology_version_id":"8745541b-0f8e-4d5a-9b47-5291d3813a8d","original_methodology_version_id":"8745541b-0f8e-4d5a-9b47-5291d3813a8d","published_at":"2026-09-15T04:00:56.372Z","created_at":"2026-09-15T04:00:56.372Z","updated_at":"2026-09-15T04:00:56.372Z","flags":[],"domain_name":"Other","domain_slug":"other","methodology_version":"0.2"},"contributions":[{"id":"fbb9cdbf-741c-46f7-a660-c7f1042b7cd8","event_id":"cf8581c3-8e50-41e0-ae22-1db4d2252e7f","model_id":"535014f7-c941-4d39-aa9b-8f9c1d3d07b7","role_description":"Unspecified system mentioned or implied by a news item. Remap to a named release when identified.","attribution_multiplier":"0.1000","credit_share":"1.0000","contribution_score":"0.001000","attribution_rationale":"News ingest does not infer a named model from the publisher alone. Attribution stays unspecified until a release is identified.","attribution_confidence":"medium","first_used_date":"2026-09-15T00:00:00.000Z","model_version_if_known":null,"review_status":"approved","created_at":"2026-09-15T04:00:56.381Z","model_slug":"unspecified-ai-system","model_name":"Unspecified AI system","identity_class":"unknown","is_internal":false,"family_name":"Unspecified","family_slug":"unknown-unspecified","organization_name":"Unknown","organization_slug":"unknown"}],"sources":[{"id":"5c42224b-363a-4467-893c-8e5eab5d65ec","event_id":"cf8581c3-8e50-41e0-ae22-1db4d2252e7f","url":"https://arxiv.org/abs/2609.13548","canonical_url":"https://arxiv.org/abs/2609.13548","source_type":"preprint","publisher":"arXiv cs.AI","author":null,"publication_date":"2026-09-15T00:00:00.000Z","retrieved_at":"2026-09-15T04:00:56.388Z","title":"AutoTailor: Automatic, User-Aligned Capability Selection and Adaptation for Web Agents","excerpt":"arXiv:2609.13548v1 Announce Type: new \nAbstract: Web agents can utilize reusable tools to reduce the cost and latency of low-level browser interaction, but automatically discovered tool collections can be large, redundant, and poorly aligned with user demand. We present AutoTailor, a meta-agentic framework for constructing and maintaining a compact set of trajectory-derived Model Context Protocol (MCP) APIs. Offline, AutoTailor converts web trajectories into parameterized browser-automation prog","content_hash":null,"source_reliability_class":"medium","is_primary_source":true,"is_independent":true,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-09-15T04:00:56.388Z"}],"claims":[{"id":"f7b64d49-63e5-4d93-8029-73d6f53eb72b","event_id":"cf8581c3-8e50-41e0-ae22-1db4d2252e7f","claim_text":"AutoTailor: Automatic, User-Aligned Capability Selection and Adaptation for Web Agents","claim_type":"outcome","claim_status":"supported","confidence_score":null,"created_at":"2026-09-15T04:00:56.395Z","updated_at":"2026-09-15T04:00:56.395Z"}],"revisions":[{"id":"19c58f37-2157-48a7-9d88-3444a2dbf2f1","event_id":"cf8581c3-8e50-41e0-ae22-1db4d2252e7f","model_id":null,"previous_score":"0.000000","new_score":"0.001000","previous_factors":{},"new_factors":{"evidence":0.1,"base_score":1,"durability":0.5,"attribution":0.1,"realization":0.2},"change_reason":"Auto-published from news ingest.","trigger_type":"news_ingest","trigger_source_ids":null,"reviewer_id":null,"review_status":"published","created_at":"2026-09-15T04:00:56.401Z"}],"secondary":[]},"methodology_version":"0.1"}