Paper Citation Record · LEDGER

DVM: Towards Controllable LLM Agents in Social Deduction Games

As of 11 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 1 inbound Pith citation observation for arXiv:2501.06695.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2501.06695 v1

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T20:57:45.050254Z

measured 32 of 32 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:55:26.052077Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-07T14:55:29.503801Z

Reference resolution

31 of 31 outbound references displayed

verified exact1
verified fuzzy12
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e9e7b2ee-ba4d-4d42-8951-9420490a445b · outbound

This paper cites Language mod- els are few-shot learners,.

DVM: Towards Controllable LLM Agents in Social Deduction Games Language mod- els are few-shot learners,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T20:57:44.874657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8413c0c2-eece-48df-926e-c959947c4a4f · outbound

This paper cites Palm: Scal- ing language modeling with pathways,.

DVM: Towards Controllable LLM Agents in Social Deduction Games Palm: Scal- ing language modeling with pathways,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-10T20:57:44.880827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e78d7e85-c327-418d-bf48-75405cdca201 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

DVM: Towards Controllable LLM Agents in Social Deduction Games LLaMA: Open and Efficient Foundation Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-10T20:57:44.886449Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2271959-9051-465e-8db1-21fa5fc2bce3 · outbound

This paper cites Determinants of LLM-assisted Decision-Making.

DVM: Towards Controllable LLM Agents in Social Deduction Games Determinants of LLM-assisted Decision-Making

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-10T20:57:44.892856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e4931df-1ff8-4d5a-a747-b86dd9c2e3c8 · outbound

This paper cites A Survey on Large Language Model-Based Game Agents.

DVM: Towards Controllable LLM Agents in Social Deduction Games A Survey on Large Language Model-Based Game Agents

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-10T20:57:44.899515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dd40147-d179-4987-9d2a-8ddf3e38bae0 · outbound

This paper cites Cradle: Empowering Foundation Agents Towards General Computer Control.

DVM: Towards Controllable LLM Agents in Social Deduction Games Cradle: Empowering Foundation Agents Towards General Computer Control

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T20:57:44.906970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fc8d56f-fcc1-47b6-bb8a-29d2789067a3 · outbound

This paper cites Mp5: A multi-modal open-ended embodied system in minecraft via active perception,.

DVM: Towards Controllable LLM Agents in Social Deduction Games Mp5: A multi-modal open-ended embodied system in minecraft via active perception,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:57:45.863866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation b602c7e7-e2c3-4960-8e8a-54089ba6219d · outbound

This paper cites Describe, explain, plan and select: Interactive planning with LLMs enables open-world multi-task agents,.

DVM: Towards Controllable LLM Agents in Social Deduction Games Describe, explain, plan and select: Interactive planning with LLMs enables open-world multi-task agents,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:57:45.848296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 468961c1-04f2-4b22-9764-f4b2965dc247 · outbound

This paper cites V oyager: An open-ended embodied agent with large language models,.

DVM: Towards Controllable LLM Agents in Social Deduction Games V oyager: An open-ended embodied agent with large language models,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:57:45.832282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation adbc158d-911a-4905-956d-a8385a4530bd · outbound

This paper cites Baba is AI: Break the rules to beat the benchmark,.

DVM: Towards Controllable LLM Agents in Social Deduction Games Baba is AI: Break the rules to beat the benchmark,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:57:45.812978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 2542daa2-a17f-4239-ad82-648ad2e98045 · outbound

This paper cites Avalonbench: Evaluating LLMs playing the game of avalon,.

DVM: Towards Controllable LLM Agents in Social Deduction Games Avalonbench: Evaluating LLMs playing the game of avalon,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:57:45.790897Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation bdfee0b1-6063-4ec6-8d1e-867b33df333a · outbound

This paper cites Playing repeated games with Large Language Models.

DVM: Towards Controllable LLM Agents in Social Deduction Games Playing repeated games with Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T20:57:44.942547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 471ef80c-5718-4c39-9a72-c271c48bdd59 · outbound

This paper cites AMONGAGENTS: Evaluating Large Language Models in the Interactive Text-Based Social Deduction Game.

DVM: Towards Controllable LLM Agents in Social Deduction Games AMONGAGENTS: Evaluating Large Language Models in the Interactive Text-Based Social Deduction Game

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T20:57:44.947467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c1c9fc7-11c1-4678-bb3c-db38da5a3084 · outbound

This paper cites Microscopic analysis on llm players via social deduction game,.

DVM: Towards Controllable LLM Agents in Social Deduction Games Microscopic analysis on llm players via social deduction game,

Reference 14

Resolution: verified exact; raw_fallback, observed 2026-08-10T20:57:45.512341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation b8595c91-19a3-45c1-a304-ae3ce4fcc31e · outbound

This paper cites Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game.

DVM: Towards Controllable LLM Agents in Social Deduction Games Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-10T20:57:44.960655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4cde7d7-45d9-414c-bda1-ae517cba6b25 · outbound

This paper cites Enhance Reasoning for Large Language Models in the Game Werewolf.

DVM: Towards Controllable LLM Agents in Social Deduction Games Enhance Reasoning for Large Language Models in the Game Werewolf

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T20:57:44.966522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dde51aa-4792-4a1a-9e10-865396d5ce65 · outbound

This paper cites Emergent password signalling in the game of werewolf,.

DVM: Towards Controllable LLM Agents in Social Deduction Games Emergent password signalling in the game of werewolf,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:57:45.768458Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 3c87d585-8ddc-4bae-896a-8631fb0c9ece · outbound

This paper cites Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf.

DVM: Towards Controllable LLM Agents in Social Deduction Games Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-10T20:57:44.978500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2374452-d6c4-4c02-abb8-f6d5c736b536 · outbound

This paper cites Werewolf among us: Multimodal resources for modeling persuasion behaviors in social deduction games,.

DVM: Towards Controllable LLM Agents in Social Deduction Games Werewolf among us: Multimodal resources for modeling persuasion behaviors in social deduction games,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:57:45.749434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 0145ff2d-b4d6-4c4c-940b-5ee3ae778a33 · outbound

This paper cites Werewolf-xl: A database for identifying spontaneous affect in large competitive group interactions,.

DVM: Towards Controllable LLM Agents in Social Deduction Games Werewolf-xl: A database for identifying spontaneous affect in large competitive group interactions,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-10T20:57:44.988346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6826a58a-1c42-481c-bcf4-30fd5095764d · outbound

This paper cites Proximal Policy Optimization Algorithms.

DVM: Towards Controllable LLM Agents in Social Deduction Games Proximal Policy Optimization Algorithms

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T20:57:44.994010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c7ab567-64dc-4dce-8b9c-c543d0eb0dc8 · outbound

This paper cites Proximal policy optimization with mixed distributed training,.

DVM: Towards Controllable LLM Agents in Social Deduction Games Proximal policy optimization with mixed distributed training,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T20:57:45.000134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04894800-9558-4724-bd1d-cad8b2fefcfa · outbound

This paper cites Proximal policy optimization via enhanced exploration efficiency,.

DVM: Towards Controllable LLM Agents in Social Deduction Games Proximal policy optimization via enhanced exploration efficiency,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:57:45.731947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 2d81d20a-d9d1-4d13-822e-030374a7855a · outbound

This paper cites Secrets of RLHF in Large Language Models Part I: PPO.

DVM: Towards Controllable LLM Agents in Social Deduction Games Secrets of RLHF in Large Language Models Part I: PPO

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T20:57:45.011114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f74dfe4-ddea-4706-b0a4-731da9010679 · outbound

This paper cites Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study.

DVM: Towards Controllable LLM Agents in Social Deduction Games Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-10T20:57:45.016486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa235c4c-6abd-42c2-a020-5a79bc58a8f6 · outbound

This paper cites A theoretical analysis of optimistic proximal policy optimization in linear markov decision processes,.

DVM: Towards Controllable LLM Agents in Social Deduction Games A theoretical analysis of optimistic proximal policy optimization in linear markov decision processes,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:57:45.714650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation dc4e5840-d085-4ffb-b73f-74cfe5ec6a6d · outbound

This paper cites Finding friend and foe in multi-agent games,.

DVM: Towards Controllable LLM Agents in Social Deduction Games Finding friend and foe in multi-agent games,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:57:45.695214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation da40be48-1122-468d-8c48-e5c5ecde9d40 · outbound

This paper cites Chatglm: A family of large language models from glm-130b to glm-4 all tools,.

DVM: Towards Controllable LLM Agents in Social Deduction Games Chatglm: A family of large language models from glm-130b to glm-4 all tools,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-10T20:57:45.033170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56f6ffd7-09c7-4db5-9c00-a15a3890d821 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model,.

DVM: Towards Controllable LLM Agents in Social Deduction Games Direct preference optimization: Your language model is secretly a reward model,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:57:45.668877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 8b717e92-4a91-440e-9aa1-22a4870e1697 · outbound

This paper cites ReAct: Synergizing Reasoning and Acting in Language Models.

DVM: Towards Controllable LLM Agents in Social Deduction Games ReAct: Synergizing Reasoning and Acting in Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-10T20:57:45.044229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d15f9e8-5e92-496b-a182-f7ab1b5c780a · outbound

This paper cites Least-to-most prompting enables complex reasoning in large language models,.

DVM: Towards Controllable LLM Agents in Social Deduction Games Least-to-most prompting enables complex reasoning in large language models,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:57:45.647655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Pith citing papers

Observation 90c2a39f-f7bc-4831-9126-30e24ae2aedc · inbound

Cracking Aegis: An Adversarial LLM-based Game for Raising Awareness of Vulnerabilities in Privacy Protection cites this paper.

Cracking Aegis: An Adversarial LLM-based Game for Raising Awareness of Vulnerabilities in Privacy Protection DVM: Towards Controllable LLM Agents in Social Deduction Games

Reference 149

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:55:29.578410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.