Pith. sign in

REVIEW 8 cited by

Character-LLM: A Trainable Agent for Role-Playing

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.10158 v2 pith:4UT5MSFZ submitted 2023-10-16 cs.CL cs.AI

classification cs.CLcs.AI
keywords agentsexperienceshumanllmsabilityagentbehaviorsbuild
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large language models (LLMs) can be used to serve as agents to simulate human behaviors, given the powerful ability to understand human instructions and provide high-quality generated texts. Such ability stimulates us to wonder whether LLMs can simulate a person in a higher form than simple human behaviors. Therefore, we aim to train an agent with the profile, experience, and emotional states of a specific person instead of using limited prompts to instruct ChatGPT API. In this work, we introduce Character-LLM that teach LLMs to act as specific people such as Beethoven, Queen Cleopatra, Julius Caesar, etc. Our method focuses on editing profiles as experiences of a certain character and training models to be personal simulacra with these experiences. To assess the effectiveness of our approach, we build a test playground that interviews trained agents and evaluates whether the agents \textit{memorize} their characters and experiences. Experimental results show interesting observations that help build future simulacra of humankind.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. ProEvent: An Event-centric Benchmark for Proactive Agents

    cs.AI 2026-07 conditional novelty 6.0 of 10

    ProEvent is a benchmark showing LLM agents keep a user's event timetable from chats poorly, with the best fully-correct score at 27.2%.

  2. LLMs vs. Chinese Anime Enthusiasts: A Comparative Study on Emotionally Supportive Role-Playing

    cs.CL 2025-08 unverdicted novelty 6.0 of 10

    ChatAnime, a new emotionally supportive anime role-play benchmark, reports top LLMs outperforming human enthusiasts on role-playing and emotional support metrics while humans keep the diversity edge.

  3. CogDual: Enhancing Dual Cognition of LLMs via Reinforcement Learning with Implicit Rule-Based Rewards

    cs.CL 2025-07 conditional novelty 6.0 of 10

    A role-playing LLM that reasons about the scene and its own state before responding, trained with two semantic rewards, beats stronger baselines on role-play benchmarks.

  4. H2HTalk: Evaluating Large Language Models as Emotional Companion

    cs.CL 2025-07 conditional novelty 5.0 of 10

    H2HTalk is a new 4,650-scenario benchmark that scores LLM emotional companions on dialogue, memory, and itinerary planning, and finds models struggle with implicit needs and long-horizon memory.

  5. SimuPanel: A Novel Immersive Multi-Agent System to Simulate Interactive Expert Panel Discussion

    cs.HC 2025-06 conditional novelty 5.0 of 10

    A multi-agent LLM system called SimuPanel simulates expert panel discussions with personas grounded in public academic sources, and a small evaluation suggests the full reasoning pipeline produces higher LLM-judged di...

  6. Can Past Experience Accelerate LLM Reasoning?

    cs.LG 2025-05 conditional novelty 5.0 of 10

    LLMs can cut reasoning compute by up to 56% on similar questions when memory of past correct solutions is combined with adaptive early stopping, though the benchmark is small and synthetic.

  7. SPeCtrum: A Grounded Framework for Multidimensional Identity Representation in LLM-Based Agent

    cs.CL 2025-02 conditional novelty 5.0 of 10

    SPeCtrum shows that short personal essays (life context) are the most powerful identity signal for LLM personas of fictional characters, but real people rate a persona built from all three layers as most authentic.

  8. Rethinking Role-Playing Evaluation: Anonymous Benchmarking and a Systematic Study of Personality Effects

    cs.CL 2026-03 conditional novelty 4.0 of 10

    Hiding character names lowers role-play performance, and adding self-generated personality descriptions partially restores fidelity in anonymous role-playing.

Pith tools