mlsanityData to 7 Oct 2026

ASTRA: A Negotiation Agent with Adaptive and Strategic Reasoning via Tool-integrated Action for Dynamic Offer Optimization

arXiv 2503.07129 ↗First posted 10 Mar 2025cs.CL cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Negotiation requires dynamically balancing self-interest and cooperation within the flow of conversation to maximize one's own utility. Yet, existing agents struggle due to bounded rationality in human data, low adaptability to counterpart behavior, and limited strategic reasoning. To address this, we introduce principle-driven negotiation agents, powered by ASTRA, a novel framework for turn-level offer optimization grounded in two core principles: opponent modeling and Tit-for-Tat reciprocity. ASTRA operates in three stages: (1) interpreting counterpart behavior, (2) optimizing counteroffers via a tool-integrated action with a linear programming (LP) solver, and (3) selecting offers based on strategy assessment and the partner's acceptance probability. Through simulations and human evaluations, our agent effectively adapts to an opponent's shifting stance and achieves favorable outcomes through enhanced adaptability and strategic reasoning. Beyond enhancing negotiation performance, it also serves as a powerful coaching tool, offering interpretable strategic feedback and optimal offer recommendations beyond human bounded rationality, with its potential further validated through human evaluation.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 20 of its 40 references that are in the map. First posted on arXiv 10 Mar 2025.

Builds on

20 of 40 references.

References · 20

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2017Deal or No Deal? End-to-End Learning for Negotiation Dialoguescited by 202
  4. 2023Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedbackcited by 202
  5. 2018Decoupling Strategy and Generation in Negotiation Dialoguescited by 156
  6. 2023Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaborationcited by 115
  7. 2023Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiationcited by 94
  8. 2024How Well Can LLMs Negotiate? NegotiationArena Platform and Analysiscited by 93
  9. 2023Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arenacited by 78
  10. 2021CaSiNo: A Corpus of Campsite Negotiation Dialogues for Automatic Negotiation Systemscited by 60
  11. 2024Game-theoretic LLM: Agent Workflow for Negotiation Gamescited by 55
  12. 2024Measuring Bargaining Abilities of LLMs: A Benchmark and A Buyer-Enhancement Methodcited by 44
8 more
  1. 2020Improving Dialog Systems for Negotiation with Personality Modelingcited by 37
  2. 2024Are LLMs Effective Negotiators? Systematic Evaluation of the Multifaceted Capabilities of LLMs in Negotiation Dialoguescited by 29
  3. 2020Learning Goal-oriented Dialogue Policy with Opposite Agent Awarenesscited by 16
  4. 2023Reverse Chain: A Generic-Rule for LLMs to Master Multi-API Planningcited by 16
  5. 2023Negotiating with LLMS: Prompt Hacks, Skill Gaps, and Reasoning Deficitscited by 16
  6. 2023Be Selfish, But Wisely: Investigating the Impact of Agent Personality in Mixed-Motive Human-Agent Interactionscited by 15
  7. 2022Opponent Modeling in Negotiation Dialogues by Related Data Adaptationcited by 13
  8. 2024ACE: A LLM-based Negotiation Coaching Systemcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Multi-User Large Language Model Agentscited by 6
  2. 2026MERIT Feedback Elicits Better Bargaining in LLM Negotiatorscited by 2
  3. 2026Why Do LLMs Struggle in Strategic Play? Broken Links Between Observations, Beliefs, and Actionscited by 2
  4. 2026DPBench: Structural Determinants of Multi-Agent LLM Coordination Under Simultaneous Resource Contentioncited by 1