Use this view to inspect the underlying evidence corpus. For ranked developments, decision posture and interpretation, use Signals.
Raw feed or Signals?
Raw feed is chronological evidence. Signals ranks and interprets material change.
Researchers study decision models for identifying knowledge-conflict types in RAG retrieval sources to improve generator accuracy.
Researchers introduce TrawMem, an agent memory framework framing LLM memory as task-oriented role-adaptive workspaces rather than static retrieval.
Researchers introduced DocXEval, a benchmark framework for evaluating explainability in multimodal document understanding models.
An audit of 51 multilingual benchmarks reveals wide but thin coverage and methodological gaps across 219 languages and 242 datasets.
A research paper evaluates decision models as faster, lower-cost judges for hallucination detection across six benchmark datasets.
Researchers introduced UCVE, a graph-structured retrieval framework designed to improve automated coverage and compliance validation.
A new arXiv study audits pretraining disclosure across 41 models from 17 families using Foundation Model Transparency Index indicators.
Researchers propose a metacognitive controller for diffusion language models to dynamically adapt token generation and compute usage.
Researchers propose GEPA-Curator, a method to filter noisy learning signals for self-improving multi-turn LLM agent workflows.
Researchers propose SCOPE, a multi-agent system for profiling news media outlets regarding bias, factuality, and credibility.
An arXiv paper examines self-distillation methods for open-weight models doing financial quantitative reasoning under data residency.
A new research paper proposes a control map for evaluating test-time language model updates beyond simple update counts.
Researchers propose a decision-theoretic framework to resolve knowledge conflicts between retrieval context and parametric memory in language models.
Researchers introduced PRISM-BENCH, a benchmark evaluating multimodal model reasoning groundedness, accuracy, and inference costs.
Researchers introduce QESChunker, a question-evidence-supervised chunking method optimizing RAG preprocessing indices.
Researchers propose batching reflective text optimization loops to run parallel proposals, cutting wall-clock execution time.
Researchers propose GUI-JEPA, a decoder-free mobile GUI agent policy using Joint-Embedding Predictive Architectures to improve speed.
Researchers introduced RubricAtlas to extract type-level rubrics from expert reports for evaluating deep research agents.
Researchers introduce AutoVend to benchmark LLM agents on long-horizon autonomous O2O commerce and physical execution.
Researchers introduced SpectRAG, a spectral graph approach for token-budgeted context selection to improve multi-hop RAG accuracy.
Researchers propose a new benchmark to evaluate whether information retrieval systems surface evidence that contradicts parametric priors.
Research on LLM agent harnesses investigates how fine-tuned policies depend on orchestration structures during post-training deployment.
Researchers demonstrate sparse feedback strategies to reduce LLM agent evaluation compute costs during iterative workflow optimization.
Google researchers announced EmbeddingGemma 2, an open multimodal embedding model representing text, images, audio, and video in a unified space.
Researchers evaluate test-time communication among 200 trading agents from four model families operating as independent decision-makers.
Researchers introduce CrossProfile, a benchmark evaluating how memory compression fails multi-agent LLM decision-making tasks.
Researchers introduced Heads of Security, an attention-gating mechanism to prevent prompt injection in models like Llama 3.3.
Researchers propose a unified framework combining LLM query routing and model cascading to optimize inference cost and response quality.
EffiBench-X is a new multi-language benchmark designed to measure the execution efficiency of LLM-generated code across six languages.
Researchers introduce FullFront, a benchmark for evaluating multimodal large language models across the complete front-end engineering workflow.