DR Pixel enables page-native deep research with vision-language models
DR Pixel is an open-source agent that reasons directly over document page images, outperforming OCR-based methods on scientific papers.
Stories per day · 30 days
2 RSS
Relatedagents2benchmark2agentic-search1backtesting1benchmarks1diffusion-models1dr-pixel1financial-forecasting1multimodal1open-source1patent-search1prior-art1supervised-fine-tuning1video1vision-language1vlm1
12 stories, newest first · one card per story
Stories tagged #deep-research
FinForesight benchmark evaluates deep research systems in financial forecasting
FinForesight is a backtesting benchmark for financial forecasting that avoids post-cutoff information.
PatEx-Gym benchmarks agents on patent prior-art search
A 4B PatEx-Agent trained on synthetic trajectories is presented as competitive with much larger general-purpose agents.
OmniDR-Bench scores agents on video-centered deep research reports
Fifty bilingual tasks and 6,414 criteria leave the best of 18 agent setups at 63.3 out of 100.
DiffResearch puts diffusion models at the core of deep research agents
On 100 benchmark tasks the authors report about a 6x end-to-end speedup versus a comparable autoregressive model.
Incremental Open-Ended Deep Research with Structured Harness
Incremental-OEDR updates research reports over time, cutting tokens and searches while preserving report quality.
OneSearch-VL: Unified Multimodal Deep Research Agent for Image and Video
OneSearch-VL-8B beats tool-using Qwen3-VL-8B by up to 20.2 points on new visual research benchmarks.
DAGent: Evaluate-then-Grow Planning for Deep Research Agents
DAGent grows research-agent plans from evidence and beats open baselines on BrowseComp-Plus, GAIA, and xbench-DeepSearch.
DAGent: Evaluate-then-Grow Planning for Deep Research Agents
DAGent plans deep-research agent graphs incrementally from evidence confidence, outperforming open baselines on three benchmarks.
LongCat-DeepResearch Technical Report
LongCat-DeepResearch uses multi-agent planning and section-level revision to produce evidence-grounded research reports.
Exa Launches Agent Ultra: A Subagent Swarm Deep Research API Built for Exhaustive List Building
Exa launched Agent Ultra, a hosted subagent research API it says leads four deep-research benchmarks.
5
Decomposition Buys Integrity, Not Yield
Study of 600 production deep-research traces finds agent-tree decomposition loses findings at rate N^(1-δ); flat architectures maximize yield.