Papers › CoSER: Coordinating LLM-Based Persona Simulation of Established Roles

CoSER: Coordinating LLM-Based Persona Simulation of Established Roles

13 Feb 2025arXiv:2502.09082archive 2025-07-28

Xintao Wang, Heng Wang, Yifei Zhang, Xinfeng Yuan, Rui Xu, Jen-tse Huang, Siyu Yuan, Haoran Guo, Jiangjie Chen, Wei Wang, Yanghua Xiao, Shuchang Zhou

Role-playing language agents (RPLAs) have emerged as promising applications of large language models (LLMs). However, simulating established characters presents a challenging task for RPLAs, due to the lack of authentic character datasets and nuanced evaluation methods using such data. In this paper, we present CoSER, a collection of a high-quality dataset, open models, and an evaluation protocol towards effective RPLAs of established characters. The CoSER dataset covers 17,966 characters from 771 renowned books. It provides authentic dialogues with real-world intricacies, as well as diverse data types such as conversation setups, character experiences and internal thoughts. Drawing from acting methodology, we introduce given-circumstance acting for training and evaluating role-playing LLMs, where LLMs sequentially portray multiple characters in book scenes. Using our dataset, we develop CoSER 8B and CoSER 70B, i.e., advanced open role-playing LLMs built on LLaMA-3.1 models. Extensive experiments demonstrate the value of the CoSER dataset for RPLA training, evaluation and retrieval. Moreover, CoSER 70B exhibits state-of-the-art performance surpassing or matching GPT-4o on our evaluation and three existing benchmarks, i.e., achieving 75.80% and 93.47% accuracy on the InCharacter and LifeChoice benchmarks respectively.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2502.09082")

Code

Syntology Ran 9 of 23 code samples harvested from 2 repositories linked to this paper; 14 have no recorded run. Of those that ran: 4 ran · honoured contract; 5 ran · our draft was wrong.

By repository: official repository: 1 sample from 1 repository, 1 ran; community (archive-listed): 22 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Neph0s/CoSER official report
neph0s/incharacter mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

23 samples harvested; 9 ran; 4 honoured the contract we drafted; 14 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

4ran · honoured contract
5ran · our draft was wrong
14unverified

Licence: 1 of the 23 samples is pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

get_character_prompt Neph0s/CoSER/gca_evaluation/utils.py official repository ran · our draft was wrong no licence file found · pointer only · c7933743a582b312 · report
base64_to_float_array neph0s/incharacter/code/ChatHaruhi/ChatHaruhi.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 4b18614854f76d47 · report
base64_to_string neph0s/incharacter/code/ChatHaruhi/ChatHaruhi.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 9083059a6053c01a · report
get_bge_embeddings neph0s/incharacter/code/ChatHaruhi/ChatHaruhi.py community (archive-listed) ran · honoured contract MIT (permissive) · 8ac80353df541407 · report
get_bge_zh_embedding neph0s/incharacter/code/ChatHaruhi/ChatHaruhi.py community (archive-listed) ran · honoured contract MIT (permissive) · 6087c37cde8b7d71 · report
get_general_embedding neph0s/incharacter/code/ChatHaruhi/ChatHaruhi.py community (archive-listed) ran · honoured contract MIT (permissive) · ccd15a636f8315df · report
get_text_from_data neph0s/incharacter/code/ChatHaruhi/ChatHaruhi.py community (archive-listed) ran · our draft was wrong MIT (permissive) · a96df6daca0f00a5 · report
is_chinese_or_english neph0s/incharacter/code/ChatHaruhi/ChatHaruhi.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · f5012fac79a4d832 · report
response_postprocess neph0s/incharacter/code/ChatHaruhi/ChatHaruhi.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · e0af9feb46733253 · report
ChatHaruhi neph0s/incharacter/code/ChatHaruhi/ChatHaruhi.py community (archive-listed) unverified MIT (permissive) · 72ca06e73065b5f0 · report
cached neph0s/incharacter/code/ChatHaruhi/ChatHaruhi.py community (archive-listed) unverified MIT (permissive) · ded92e88e0b003ab · report
download_models neph0s/incharacter/code/ChatHaruhi/ChatHaruhi.py community (archive-listed) unverified MIT (permissive) · 3886f44e69594927 · report
get_bge_embedding neph0s/incharacter/code/ChatHaruhi/ChatHaruhi.py community (archive-listed) unverified MIT (permissive) · 4a6302a49807a5e7 · report
get_bge_embeddings_safe neph0s/incharacter/code/ChatHaruhi/ChatHaruhi.py community (archive-listed) unverified MIT (permissive) · fb71211b0752f685 · report
get_db_from_type neph0s/incharacter/code/ChatHaruhi/ChatHaruhi.py community (archive-listed) unverified MIT (permissive) · d39ee52667a78ef8 · report
get_embedding_for_chinese neph0s/incharacter/code/ChatHaruhi/ChatHaruhi.py community (archive-listed) unverified MIT (permissive) · 338cf403e8136171 · report
get_embedding_for_english neph0s/incharacter/code/ChatHaruhi/ChatHaruhi.py community (archive-listed) unverified MIT (permissive) · 1acb7e8163ea94f9 · report
get_general_embeddings neph0s/incharacter/code/ChatHaruhi/ChatHaruhi.py community (archive-listed) unverified MIT (permissive) · b6444230426a2754 · report
get_general_embeddings_safe neph0s/incharacter/code/ChatHaruhi/ChatHaruhi.py community (archive-listed) unverified MIT (permissive) · 9d6500eb148b11cd · report
get_luotuo_model neph0s/incharacter/code/ChatHaruhi/ChatHaruhi.py community (archive-listed) unverified MIT (permissive) · 936046d800c3e83d · report
luotuo_embedding neph0s/incharacter/code/ChatHaruhi/ChatHaruhi.py community (archive-listed) unverified MIT (permissive) · cd9ff808f0197b70 · report
luotuo_openai_embedding neph0s/incharacter/code/ChatHaruhi/ChatHaruhi.py community (archive-listed) unverified MIT (permissive) · 0ef004806ceb47bb · report
tiktokenizer neph0s/incharacter/code/ChatHaruhi/ChatHaruhi.py community (archive-listed) unverified MIT (permissive) · 55e9d4ef95279fed · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections