{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.08292", "kind": "paper", "url": "https://arxiv.org/abs/2609.08292"}], "authors": ["Xilin Wang", "Guoxi Zhang", "Hongming Xu", "Zhuofan Zhang", "Tianxu Wang", "Lifeng Fan"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.08292", "source_url": "https://arxiv.org/abs/2609.08292"}, "categories": ["Robotics & Embodied AI", "cs.RO"], "description": {"en": "EvoNav-Bench evaluates lifelong navigation agents in evolving environments built on ProcTHOR, with environment modifications between tasks."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.08292", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.08292", "title": "EvoNav-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Beijing Institute for General Artificial Intelligence", "Tsinghua University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2609.08292", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2609.08292", "source_url": "https://openalex.org/W7212079153"}, "key": "claire-radar:2609.08292", "modality": null, "name": "EvoNav-Bench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "true", "origin_record_id": "bm_evonav-bench_6370db2f", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "61d6a59585c1d9a0bf6e7891884c45513634ad0904da34da4a00ffe55100d7d7", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-10T00:52:28.558291Z", "source_url": "https://arxiv.org/abs/2609.08292"}, "publisher": null, "released": "2026-09-08", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.08292", "source_url": "https://arxiv.org/abs/2609.08292"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-08292", "source": "claire_radar", "source_benchmark_id": "2609.08292", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Robotics & Embodied AI"], "area": "Robotics & Embodied AI", "attention": {"asOf": "2026-09-09", "attemptedAt": "2026-09-09T12:31:07.558041Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.08292", "observedAt": "2026-09-08T01:38:09.842216Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-09-09T12:31:07.558041Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Embodied navigation in evolving environments is a specialized subfield, and the lack of direct artifact links may reduce early attention.", "score": 28}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-10T00:52:28.558291Z", "inputHash": "a380cf4a1bb5dd1bea28a114a3ade5992a17354adb2de9e7e61b908572be4436", "model": "deepseek-v4-pro"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "In this paper, we present EvoNav-Bench, which extends the GOAT-Bench style LN formulation in the context of evolving environments.", "canonicalNameSource": "abstract", "decisionReason": "EvoNav-Bench is a formally named benchmark extending an existing formulation with a defined evaluation setup and comparable baselines.", "evaluationEvidence": {"reuse": "Built on the ProcTHOR framework, EvoNav-Bench introduces environment modifications between navigation tasks, making prior experience useful but not fully reliable.", "scoring": "Using EvoNav-Bench, we benchmark three recent methods that build and reuse scene representations for navigation. We also compare three simple heuristic strategies for handling environment evolution: Frontier-Update, Fail-then-Update, and Stage-Reset. Our results show that existing methods are brittle under environment evolution, while the heuristic strategies enable a controlled analysis of how agents can adapt to scene changes and mitigate their impact.", "task": "EvoNav-Bench introduces environment modifications between navigation tasks, making prior experience useful but not fully reliable. This design enables controlled evaluation of how environment evolution affects LN agents that reuse prior scene observations."}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-10T00:52:28.558291Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "EvoNav-Bench evaluates lifelong navigation agents in evolving environments built on ProcTHOR, with environment modifications between tasks.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "In this paper, we present EvoNav-Bench, which extends the GOAT-Bench style LN formulation in the context of evolving environments."}, "familyId": "bmf_f2bef5a44ff3", "firstSeenAt": "2026-09-09", "heat": null, "id": "bm_evonav-bench_6370db2f", "indexedAt": "2026-09-09T06:18:29.794093Z", "industrySectors": ["Robotics"], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.08292", "pdf": "https://arxiv.org/pdf/2609.08292", "project": null, "report": "https://arxiv.org/abs/2609.08292"}, "metrics": [], "motivation": "Lifelong navigation (LN) requires an embodied agent to solve a sequence of navigation subtasks in the same environment.", "name": "EvoNav-Bench", "oneLine": "EvoNav-Bench evaluates lifelong navigation agents in evolving environments built on ProcTHOR, with environment modifications between tasks.", "paperTitle": "EvoNav-Bench: Benchmarking Lifelong Navigation in Evolving Environments", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.08292", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-09T06:18:29.794093Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.0, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}, "90d": {"confidence": "Low", "coverage": 0.0, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}, "today": {"confidence": "Low", "coverage": 0.0, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": 1, "historyDate": "2026-09-08", "rank": null, "score": null, "windowDays": 1}, "level": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "llmAttentionForecast": {"maxContribution": 0.25, "percentile": 0.0, "role": "bonus", "value": 0}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": 0}, "method": "attention-ranking-v13", "rank": null, "score": 0}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-09-08", "source": {"authors": ["Xilin Wang", "Guoxi Zhang", "Hongming Xu", "Zhuofan Zhang", "Tianxu Wang", "Lifeng Fan"], "categories": ["cs.RO"], "id": "2609.08292", "title": "EvoNav-Bench: Benchmarking Lifelong Navigation in Evolving Environments", "type": "arxiv", "url": "https://arxiv.org/abs/2609.08292"}, "sourceUpdatedAt": "2026-09-08T06:05:05Z", "topics": ["cs.RO"], "venueAttempts": [], "whyItMatters": "It reveals brittleness of existing navigation methods when environments change and provides a basis for testing adaptation strategies."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
