Source: arxiv | Overall 6.6/10 | Corroboration: 1
Signal 9.4
Novelty 5.1
Impact 2.0
Confidence 9.5
Actionability 6.5
Summary: arXiv:2607.08691v1 Announce Type: cross Abstract: Repository-level code generation requires implementing target functions while accounting for complex cross-file dependencies and.
- What happened: We propose ProjAgent, a repository-level code generation system that introduces procedural similarity as an explicit retrieval signal.
- Why it matters: arXiv:2607.08691v1 Announce Type: cross Abstract: Repository-level code generation requires implementing target functions while accounting for complex cross-file.
- What to do: Validate with one small internal benchmark and compare against your current baseline this week.
Deep
Context
The retrieved procedural context is integrated with conventional semantic retrieval to construct a richer repository context for code generation.
What's new
Existing retrieval methods predominantly rely on lexical, structural, or semantic similarity, often overlooking repository functions that implement similar procedural logic despite differing in identifiers or application domains.
Key details
- Existing retrieval methods predominantly rely on lexical, structural, or semantic similarity, often overlooking repository functions that implement similar procedural logic despite differing in identifiers or application domains.
- We propose ProjAgent, a repository-level code generation system that introduces procedural similarity as an explicit retrieval signal.
- ProjAgent decomposes the target function into intermediate reasoning steps and employs an agentic workflow to retrieve repository functions that exhibit similar procedural behavior at each step.
- The retrieved procedural context is integrated with conventional semantic retrieval to construct a richer repository context for code generation.
Results & evidence
- arXiv:2607.08691v1 Announce Type: cross Abstract: Repository-level code generation requires implementing target functions while accounting for complex cross-file dependencies and project-specific conventions.
- Evaluated on REPOCOD, ProjAgent achieves 41.14% Pass@1, outperforming existing retrieval-based baselines.
- Computer Science > Software Engineering [Submitted on 9 Jul 2026] Title:ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation View PDF HTML (experimental)Abstract:Repository-level code generation requires implementing target functi...
Limitations / unknowns
- Generalization outside curated tasks is still unclear.
Next-step validation checks
- Reproduce one claim with a public baseline and fixed evaluation settings.
- Check robustness on out-of-distribution or long-context cases.
- Track whether independent teams report matching results.
Source: arxiv | Overall 6.5/10 | Corroboration: 1
Signal 9.4
Novelty 5.1
Impact 2.0
Confidence 8.7
Actionability 6.5
Summary: arXiv:2607.08177v1 Announce Type: new Abstract: In this paper, we study the automatic schema generation problem: given a collection of historical ship maintenance and operational.
- What happened: arXiv:2607.08177v1 Announce Type: new Abstract: In this paper, we study the automatic schema generation problem: given a collection of historical ship maintenance and.
- Why it matters: arXiv:2607.08177v1 Announce Type: new Abstract: In this paper, we study the automatic schema generation problem: given a collection of historical ship maintenance and.
- What to do: Validate with one small internal benchmark and compare against your current baseline this week.
Deep
Context
arXiv:2607.08177v1 Announce Type: new Abstract: In this paper, we study the automatic schema generation problem: given a collection of historical ship maintenance and operational reports across multiple form categories, automatically discover compact and in...
What's new
arXiv:2607.08177v1 Announce Type: new Abstract: In this paper, we study the automatic schema generation problem: given a collection of historical ship maintenance and operational reports across multiple form categories, automatically discover compact and in...
Key details
- To address this challenge, we propose ASMR, a modular agentic framework consisting of two specialized agents.
- A Field Generation Agent extracts semantic concepts from historical narratives and generates candidate schema fields through adaptive multi-granularity clustering, while a Structural Optimizer Agent employs reinforcement learning to identify compact, inform...
- The resulting schemas can guide report authors toward producing more complete, consistent, and actionable reports.
- Preliminary results demonstrate the promise of the proposed approach and highlight several open research challenges at the intersection of data management, agentic AI, and human-centered AI.
Results & evidence
- arXiv:2607.08177v1 Announce Type: new Abstract: In this paper, we study the automatic schema generation problem: given a collection of historical ship maintenance and operational reports across multiple form categories, automatically discover compact and in...
- Computer Science > Artificial Intelligence [Submitted on 9 Jul 2026] Title:ASMR: Agentic Schema Generation for Ship Maintenance Report Writing View PDF HTML (experimental)Abstract:In this paper, we study the automatic schema generation problem: given a coll...
- Submission history From: Sohrab Namazi Nia [view email][v1] Thu, 9 Jul 2026 07:25:28 UTC (6,648 KB) References & Citations Loading...
Limitations / unknowns
- Generalization outside curated tasks is still unclear.
Next-step validation checks
- Reproduce one claim with a public baseline and fixed evaluation settings.
- Check robustness on out-of-distribution or long-context cases.
- Track whether independent teams report matching results.
Source: arxiv | Overall 6.2/10 | Corroboration: 1
Signal 9.4
Novelty 4.0
Impact 2.0
Confidence 8.7
Actionability 6.5
Summary: arXiv:2607.07836v1 Announce Type: new Abstract: We present Infinity-Parser2, a large multimodal model that couples a controllable data-synthesis pipeline with multi-task.
- What happened: Second, we introduce a verifiable, multi-task reward system that enables Joint Reinforcement Learning across eight co-trained objectives (document parsing, layout.
- Why it matters: arXiv:2607.07836v1 Announce Type: new Abstract: We present Infinity-Parser2, a large multimodal model that couples a controllable data-synthesis pipeline with multi-task.
- What to do: Validate with one small internal benchmark and compare against your current baseline this week.
Deep
Context
arXiv:2607.07836v1 Announce Type: new Abstract: We present Infinity-Parser2, a large multimodal model that couples a controllable data-synthesis pipeline with multi-task reinforcement learning for end-to-end document parsing, addressing the persistent scarc...
What's new
arXiv:2607.07836v1 Announce Type: new Abstract: We present Infinity-Parser2, a large multimodal model that couples a controllable data-synthesis pipeline with multi-task reinforcement learning for end-to-end document parsing, addressing the persistent scarc...
Key details
- First, we build a scalable synthesis engine, pairing a controllable rendering framework with an iterative refinement loop, and use it to construct and open-source Infinity-Doc2-5M: a 5-million-sample bilingual (Chinese/English) corpus spanning diverse docum...
- Second, we introduce a verifiable, multi-task reward system that enables Joint Reinforcement Learning across eight co-trained objectives (document parsing, layout analysis, table parsing, math formula parsing, chart parsing, chemical formula parsing, docume...
- Third, we release two variants under a shared architecture: Infinity-Parser2-Flash, optimized for low-latency inference with a $3.68\times$ throughput gain over Infinity-Parser-7B, and Infinity-Parser2-Pro, engineered for precision-critical settings.
- Infinity-Parser2-Pro reaches state-of-the-art 87.6% on olmOCR-Bench and 74.3% on ParseBench, surpassing DeepSeek-OCR-2, PaddleOCR-VL-1.5, and MinerU2.5, with strong generalization to charts, chemical formulas, and document VQA.
Results & evidence
- arXiv:2607.07836v1 Announce Type: new Abstract: We present Infinity-Parser2, a large multimodal model that couples a controllable data-synthesis pipeline with multi-task reinforcement learning for end-to-end document parsing, addressing the persistent scarc...
- First, we build a scalable synthesis engine, pairing a controllable rendering framework with an iterative refinement loop, and use it to construct and open-source Infinity-Doc2-5M: a 5-million-sample bilingual (Chinese/English) corpus spanning diverse docum...
- Third, we release two variants under a shared architecture: Infinity-Parser2-Flash, optimized for low-latency inference with a $3.68\times$ throughput gain over Infinity-Parser-7B, and Infinity-Parser2-Pro, engineered for precision-critical settings.
Limitations / unknowns
- Generalization outside curated tasks is still unclear.
Next-step validation checks
- Reproduce one claim with a public baseline and fixed evaluation settings.
- Check robustness on out-of-distribution or long-context cases.
- Track whether independent teams report matching results.