REVIEW 34 cited by
Deep Research Agents: A Systematic Examination And Roadmap
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Deep Research Agents: A Systematic Examination And Roadmap
read the original abstract
The rapid progress of Large Language Models (LLMs) has given rise to a new category of autonomous AI systems, referred to as Deep Research (DR) agents. These agents are designed to tackle complex, multi-turn informational research tasks by leveraging a combination of dynamic reasoning, adaptive long-horizon planning, multi-hop information retrieval, iterative tool use, and the generation of structured analytical reports. In this paper, we conduct a detailed analysis of the foundational technologies and architectural components that constitute Deep Research agents. We begin by reviewing information acquisition strategies, contrasting API-based retrieval methods with browser-based exploration. We then examine modular tool-use frameworks, including code execution, multimodal input processing, and the integration of Model Context Protocols (MCPs) to support extensibility and ecosystem development. To systematize existing approaches, we propose a taxonomy that differentiates between static and dynamic workflows, and we classify agent architectures based on planning strategies and agent composition, including single-agent and multi-agent configurations. We also provide a critical evaluation of current benchmarks, highlighting key limitations such as restricted access to external knowledge, sequential execution inefficiencies, and misalignment between evaluation metrics and the practical objectives of DR agents. Finally, we outline open challenges and promising directions for future research. A curated and continuously updated repository of DR agent research is available at: {https://github.com/ai-agents-2030/awesome-deep-research-agent}.
Forward citations
Cited by 34 Pith papers
-
Multi-Head Recurrent Memory Agents
The paper proposes Multi-Head Recurrent Memory (MHM) with a select-then-update strategy to improve memory retention in long-context recurrent agents.
-
HarnessBridge: Learnable Bidirectional Controller for LLM Agent Harness
HarnessBridge is a learnable bidirectional controller that projects observations and actions for LLM agent harnesses, matching specialized performance while cutting tokens and generalizing across model sizes.
-
PropGuard: Safeguarding LLM-MAS via Propagation-Aware Exploration and Remediation
PropGuard is a propagation-aware framework for LLM-MAS that constructs dual-view spatio-temporal graphs, employs a GE-GRPO inspector to recover suspicious subgraphs, and applies source-guided remediation to lower atta...
-
Metis: Memory Foundation Model
Metis equips frozen LLMs with gradient-free native memory states and mid-trained store/use procedures that beat no-context parametric baselines on short memory tasks but still lag full context and degrade over long tr...
-
HiEviDR-Bench: A Benchmark for Hierarchical Evidence Aggregation in Deep Research
A hierarchical evidence-graph benchmark reveals that multimodal deep-research models write fluent reports while failing citation, claim, and answer grounding.
-
SciDataSailor: Deep Scientific Data Exploring
SciDataSailor uses Monte Carlo tree search to synthesize tool-use trajectories for training and benchmarking LLM agents that explore raw scientific repositories.
-
AREX: Towards a Recursively Self-Improving Agent for Deep Research
A recursively self-improving research agent using constraint-wise verification, a learned context-update tool, and key-step-focused RL reaches frontier-level accuracy with only 10B active parameters.
-
Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agents
IGRPO allocates multi-turn LLM agent rollout budget proportional to intermediate-state information gain, inducing an exponentially tilted teacher distribution for policy optimization.
-
MedBench v5: A Dynamic, Process-Oriented, and Hallucination-Aware Benchmark for Clinical Multimodal Models
Strong medical-model task scores do not guarantee process stability: omission, contradiction, and delay mainly break contradiction detection, diagnosis updating, and hallucination self-correction while final evidence ...
-
MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval
MCompassRAG adds topic metadata to chunk representations and uses LLM distillation to train a lightweight topic-aware retriever, reporting 8.24% average information efficiency gain and over 5x lower latency than stron...
-
Creative Reading: Scaffolding Reading for Transformation
Proposes creative reading as a provocation-oriented design space for reading augmentation that values reader self-creation and plurality of interpretations by synthesizing literary theory with sensemaking and creativi...
-
Helicase: Uncertainty-Guided Supply Chain Knowledge Graph Construction with Autonomous Multi-Agent LLMs
Helicase proposes an autonomous multi-agent LLM framework for uncertainty-guided supply chain knowledge graph construction evaluated on the new SCQA benchmark of 80 queries.
-
Position: Academic Conferences are Potentially Facing Denominator Gaming Caused by Fully Automated Scientific Agents
Malicious actors could use AI agents to submit large numbers of fake papers, inflating the submission count and thereby raising the acceptance odds for a small set of chosen legitimate papers under stable conference a...
-
Behavior Cue Reasoning: Monitorable Reasoning Improves Efficiency and Safety through Oversight
Behavior Cue Reasoning trains LLMs to emit special tokens before behaviors, enabling monitors to prune up to 50% of wasted tokens and recover safe actions from 80% of unsafe traces, more than doubling success rates wi...
-
Behavior Cue Reasoning: Monitorable Reasoning Improves Efficiency and Safety through Oversight
Behavior Cue Reasoning trains LLMs to emit special tokens before behaviors, enabling monitors to cut up to 50% wasted reasoning tokens and recover safe actions from 80% of unsafe traces, more than doubling success rat...
-
AgentEconomist: An End-to-end Agentic System Translating Economic Intuitions into Executable Computational Experiments
AgentEconomist is an end-to-end agentic system with idea development, experimental design, and execution stages that uses a large economics paper database to produce research ideas with better literature grounding, no...
-
Self-Optimizing Multi-Agent Systems for Deep Research
Multi-agent deep research systems self-optimize prompts through self-play to match or outperform expert-crafted versions.
-
Learning to Retrieve from Agent Trajectories
Retrievers trained on agent trajectories via the LRAT framework improve evidence recall, task success, and efficiency in agentic search benchmarks.
-
Large Language Model Agent for User-friendly Chemical Process Simulations
An LLM agent integrated with AVEVA Process Simulation via MCP enables natural language driven flowsheet analysis, optimization, and construction for chemical separation processes.
-
MedBench v5: A Dynamic, Process-Oriented, and Hallucination-Aware Benchmark for Clinical Multimodal Models
MedBench v5 is a dynamic benchmark with process auditing, information stressors, and hallucination monitoring for clinical multimodal models across 63 tasks.
-
MedBench v5: A Dynamic, Process-Oriented, and Hallucination-Aware Benchmark for Clinical Multimodal Models
MedBench v5 is a new dynamic benchmark framework for clinical multimodal models that adds process auditing, factorized stressors, and hallucination propagation tracking across 63 tasks.
-
OpenSkill: Open-World Self-Evolution for LLM Agents
OpenSkill bootstraps LLM agent self-evolution by pulling grounded knowledge and anchors from open-world sources, synthesizing transferable skills, and refining them on self-generated virtual tasks, achieving top bench...
-
Workflow Closure Is Not Scientific Closure in Auto-Research Systems
Survey of auto-research systems identifies objective, validation, and acceptance collapses, concluding that workflow closure does not equal scientific closure and advocating non-autonomous epistemic control.
-
Scaling Retrieval-Augmented Reasoning with Parallel Search and Explicit Merging
MultiSearch uses parallel multi-query retrieval plus explicit merging inside a reinforcement-learning loop to improve retrieval-augmented reasoning, outperforming baselines on seven QA benchmarks.
-
ViDR: Grounding Multimodal Deep Research Reports in Source Visual Evidence
ViDR treats source figures as retrievable and verifiable evidence objects in multimodal deep research reports and introduces MMR Bench+ to measure improvements in visual integration and verifiability.
-
LLM-Oriented Information Retrieval: A Denoising-First Perspective
Denoising to maximize usable evidence density and verifiability is becoming the primary bottleneck in LLM-oriented information retrieval, conceptualized via a four-stage framework and addressed through a pipeline taxo...
-
Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction
Web2BigTable introduces a bi-level multi-agent system that achieves new state-of-the-art results on wide-coverage and deep web-to-table search benchmarks through orchestration, coordination, and closed-loop reflection.
-
Emergent Social Intelligence Risks in Generative Multi-Agent Systems
Generative multi-agent systems exhibit emergent collusion and conformity behaviors that cannot be prevented by existing agent-level safeguards.
-
IoDResearch: Deep Research on Private Heterogeneous Data via the Internet of Data
IoDResearch is a private data-centric Deep Research framework that uses FAIR digital objects, atomic knowledge units, heterogeneous graph indexes, and a multi-agent system to outperform standard RAG baselines on retri...
-
Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs
ERL trains LLMs to erase faulty reasoning steps and regenerate them in place, yielding gains of up to 8.48% EM on multi-hop QA benchmarks like HotpotQA.
-
VaseMuseum: Digital Intelligent Museum for Ancient Greek Pottery
VaseMuseum is a training-free multimodal agent that combines DeepResearch-style retrieval, source/response reliability control, and best-of-K reranking to improve citation validity and reduce hallucination for museum ...
-
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.
-
EigentSearch-Q+: Enhancing Deep Research Agents with Structured Reasoning Tools
Structured query and evidence tools added to an AI research agent improve benchmark accuracy by 0.6 to 3.8 percentage points.
-
Towards Trustworthy Report Generation: A Deep Research Agent with Progressive Confidence Estimation and Calibration
A deep research agent incorporates progressive confidence estimation and calibration to produce trustworthy reports with transparent confidence scores on claims.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.