A meta-agent uses failure analysis to evolve a task agent's instructions for coordinating lexical, semantic, and multimodal retrievers, leading to up to 19.6 point gains on document QA benchmarks.
Docbench: A benchmark for evaluating llm-based document reading systems
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
ATTAIN is a three-module trace-driven framework that combines exploit execution, LLM-guided diff search, and evidence-based judgment to identify affected library versions for CVEs, reporting 93.24% F1 on 224 CVEs across 25,943 versions.
DocRetriever introduces a framework using layout-aware sparse embeddings for hybrid encoding without OCR and a generalizable reasoning-augmented reranker for few-shot settings, plus the MultiDocR benchmark for evaluation.
Cognitive Kernel-Pro provides an open-source agent framework with curated training data across web, file, code, and reasoning domains plus test-time reflection and voting, achieving SOTA results on GAIA among free agents.
An experiment with 276 participants finds that vision language model assistance improves human game testers' defect identification, especially with design documentation, while AI errors create challenges.
citing papers explorer
-
Hybrid Retriever Evolution for Multimodal Document Reasoning Agents
A meta-agent uses failure analysis to evolve a task agent's instructions for coordinating lexical, semantic, and multimodal retrievers, leading to up to 19.6 point gains on document QA benchmarks.
-
ATTAIN: Automated Exploit Failure Analysis through Trace-Driven Diff Analysis
ATTAIN is a three-module trace-driven framework that combines exploit execution, LLM-guided diff search, and evidence-based judgment to identify affected library versions for CVEs, reporting 93.24% F1 on 224 CVEs across 25,943 versions.
-
DocRetriever: A Plug-and-Play Framework for Multimodal Document Retrieval with Comprehensive Benchmark
DocRetriever introduces a framework using layout-aware sparse embeddings for hybrid encoding without OCR and a generalizable reasoning-augmented reranker for few-shot settings, plus the MultiDocR benchmark for evaluation.
-
Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training
Cognitive Kernel-Pro provides an open-source agent framework with curated training data across web, file, code, and reasoning domains plus test-time reflection and voting, achieving SOTA results on GAIA among free agents.
-
Human-AI Collaborative Game Testing with Vision Language Models
An experiment with 276 participants finds that vision language model assistance improves human game testers' defect identification, especially with design documentation, while AI errors create challenges.