Challenge: Existing deep-research agents run in a 'fire-and-forget' mode, with no way to fix errors or add expert knowledge during execution.
Approach: They propose to use a planner-executor to write every step to a live 'plan-as-document' a fast communication layer streams each action, file change, and tool call to . web interface.
Outcome: The proposed framework surpasses OpenAI’s DeepResearch and Manus in the GAIA benchmark.

Similar Papers

TinyScientist: An Interactive, Extensible, and Controllable Framework for Building Research Agents (2025.emnlp-demos)

Copied to clipboard

Challenge: Existing research systems often design and use agentic workflows to perform research tasks such as ideation, scientific coding, review writing, and tree-based search.
Approach: They propose an open-source codebase, an interactive web demonstration, and a PyPI Python package to make state-of-the-art auto-research pipelines broadly accessible to every researcher and developer.
Outcome: The proposed framework adapts easily to new tools and supports iterative growth.
Agent Laboratory: Using LLM Agents as Research Assistants (2025.findings-emnlp)

Copied to clipboard

Challenge: Agent Laboratory is an autonomous LLM-based framework that can complete the entire research process.
Approach: Agent Laboratory is an autonomous LLM-based framework that can complete the entire research process.
Outcome: Agent Laboratory is an autonomous LLM-based framework that can complete the entire research process.
Deep-Reporter: Deep Research for Grounded Multimodal Long-Form Generation (2026.acl-long)

Copied to clipboard

Challenge: Recent agentic search frameworks are text-centric, overlooking multimodal evidence . a pressing task is multimodal long-form generation, a new paper argues .
Approach: They propose a unified agentic framework for grounded multimodal long-form generation.
Outcome: The proposed framework is based on a unified agentic framework for grounded multimodal long-form generation.
LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces (2026.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks for agentic programming in long-horizon command-line interface tasks are limited by short task horizons, data contamination from GitHub scraping, and a lack of fine-grained evaluation metrics.
Approach: They propose a benchmark to evaluate agentic capabilities across long-horizon command-line interface tasks.
Outcome: The proposed benchmarks cover four engineering categories: from scratch, feature addition, bug fixing, and refactoring.
DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) with web search capabilities show significant potential for deep research.
Approach: They introduce a framework for end-to-end training of LLM-based deep research agents . they implement a specialized multi-agent architecture where browsing agents extract relevant information from various webpage structures.
Outcome: The proposed framework improves on open-domain research tasks by 28.9 points over prompt engineering and 7.2 points over RAG-based RL agents.
DR-Arena: an Automated Evaluation Framework for Deep Research Agents (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for evaluating deep research capabilities rely on static datasets.
Approach: They propose a fully automated evaluation framework that pushes DR agents to their capability limits through dynamic investigation.
Outcome: DR-Arena achieves a Spearman correlation of 0.94 with the LMSYS Search Arena leaderboard.
HiRAS: A Hierarchical Multi-Agent Framework for Paper-to-Code Generation and Execution (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to automate computational research use fixed sequential agent pipelines with weak global coordination, which limits their robustness and overall performance.
Approach: They propose a hierarchical multi-agent framework for end-to-end paper reproduction that employs supervisory manager agents to coordinate specialised agents across fine-grained stages.
Outcome: The proposed framework improves the paper2code benchmark and significantly reduces hallucination in the evaluation.
LLM-Based Web Data Collection for Research Dataset Creation (2025.findings-emnlp)

Copied to clipboard

Challenge: researchers across many fields rely on web data to gain new insights and validate methods.
Approach: They propose a human-in-the-loop framework that automates web-scale data collection end-to-end using large language models (LLMs)
Outcome: The proposed framework outperforms existing methods in three different tasks and a user evaluation demonstrates its practical utility.
RExBench: Can coding agents autonomously implement AI research extensions? (2026.acl-long)

Copied to clipboard

Challenge: Existing large language model (LLM) agents are not capable of performing research extension tasks autonomously.
Approach: They propose a benchmark to evaluate LLM agents' ability to extend existing AI research . they use extensions of 12 recently published research papers accompanied by domain expert-written instructions .
Outcome: The proposed benchmark evaluates 12 LLM agents implemented using aider and OpenHands.
GUI Agents: A Survey (2025.findings-acl)

Copied to clipboard

Challenge: Large Foundation Models (LFMs) have transformed the landscape of AI research and day-to-day life.
Approach: They propose a framework that delineates GUI agents' perception, reasoning, planning, and acting capabilities.
Outcome: The proposed framework delineates their perception, reasoning, planning, and acting capabilities.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations