DAGent: Evaluate-then-Grow Planning for Deep Research Agents

arXiv:2609.39154 · cs.CL, cs.AI · Submitted 2026-09-30 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-09-30

Updated: 2026-09-30

Comments: Accepted at NeurIPS 2026

Code: https://github.com/hanwenliu6825/DAGent

Project page: https://manus.im

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• GRPO — 65× in this paper · explained in 6 episodes
• Benchmark — 57× in this paper · explained in 2 episodes
• Regularization — 20× in this paper · explained in 3 episodes
• LLM judge — 15× in this paper · explained in 2 episodes
• Accuracy — 13× in this paper · explained in 1 episode
• Verification — 11× in this paper · explained in 2 episodes
• Reinforcement Learning — 9× in this paper · explained in 4 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Trace — 6× in this paper · explained in 2 episodes
• Adaptation — 5× in this paper · explained in 1 episode
• Multi-Agent System — 5× in this paper · explained in 6 episodes
• Consistency — 3× in this paper · explained in 3 episodes
• Core — 3× in this paper · explained in 2 episodes
• Multi-Agent Framework — 3× in this paper · explained in 3 episodes
• Task Decomposition — 3× in this paper · explained in 2 episodes
• Agentic Reasoning — 2× in this paper · explained in 1 episode
• Credit assignment — 2× in this paper · explained in 3 episodes
• RAG — 2× in this paper · explained in 3 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Adaptive Reasoning — 1× in this paper · explained in 2 episodes
• Agent-callable tools — 1× in this paper · explained in 1 episode
• Agentic System — 1× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Commentary — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• GRPO Objective — 1× in this paper · explained in 2 episodes
• Knowledge Graph — 1× in this paper · explained in 7 episodes
• Knowledge graphs — 1× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Multi-agent Collaboration — 1× in this paper · explained in 2 episodes
• Provenance — 1× in this paper · explained in 3 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Structural Constraints — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• Multi-Agent Deep Research: Training Multi-Agent Systems with M-GRPO
• Counterfactual Credit Policy Optimization for Multi-Agent Collaboration
• Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
• OpenAI GPT-5 System Card
• Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution
• FoldAct: Efficient and Stable Context Folding for Long-Horizon Search Agents
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization
• Qwen3 Technical Report
• ParallelSearch: Train your LLMs to Decompose Query and Search Sub-queries in Parallel with Reinforcement Learning

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering