mlsanityData to 13 Oct 2026

SOTOPIA-Omega: Dynamic Strategy Injection Learning and Social Instruction Following Evaluation for Social Agents

arXiv 2502.15538 ↗First posted 21 Feb 2025cs.CL cs.CY cs.HCcited by 16

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Despite the abundance of prior social strategies possessed by humans, there remains a paucity of research dedicated to their transfer and integration into social agents. Our proposed SOTOPIA-Omega framework aims to address and bridge this gap, with a particular focus on enhancing the social capabilities of language agents. This framework dynamically injects multi-step reasoning strategies inspired by negotiation theory and two simple direct strategies into expert agents, thereby automating the construction of a high-quality social dialogue training corpus. Additionally, we introduce the concept of Social Instruction Following (S-IF) and propose two new S-IF evaluation metrics that complement social capability. We demonstrate that several 7B models trained on high-quality corpus not only significantly surpass the expert agent (GPT-4) in achieving social goals but also enhance S-IF performance. Analysis and variant experiments validate the advantages of dynamic construction, which can especially break the agent's prolonged deadlock.

Key facts. Cited by 16 papers in the map (data through 13 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 51 of its 89 references that are in the map. First posted on arXiv 21 Feb 2025.

Builds on

51 of 89 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024AgentSense: Benchmarking Social Intelligence of Language Agents through Interactive Scenarios25 Oct
  2. 2024SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agents13 Mar
  3. 2023Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents1 Nov
  4. 2023SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents18 Oct
  5. 2023SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks27 May

Other references · 46

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,231
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,492
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,541
  4. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,450
  5. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,362
  6. 2023Character-LLM: A Trainable Agent for Role-Playingcited by 336
  7. 2024MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialoguescited by 250
  8. 2022Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMscited by 220
  9. 2024Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalizationcited by 208
  10. 2023InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviewscited by 178
  11. 2022ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoningcited by 176
  12. 2024Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustmentcited by 174
34 more
  1. 2024Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systemscited by 163
  2. 2018Decoupling Strategy and Generation in Negotiation Dialoguescited by 159
  3. 2024MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmarkcited by 103
  4. 2023Wider and Deeper LLM Networks are Fairer LLM Evaluatorscited by 92
  5. 2024From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agentscited by 81
  6. 2023Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arenacited by 78
  7. 2024CFBench: A Comprehensive Constraints-Following Benchmark for LLMscited by 65
  8. 2023LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplaycited by 63
  9. 2023Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmarkcited by 62
  10. 2023NormBank: A Knowledge Bank of Situational Social Normscited by 60
  11. 2023CharacterChat: Learning towards Conversational AI with Personalized Social Supportcited by 59
  12. 2024Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMscited by 59
  13. 2025Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinkingcited by 57
  14. 2024Game-theoretic LLM: Agent Workflow for Negotiation Gamescited by 55
  15. 2024Measuring and Controlling Instruction (In)Stability in Language Model Dialogscited by 53
  16. 2024SocialBench: Sociality Evaluation of Role-Playing Conversational Agentscited by 49
  17. 2023A Comprehensive Analysis of the Effectiveness of Large Language Models as Automatic Dialogue Evaluatorscited by 45
  18. 2024Thinking LLMs: General Instruction Following with Thought Generationcited by 45
  19. 2024On the Multi-turn Instruction Following for Conversational Web Agentscited by 43
  20. 2020Improving Dialog Systems for Negotiation with Personality Modelingcited by 37
  21. 2024FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMscited by 36
  22. 2024IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimizationcited by 31
  23. 2024Strength Lies in Differences! Improving Strategy Planning for Non-collaborative Dialogues via Diversified User Simulationcited by 21
  24. 2024Mitigating Hallucination in Fictional Character Role-Playcited by 18
  25. 2024The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trendscited by 11
  26. 2024Don't Half-listen: Capturing Key-part Information in Continual Instruction Tuningcited by 10
  27. 2024Soda-Eval: Open-Domain Dialogue Evaluation in the age of LLMscited by 10
  28. 2024Injecting Salesperson's Dialogue Strategies in Large Language Models with Chain-of-Thought Reasoningcited by 9
  29. 2024Revealing and Mitigating the Challenge of Detecting Character Knowledge Errors in LLM Role-Playingcited by 9
  30. 2024DEMO: Reframing Dialogue Interaction with Fine-grained Element Modelingcited by 6
  31. 2024Optimal Transport Guided Correlation Assignment for Multimodal Entity Linkingcited by 5
  32. 2023Dynamic Multi-Scale Context Aggregation for Conversational Aspect-Based Sentiment Quadruple Analysiscited by 4
  33. 2024Rethinking the Evaluation of Dialogue Systems: Effects of User Feedback on Crowdworkers and LLMscited by 2
  34. 2024Adaptive Data Augmentation for Aspect Sentiment Quad Predictioncited by 1

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2025: 6; 2026: 10.

16 papers.

Sort:

By area:

  1. 2026ExpSeek: Self-Triggered Experience Seeking for Web Agentscited by 23
  2. 2025Sotopia-RL: Reward Design for Social Intelligencecited by 22
  3. 2025Adaptive Social Learning via Mode Policy Optimization for Language Agentscited by 15
  4. 2025Exploring the System 1 Thinking Capability of Large Reasoning Modelscited by 10
  5. 2025Agentic Services Computingcited by 6
  6. 2026Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generationcited by 5
  7. 2026ActorMind: Emulating Human Actor Reasoning for Speech Role-Playingcited by 4
  8. 2025The Stackelberg Speaker: Optimizing Persuasive Communication in Social Deduction Gamescited by 3
  9. 2026SAVOIR: Learning Social Savoir-Faire via Shapley-based Reward Attributioncited by 3
  10. 2026Towards Better Agents for Multi-Turn User Interaction: The Next User Turn Is More Than Contextcited by 1
  11. 2025ToMPO: Training LLM Strategic Decision Making from a Multi-Agent Perspectivecited by 0
  12. 2026Beneath the Surface: Investigating LLMs' Capabilities for Communicating with Subtextcited by 0
4 more
  1. 2026SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variationscited by 0
  2. 2026From Blueprint to Reality: Modeling and Applying Putnam's Social Capital Theory with LLM-based Multi-agent Simulationscited by 0
  3. 2026Enhancing Social Intelligence in LLMs with Hierarchical Reasoning and Utterance-Level Goal Rewardingcited by 0
  4. 2026Towards Communication-Efficient Social Intelligence in Language Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025LIFELONG SOTOPIA: Evaluating Social Intelligence of Language Agents Over Lifelong Social Interactions
  2. 2024Towards Objectively Benchmarking Social Intelligence for Language Agents at Action Level
  3. 2026From Passive Delegates to Strategic Negotiators: Reinforcing Social Reasoning in Small Language Models with SocialRL
  4. 2025SI-Bench: Benchmarking Social Intelligence of Large Language Models in Human-to-Human Conversations
  5. 2026SocialRL: Refining LLMs' Social Intelligence through Multi-turn Reinforcement Learning and Reward Design
  6. 2025AI Pedagogy: Dialogic Social Learning for Artificial Agents
  7. 2026Social World Model for Lifelong Social Intelligence
  8. 2026Social-R1: Towards Human-like Social Reasoning in LLMs