One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL | Paper Citation Record

Observation ea338534-eff5-4f60-b471-4449fd62e289 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.453312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c737c19-cd18-448f-90d1-888e0e7f4e82 · outbound

This paper cites Understanding R1-Zero-Like Training: A Critical Perspective.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Understanding R1-Zero-Like Training: A Critical Perspective

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.460262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a79b4430-5332-4d40-8254-c46cd54e5875 · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.465639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9878a06f-50fd-4c68-a7f5-23ce74c7ed8b · outbound

This paper cites ReTool: Reinforcement Learning for Strategic Tool Use in LLMs.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL ReTool: Reinforcement Learning for Strategic Tool Use in LLMs

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.471444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc2336a1-ff6b-40d7-9e78-707c7ae155b0 · outbound

This paper cites Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.476116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66688e70-7873-4b78-b699-10b0eabd0654 · outbound

This paper cites SWE-smith: Scaling Data for Software Engineering Agents.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL SWE-smith: Scaling Data for Software Engineering Agents

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.480953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 757ed77b-732e-4bc0-baab-0d2158e02df5 · outbound

This paper cites SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.486458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a71afce6-d652-4621-aa52-428c2a44339f · outbound

This paper cites UserRL: Training Interactive User-Centric Agent via Reinforcement Learning, September.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL UserRL: Training Interactive User-Centric Agent via Reinforcement Learning, September

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:15:07.001260Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8fc7d44e-c8c1-40e2-8039-afce0e969ef4 · outbound

This paper cites TOM-SWE: User Mental Modeling For Software Engineering Agents, October 2025.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL TOM-SWE: User Mental Modeling For Software Engineering Agents, October 2025

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.500306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56c06e39-cbb7-4a26-b23a-53b036d7c4f2 · outbound

This paper cites HumanLM: Simulating Users with State Alignment Beats Response Imitation, February 2026.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL HumanLM: Simulating Users with State Alignment Beats Response Imitation, February 2026

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.504225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 558deb1f-850c-47cf-a278-ee375086da82 · outbound

This paper cites $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.507966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e3bdbe8-e2ec-455f-8129-2d9b8a6e7f86 · outbound

This paper cites Lieberwirth, Xinkai Yu, Yicheng Fu, Michael J.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Lieberwirth, Xinkai Yu, Yicheng Fu, Michael J

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.511940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3ec8aee-1627-4f78-a2f2-0d710c2bc7d2 · outbound

This paper cites Position: Humans are missing from ai coding agent research.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Position: Humans are missing from ai coding agent research

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:15:06.986895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 83b9cb85-b2d3-435b-86c3-92d328846d39 · outbound

This paper cites Persuasion for good: Towards a personalized persuasive dialogue system for social good.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Persuasion for good: Towards a personalized persuasive dialogue system for social good

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:15:06.972671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 73bb10d5-7452-4c18-91d9-21ef361ab848 · outbound

This paper cites Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning, October.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning, October

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.524125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 354ddfcc-ccf8-446b-a58b-ad800dfc1ed8 · outbound

This paper cites Bernstein.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Bernstein

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.533329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81d1c642-83c0-4b21-a540-5ea5a779176d · outbound

This paper cites arXiv:2511.00222 [cs].

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL arXiv:2511.00222 [cs]

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.528529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f1cec51-b85e-4999-b8a3-a21dde612dc8 · outbound

This paper cites Sotopia-RL: Reward Design for Social Intelligence, October 2025.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Sotopia-RL: Reward Design for Social Intelligence, October 2025

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.542316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53ce8f94-5f2f-409d-80d2-36873209c9da · outbound

This paper cites LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.537288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ece0c50-a8cc-47e5-b206-4a5bb9d7f39a · outbound

This paper cites Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond), October 2025.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond), October 2025

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.551128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0826ad6c-26d8-47a0-9f7d-84241ab7d5f9 · outbound

This paper cites LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.546670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c759508-dca8-4e29-9d72-620b09e13353 · outbound

This paper cites Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.558740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a82446fb-cdb2-44c9-94d3-738c206b6ebc · outbound

This paper cites KL-regularized reinforcement learning is designed to mode collapse, 2025.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL KL-regularized reinforcement learning is designed to mode collapse, 2025

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.555118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5187323f-70e8-4871-b27b-b894c734c55f · outbound

This paper cites Chasing moving targets with online self-play reinforcement learning for safer language models, 2025.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Chasing moving targets with online self-play reinforcement learning for safer language models, 2025

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.568741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b5f4f66-123a-4944-8531-c3cb8d585c11 · outbound

This paper cites Natural emergent misalignment from reward hacking in production RL, 2025.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Natural emergent misalignment from reward hacking in production RL, 2025

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.564081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a2e3376-0928-46c9-9f6e-382e2fc0b6d0 · outbound

This paper cites Williams.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Williams

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.577287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78310470-81af-40b0-8f96-2253d485a236 · outbound

This paper cites SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning, July 2025.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning, July 2025

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.573268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79b4edda-9754-47ec-bf58-3e997bd46958 · outbound

This paper cites Flipping the Dialogue: Training and Evaluating User Language Models, October 2025.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Flipping the Dialogue: Training and Evaluating User Language Models, October 2025

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.590001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66956b33-e5c5-4f58-b112-8a0619171687 · outbound

This paper cites Noveltybench: Evaluating language models for humanlike diversity,.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Noveltybench: Evaluating language models for humanlike diversity,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:15:06.942798Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c524adc3-b61f-4a28-ad18-499a4ec70cbd · outbound

This paper cites NoveltyBench: Evaluating Language Models for Humanlike Diversity.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL NoveltyBench: Evaluating Language Models for Humanlike Diversity

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.585634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 500f716f-e128-4c32-a457-ba34fed773ea · outbound

This paper cites SPICE: Self-Play In Corpus Environments Improves Reasoning, October 2025.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL SPICE: Self-Play In Corpus Environments Improves Reasoning, October 2025

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.602450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f747676c-b894-444b-9219-ced9c253466b · outbound

This paper cites Mind the Sim2Real Gap in User Simulation for Agentic Tasks.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Mind the Sim2Real Gap in User Simulation for Agentic Tasks

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.593555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29fce8ca-4b7b-4ce2-b59d-c7f8cc5b66d9 · outbound

This paper cites Measuring and Mitigating the Distributional Gap Between Real and Simulated User Behaviors.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Measuring and Mitigating the Distributional Gap Between Real and Simulated User Behaviors

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-08-16T00:15:05.782484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e5a69584-fcaf-4d86-9026-f1b8ba864561 · outbound

This paper cites RAGEN-2: Reasoning Collapse in Agentic RL.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL RAGEN-2: Reasoning Collapse in Agentic RL

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.613847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35736ef2-fde6-4f85-8a06-f8422e014cf9 · outbound

This paper cites Hi- erarchical agenda reasoning for strategic multi-turn dialogue agents.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Hi- erarchical agenda reasoning for strategic multi-turn dialogue agents

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:15:06.927989Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7a78fb76-ff17-4df9-9991-59e7de1a0857 · outbound

This paper cites Llm probability concentration: How alignment shrinks the generative horizon, 2025.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Llm probability concentration: How alignment shrinks the generative horizon, 2025

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.610256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d46331dc-b1ae-4f63-97d0-e5f686348cc2 · outbound

This paper cites MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.627801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad985377-0b6b-436b-8bb0-52cfc35b826b · outbound

This paper cites The Chameleon's Limit: Investigating Persona Collapse and Homogenization in Large Language Models.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL The Chameleon's Limit: Investigating Persona Collapse and Homogenization in Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.617997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9dd7c70-72cd-4694-9e11-3fa92c1170f7 · outbound

This paper cites LLM Social Simulations Are a Promising Research Method.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL LLM Social Simulations Are a Promising Research Method

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.623422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe626c99-dc7f-4f61-a654-bc4936757de8 · outbound

This paper cites Beyond Cooperative Simulators: Generating Realistic User Personas for Robust Evaluation of LLM Agents.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Beyond Cooperative Simulators: Generating Realistic User Personas for Robust Evaluation of LLM Agents

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.642064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e90aac5-60d9-4210-830d-76adf774ed7e · outbound

This paper cites Training Proactive and Personalized LLM Agents, November 2025.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Training Proactive and Personalized LLM Agents, November 2025

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.632848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a0c0564-38f9-4f7b-be63-d0b313474b43 · outbound

This paper cites an unresolved cited work.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Unresolved cited work

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.637451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4085fdb1-4365-4202-aa57-da42c1199097 · outbound

This paper cites Enhancing personalized multi-turn dialogue with curiosity reward, 2025.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Enhancing personalized multi-turn dialogue with curiosity reward, 2025

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.654081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ee0ed04-67ad-4600-82c0-53b2f33555f1 · outbound

This paper cites Quantifying the Utility of User Simulators for Building Collaborative LLM Assistants.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Quantifying the Utility of User Simulators for Building Collaborative LLM Assistants

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-08-16T00:15:05.239896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a8357c08-443e-43b1-b8ac-30337175e0d9 · outbound

This paper cites Non- collaborative user simulators for tool agents, September 2025.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Non- collaborative user simulators for tool agents, September 2025

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.650372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ace82092-9a6c-4c0d-944a-246df5695d30 · outbound

This paper cites Dota 2 with Large Scale Deep Reinforcement Learning.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Dota 2 with Large Scale Deep Reinforcement Learning

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.669651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 070cc558-62ca-4e34-81d2-7ec53b558aab · outbound

This paper cites Multi-User Large Language Model Agents.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Multi-User Large Language Model Agents

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.658345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f82917b2-2ab5-4a64-b603-54e0e999b232 · outbound

This paper cites an unresolved cited work.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Unresolved cited work

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.663523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93466362-ff19-47fc-bd89-79c4fcf393b6 · outbound

This paper cites Coevolving with the other you: Fine-tuning LLM with sequential cooperative multi-agent reinforcement learning.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Coevolving with the other you: Fine-tuning LLM with sequential cooperative multi-agent reinforcement learning

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:15:06.914295Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 47ad6414-e8a4-4302-8dd4-6dac1276fd00 · outbound

This paper cites Absolute Zero: Reinforced Self-play Reasoning with Zero Data.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Absolute Zero: Reinforced Self-play Reasoning with Zero Data

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.674667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e0d651d-7a12-429a-b7ed-7ec8b4a1abfa · outbound

This paper cites Efficacy of Language Model Self-Play in Non-Zero-Sum Games.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Efficacy of Language Model Self-Play in Non-Zero-Sum Games

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.678569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c457f6f-b581-4af4-ac77-d68b18bbca7f · outbound

This paper cites SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.693596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63c1f234-8256-4890-af30-af80c11a030d · outbound

This paper cites an unresolved cited work.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Unresolved cited work

Reference 53

Resolution: unresolved; raw_fallback, observed 2026-08-16T00:15:06.900484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d64f14a8-bfb1-4203-b8e9-ada6c586c6b1 · outbound

This paper cites Tool-R0: Self-evolving LLM agents for tool-learning from zero data, 2026.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Tool-R0: Self-evolving LLM agents for tool-learning from zero data, 2026

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:15:06.887983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d516b38c-3679-40e4-9459-4b727b4c1c38 · outbound

This paper cites Manning, Stefano Ermon, and Chelsea Finn.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Manning, Stefano Ermon, and Chelsea Finn

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:15:06.873951Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a7a17a8e-a712-41c7-9b63-b7075dee5a45 · outbound

This paper cites Natural Language Actor- Critic: Scalable Off-Policy Learning in Language Space, December 2025.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Natural Language Actor- Critic: Scalable Off-Policy Learning in Language Space, December 2025

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.697681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1cb2f5c-9429-4353-a794-7ef920329924 · outbound

This paper cites Ma, Seun Eisape, Ellie French, Tingting Du, Tianjiao Zhang, Alexander Koller, and Alane Suhr.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Ma, Seun Eisape, Ellie French, Tingting Du, Tianjiao Zhang, Alexander Koller, and Alane Suhr

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.701587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0b5a150-ffbf-49ad-a1e3-8cbaf1a3e4aa · outbound

This paper cites OpenAI Gym.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL OpenAI Gym

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.719186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 904f6f92-78bf-45fc-aa6b-145d9552b2d0 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.710147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3adb7e51-8235-488b-b820-79e5e5a13341 · outbound

This paper cites Proximal Policy Optimization Algorithms.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Proximal Policy Optimization Algorithms

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.714785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3fcff93-69b1-487c-ba01-85caeb68a3b1 · outbound

This paper cites slime: An llm post-training framework for rl scaling.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL slime: An llm post-training framework for rl scaling

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.731708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1252219-a1fd-4789-85e7-d96bcc40214c · outbound

This paper cites SGLang: Efficient Execution of Structured Language Model Programs.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL SGLang: Efficient Execution of Structured Language Model Programs

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.723393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83045f16-1c71-4538-b8b6-a9be9f71207b · outbound

This paper cites Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.727651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbbdf98a-1e51-4c62-8d99-6498a90f2f81 · outbound

This paper cites Qwen3.5: Towards native multimodal agents, February 2026.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Qwen3.5: Towards native multimodal agents, February 2026

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.743354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c53bbcc-df9b-4991-aaf0-e03e05a32f86 · outbound

This paper cites HybridFlow: A flexible and efficient RLHF framework.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL HybridFlow: A flexible and efficient RLHF framework

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:15:06.853370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 14b14b77-d4f0-4ad5-ace9-8ac3a8523a23 · outbound

This paper cites AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs

Reference 66

Resolution: metadata mismatch; local_arxiv, observed 2026-08-16T00:15:04.855445Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5ca3e580-9a2d-456c-8bdd-442861246c0c · outbound

This paper cites Olmo 3.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Olmo 3

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.747165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5d1f561-7b71-410b-b4d5-0a4db8808385 · outbound

This paper cites SPIRAL [ 25], SPICE [31], Absolute Zero [47]): one model serves both roles with role-specific loss masks.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL SPIRAL [ 25], SPICE [31], Absolute Zero [47]): one model serves both roles with role-specific loss masks

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:15:06.833814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 35a6214d-db4a-424a-9e49-e27de0c33ac4 · outbound

This paper cites an unresolved cited work.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Unresolved cited work

Reference 70

Resolution: unresolved; raw_fallback, observed 2026-08-16T00:15:06.821870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 638d7632-dfa5-486d-a1a7-6542aa1c841d · outbound

This paper cites Updated?.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Updated?

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:15:06.809353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 46274806-3801-4e2e-85fa-08471e40c932 · outbound

This paper cites an unresolved cited work.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Unresolved cited work

Reference 72

Resolution: parse uncertain; raw_fallback, observed 2026-08-16T00:15:06.797513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f161cbfc-21f5-4bc0-aa22-439f28c13bee · outbound

This paper cites an unresolved cited work.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Unresolved cited work

Reference 73

Resolution: unresolved; raw_fallback, observed 2026-08-16T00:15:06.785421Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 494a49c9-ada6-4e4a-9c7d-ef6d159a6d21 · outbound

This paper cites an unresolved cited work.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Unresolved cited work

Reference 74

Resolution: unresolved; raw_fallback, observed 2026-08-16T00:15:06.772211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ba90d65d-a7c0-45aa-bcbe-c085f99c2fce · outbound

This paper cites responses.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL responses

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:15:06.757652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 39f02e0f-dbb2-40b5-ae65-3044662a48e9 · outbound

This paper cites arXiv:2509.19736 [cs].

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL arXiv:2509.19736 [cs]

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-16T00:15:04.495639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers