AgentDisCo disentangles exploration and exploitation via critic-generator agent pairs and code-agent meta-optimization to generate research reports, matching top systems on benchmarks while introducing the GALA benchmark from browsing histories.
Deep researcher with test-time diffusion
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
method 1
citation-polarity summary
representative citing papers
ScaffoldAgent improves long-form report generation by modeling outline evolution as expansion, contraction, and revision guided by a utility function estimating downstream value.
DuMate-DeepResearch introduces a multi-agent deep research system with graph-based planning, recursive execution, and rubric optimization that reports new state-of-the-art scores of 58.03% and 61.95% on two benchmarks.
CAP-TTA triggers context-aware LoRA updates under a bias-risk threshold to debias LLM narrative generation at test time.
EvoIF integrates within-family and cross-family evolutionary signals into a compact model to achieve competitive or state-of-the-art zero-shot fitness prediction on ProteinGym using only 0.15% of typical training data.
Argues for a denoising-first paradigm in LLM-oriented information retrieval, framing challenges via a four-stage progression and providing a taxonomy of signal-to-noise optimization techniques across the pipeline.
citing papers explorer
-
AgentDisCo: Towards Disentanglement and Collaboration in Open-ended Deep Research Agents
AgentDisCo disentangles exploration and exploitation via critic-generator agent pairs and code-agent meta-optimization to generate research reports, matching top systems on benchmarks while introducing the GALA benchmark from browsing histories.
-
ScaffoldAgent: Utility-Guided Dynamic Outline Optimization for Open-Ended Deep Research
ScaffoldAgent improves long-form report generation by modeling outline evolution as expansion, contraction, and revision guided by a utility function estimating downstream value.
-
DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning
DuMate-DeepResearch introduces a multi-agent deep research system with graph-based planning, recursive execution, and rubric optimization that reports new state-of-the-art scores of 58.03% and 61.95% on two benchmarks.
-
Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Generation
CAP-TTA triggers context-aware LoRA updates under a bias-risk threshold to debias LLM narrative generation at test time.
-
Evolutionary Profiles for Protein Fitness Prediction
EvoIF integrates within-family and cross-family evolutionary signals into a compact model to achieve competitive or state-of-the-art zero-shot fitness prediction on ProteinGym using only 0.15% of typical training data.
-
LLM-Oriented Information Retrieval: A Denoising-First Perspective
Argues for a denoising-first paradigm in LLM-oriented information retrieval, framing challenges via a four-stage progression and providing a taxonomy of signal-to-noise optimization techniques across the pipeline.