# From Passive Delegates to Strategic Negotiators: Reinforcing Social Reasoning in Small Language Models with SocialRL

arXiv: https://arxiv.org/abs/2608.13787 · HTML: https://mlsanity.com/paper/2608.13787/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 45 of its 56 references that are in the map.
- First posted on arXiv 13 Aug 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 30 of 45)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models](https://mlsanity.com/paper/2508.06471/) (2025)
- [Understanding the Effects of RLHF on LLM Generalisation and Diversity](https://mlsanity.com/paper/2310.06452/) (2023)
- [RLHF Workflow: From Reward Modeling to Online RLHF](https://mlsanity.com/paper/2405.07863/) (2024)
- [Deal or No Deal? End-to-End Learning for Negotiation Dialogues](https://mlsanity.com/paper/1706.05125/) (2017)
- [Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback](https://mlsanity.com/paper/2305.10142/) (2023)
- [Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation](https://mlsanity.com/paper/2602.12125/) (2026)
- [Decoupling Strategy and Generation in Negotiation Dialogues](https://mlsanity.com/paper/1808.09637/) (2018)
- [Agent Lightning: Train ANY AI Agents with Reinforcement Learning](https://mlsanity.com/paper/2508.03680/) (2025)
- [How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis](https://mlsanity.com/paper/2402.05863/) (2024)
- [SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agents](https://mlsanity.com/paper/2403.08715/) (2024)
- [OpenClaw-RL: Train Any Agent Simply by Talking](https://mlsanity.com/paper/2603.10165/) (2026)
- [MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training](https://mlsanity.com/paper/2606.30406/) (2026)
- [Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning](https://mlsanity.com/paper/2602.10090/) (2026)
- [Authenticated Delegation and Authorized AI Agents](https://mlsanity.com/paper/2501.09674/) (2025)
- [CaSiNo: A Corpus of Campsite Negotiation Dialogues for Automatic Negotiation Systems](https://mlsanity.com/paper/2103.15721/) (2021)
- [Game-theoretic LLM: Agent Workflow for Negotiation Games](https://mlsanity.com/paper/2411.05990/) (2024)
- [Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models](https://mlsanity.com/paper/2512.13607/) (2025)
- [Fara-7B: An Efficient Agentic Model for Computer Use](https://mlsanity.com/paper/2511.19663/) (2025)
- [MAGPIE: A benchmark for Multi-AGent contextual PrIvacy Evaluation](https://mlsanity.com/paper/2510.15186/) (2025)
- [Sotopia-RL: Reward Design for Social Intelligence](https://mlsanity.com/paper/2508.03905/) (2025)
- [EvoTool: Self-Evolving Tool-Use Policy Optimization in LLM Agents via Blame-Aware Mutation and Diversity-Aware Selection](https://mlsanity.com/paper/2603.04900/) (2026)
- [What Is Your AI Agent Buying? Evaluation, Biases, Model Dependence, & Emerging Implications for Agentic E-Commerce](https://mlsanity.com/paper/2508.02630/) (2025)
- [Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human States](https://mlsanity.com/paper/2505.17663/) (2025)
- [Efficacy of Language Model Self-Play in Non-Zero-Sum Games](https://mlsanity.com/paper/2406.18872/) (2024)

## Abstract (arXiv)

AI agents increasingly act on their users' behalf, handling tasks such as scheduling meetings, comparing offers, and haggling over prices. These principal-driven tasks routinely place the agent across from a counterpart (another user's agent, a seller, a recruiter) whose goals may conflict with its principal's. Yet the dispositions that make an assistant pleasant can make it a poor delegate: a friendly, helpful frontier model may disclose its principal's private information unprompted and concede at the first sign of resistance. We present SocialRL, a general recipe that trains social reasoning directly, and apply it to a 4B model across six domains: Deal-or-No-Deal, CaSiNo, Craigslist, Job Interview, Calendar, and Marketplace. Every domain is trained in-domain under the same recipe, and every policy is evaluated on all six. We find that (1) in-domain training reaches the frontier: on held-out scenarios the 4B matches or exceeds the GPT-5 family per domain, closing 73-122% of the baseline-to-frontier gap on the negotiation games, with 78% of buyer openings anchoring below target versus 3% untrained; (2) cross-domain transfer follows game structure: structurally paired games lift each other, a broad multi-issue donor lifts nearly all domains, and structurally isolated games transfer nothing; (3) guided by this transfer structure, two strategies, cascade RL and multi-teacher on-policy distillation (OPD), consolidate the per-domain specialists into a single unified 4B that reaches 0.627 average utility across all six environments, matching or exceeding GPT-4.1 (0.625), GPT-5.1 (0.619), and GPT-5.2 (0.613); (4) an explicit theory-of-mind scaffold helps only through training: distilling the ToM trace, rather than actions alone, lifts utility on every environment and generalizes better across them, and of the two ToM skills, only next-action prediction predicts negotiation outcomes.