Daily edition · Information Retrieval
TILens turns technical updates into a focused daily brief: official releases, trusted reporting, and practitioner analysis, deduplicated and organized by topic.
22 articles · 5 sources · 22 papers ·
Top topics: Information Retrieval · AI Research · AI
arXiv:2610.23707v1 Announce Type: new Abstract: A multi-step agent task fails when a single tool it needs is missing, yet the tools an agent may need are too many to list: the roughly 8,200 tools on the platform we…
arXiv:2610.22511v1 Announce Type: cross Abstract: Evaluating language models and agents requires combining benchmark accuracy, judge-based assessment, runtime performance, tool-use behavior, and retrieval quality.…
arXiv:2610.23510v1 Announce Type: new Abstract: Current learned sparse approaches for recommender systems, such as STAR, represent a user by concatenating their interaction history into a single query string. For news,…
arXiv:2610.18654v2 Announce Type: replace-cross Abstract: Summary-token architectures such as Kwai Summary Attention (KSA) compress distant context into learnable Summary token per chunk, and hybrid variants interleave…
arXiv:2610.22474v1 Announce Type: cross Abstract: Figures are essential for scientific communication, and the field of Visual Question Answering (VQA) aims to test the figure understanding capabilities of large…
arXiv:2610.23470v1 Announce Type: new Abstract: Open-ended search combined with foundation models has produced advances such as faster algorithms, new results on open mathematical problems, and self-improving agents. We…
arXiv:2609.01780v2 Announce Type: replace Abstract: Knowledge Graph Question Answering (KGQA) over RDF graphs remains challenging in domain-specific settings, where formal ontologies and curated text-SPARQL pairs are…
arXiv:2607.25182v2 Announce Type: replace-cross Abstract: Reasoning distillation trains a student to reproduce both the teacher's chain-of-thought trace and its final answer. We ask whether the trace is better used as…
arXiv:2610.23186v1 Announce Type: cross Abstract: Agent skills have proven to be an effective technique for improving agent ability on specific tasks, including software engineering, natural science, and mathematics.…
arXiv:2610.22726v1 Announce Type: cross Abstract: Distinguishing visually similar characters is a persistent challenge for optical character recognition (OCR) systems, causing errors in critical applications of text…
arXiv:2610.23346v1 Announce Type: new Abstract: This study investigates Jev, a System One model designed for fast, structured decision-making, in information retrieval. We use Jev-as-a-judge to generate relevance…
arXiv:2610.22797v1 Announce Type: new Abstract: Reasoning rerankers write a rationale before ranking a candidate slate, and existing systems read item metadata to do so, even though generative recommenders increasingly…
arXiv:2610.20191v2 Announce Type: replace-cross Abstract: Medication recommendation (MR) is critical for clinical decision support. While existing MR methods are mostly designed for single-center learning, where only…
arXiv:2609.11052v3 Announce Type: replace Abstract: Industrial recommender systems use cascaded stages with different candidate spaces, data distributions, and latency constraints. Independently optimizing their…
arXiv:2610.23541v1 Announce Type: new Abstract: Humanity's Last Choice describes the idea that the last choice people need to make is which AI system they entrust with the decisions that follow. These systems rely on…
arXiv:2610.11370v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) grounds language models in external corpora. Agentic RAG enables iterative search, yet exposes the model to isolated chunks…
arXiv:2605.23916v3 Announce Type: replace Abstract: AI agents often pick tools from registries, where each provider writes its tool's description; we ask whether sales language there changes which tool an agent picks.…
arXiv:2610.22703v1 Announce Type: new Abstract: NoveltyScope is a prototype that compares a scientific paper with retrieved prior work and produces a structured report and a five-level novelty score. The system extracts…
arXiv:2610.23311v1 Announce Type: cross Abstract: Large language models (LLMs) can generate fluent outputs that lack source support or conflict with local operational constraints. We introduce Self-Reflective…
arXiv:2610.22588v1 Announce Type: new Abstract: Strong multi-hop retrieval should be practical to deploy without expensive corpus preparation or complex database infrastructure. We present SAG2, an embedding-free…
Showing 1 day · 22 items available
