SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.13185 · 2024

Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 15 functions out of this paper's own repositories and ran 14 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
damo-nlp-sg/coi-agent canonical 14 of 15
FunctionStatusWhere it lives
encode_image Ran damo-nlp-sg/coi-agent/LLM.py
code served (permissive licence) · get_code("f41cb1a19b154297")
extract Ran damo-nlp-sg/coi-agent/utils.py
code served (permissive licence) · get_code("f650e65cc3083d84")
extract Ran damo-nlp-sg/coi-agent/searcher/sementic_search.py
code served (permissive licence) · get_code("4abf0ae6b3c8d8de")
extract_json Ran damo-nlp-sg/coi-agent/utils.py
code served (permissive licence) · get_code("8da3d9ba5f65d0b8")
fetch Ran damo-nlp-sg/coi-agent/searcher/sementic_search.py
code served (permissive licence) · get_code("4872fb8c1582e598")
get_content_between_a_b Ran damo-nlp-sg/coi-agent/LLM.py
code served (permissive licence) · get_code("a6d4e225abfd096e")
get_deep_check_idea_novel_search_query_prompt Ran damo-nlp-sg/coi-agent/prompts/deep_research_agent_prompts.py
code served (permissive licence) · get_code("62498ce66167479b")
get_deep_rewrite_query_prompt Ran damo-nlp-sg/coi-agent/prompts/deep_research_agent_prompts.py
code served (permissive licence) · get_code("9f075963c52cb8a9")
get_deep_search_query_prompt Ran damo-nlp-sg/coi-agent/prompts/deep_research_agent_prompts.py
code served (permissive licence) · get_code("954ecd542ae11bc3")
get_judge_experiment_all_prompt Ran damo-nlp-sg/coi-agent/prompts/juder_prompts.py
code served (permissive licence) · get_code("4ddd0eb717fa5b8e")
get_judge_idea_all_prompt Ran damo-nlp-sg/coi-agent/prompts/juder_prompts.py
code served (permissive licence) · get_code("8f8af080a9c99830")
get_review_experiment_design_suggestions_prompt Ran damo-nlp-sg/coi-agent/prompts/review_agent_prompts.py
code served (permissive licence) · get_code("455aefd097ad94ca")
get_review_search_related_paper_prompt Ran damo-nlp-sg/coi-agent/prompts/review_agent_prompts.py
code served (permissive licence) · get_code("ec479392ccee5103")
get_review_suggestions_from_papers_prompt Ran damo-nlp-sg/coi-agent/prompts/review_agent_prompts.py
code served (permissive licence) · get_code("7480cf0c2cd3d240")
get_openai_url Not yet run damo-nlp-sg/coi-agent/LLM.py
code served (permissive licence) · get_code("d79e88c565eff1fa")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Effective research ideation is a critical step for scientific research. However, the exponential increase in scientific literature makes it challenging for researchers to stay current with recent advances and identify meaningful research directions. Recent developments in large language models~(LLMs) suggest a promising avenue for automating the generation of novel research ideas. However, existing methods for idea generation either trivially prompt LLMs or directly expose LLMs to extensive literature without indicating useful information. Inspired by the research process of human researchers, we propose a Chain-of-Ideas~(CoI) agent, an LLM-based agent that organizes relevant literature in a chain structure to effectively mirror the progressive development in a research domain. This organization facilitates LLMs to capture the current advancements in research, thereby enhancing their ideation capabilities. Furthermore, we propose Idea Arena, an evaluation protocol that can comprehensively evaluate idea generation methods from different perspectives, aligning closely with the preferences of human researchers. Experimental results indicate that the CoI agent consistently outperforms other methods and shows comparable quality as humans in research idea generation. Moreover, our CoI agent is budget-friendly, with a minimum cost of \$0.50 to generate a candidate idea and its corresponding experimental design.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2410.13185")
get_code_for_paper("2410.13185")
have("2410.13185")

Connect an agent — have() is free.