SEER is an evidence-grounded multi-agent system for generating structured scientific surveys through recursive backtracking, parallel drafting, and citation-normalized LaTeX/PDF assembly.

Stars

3

7-day growth

No data

Forks

0

Open issues

0

License

Apache-2.0

Last updated

2026-07-30

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It transforms survey generation from a frozen single-pass pipeline into a recursive hierarchy where parent agents repair completed child subtrees, with shared literature memory and traceable citation provenance.

Who it is for

  • Researchers in NLP, LLM agents, and automated scientific writing
  • Scientists and scholars who need structured literature surveys
  • Developers building research automation or survey-generation tools
  • Users of OpenAI-compatible model endpoints seeking reproducible survey workflows

Use cases

  • Generating a structured outline and full literature survey for a research topic
  • Producing evidence-grounded long-form surveys with citation normalization and LaTeX/PDF export
  • Using the bundled Codex skill to run self-contained literature-survey workflows
  • Resuming and exporting an existing survey run as LaTeX or PDF

Strengths

  • Recursive outline agents use ReAct-style search, browse, propose, critique, and finish loops
  • Parent adjudication can promote, demote, move, merge, or remove nodes to resolve hierarchy conflicts
  • Leaf agents write disjoint sections in parallel with local evidence sets and citation provenance
  • Shared PaperDB and task-scoped context keep knowledge reusable without carrying all intermediate traces

Considerations

  • Requires Python 3.10+ and OpenAI-compatible model endpoints with external credentials
  • Search adapters and model-specific environment variables must be configured by the user
  • The repository intentionally excludes benchmarks, evaluation code, tests, logs, and generated outputs

README quick start

Installation

Description

official codebase: SEER: Automated Survey Generation via Recursive Backtracking Multi-Deep-Research-Agent Systems

Related repositories

Similar projects matched by category, topics, and programming language.

MoonshotAI
Featured
MoonshotAI GitHub avatar

Kimi-K3

Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.

AI & Machine LearningAI Agents
3,348
yetone
Featured
yetone GitHub avatar

kill-ai-slop

Kill AI Slop is a multilingual field guide and agent skill that catalogues 33 common AI-generated design tells with interactive before-after demos, and provides a tool to scan and fix web projects.

AI & Machine LearningAI Agents
805
gnipbao
Featured
gnipbao GitHub avatar

story-to-handdrawn-video

A Remotion-based tool that converts Chinese story text or ordered hand-drawn images into vertical hand-drawn diary-comic animation with handwritten captions, left-to-right reveals, optional page-curl transitions, and silent H.264 output for post-production dubbing.

AI & Machine LearningAI Agents
683