EvoTac: A Self-Evolving LLM Agent for Eliciting Reusable Tacit Negotiation Heuristics from Terminal Outcomes

ACL ARR 2026 January Submission575 Authors

Keywords: negotiation, tacit knowledge, large language models, memory, cognitive agents

Abstract: We propose EvoTac, an LLM-based framework for real-world negotiation that converts sparse terminal outcomes into reusable tacit experience without fine-tuning the base model. It continuously adapts to changing opponents and scenarios through a simple predict-reflect-update loop, using decoupled layered memory to represent the agent's constraints, observed opponent behavior patterns, and persistent hypotheses about opponent stance/type. Experiments on a large-scale online marketing negotiation task (predicting final commission rates) show that EvoTac outperforms traditional models and multiple LLM baselines in prediction accuracy and first-round offer hit rate.

Paper Type: Long

Research Area: AI/LLM Agents

Research Area Keywords: LLM/AI agents, financial/business NLP

Contribution Types: NLP engineering experiment, Theory

Languages Studied: English

Submission Number: 575