Metraipolis › archive › dc_f15546eec85d

TradeWar: A Benchmark for Execution-Grounded Trade Negotiation with Adaptive LLM Agents — arXiv:2610.42004

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.42004
License (as archived)
CC0-1.0
Archived
2026-11-03T07:32:23.265Z
SHA-256 of the archived text
ba0fc641979c9aa1a6c8c2dbd32f64e8b8163470fd127c5cbc2d6529ab372840
Stable URL of this page
https://metraipolis.com/documento/dc_f15546eec85d

How to cite

TradeWar: A Benchmark for Execution-Grounded Trade Negotiation with Adaptive LLM Agents — arXiv:2610.42004 — arXiv (en), https://arxiv.org/abs/2610.42004 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f15546eec85d (Metraipolis archive dc_f15546eec85d, sha256 ba0fc641979c9aa1a6c8c2dbd32f64e8b8163470fd127c5cbc2d6529ab372840)
BibTeX
@misc{dcf15546eec85d,
  title = {TradeWar: A Benchmark for Execution-Grounded Trade Negotiation with Adaptive LLM Agents — arXiv:2610.42004},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.42004},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f15546eec85d; sha256 ba0fc641979c9aa1a6c8c2dbd32f64e8b8163470fd127c5cbc2d6529ab372840},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.42004. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-turn negotiation remains a challenging problem for large language model (LLM) agents. While LLMs can conduct natural-language dialogue, existing benchmarks predominantly assess only agreement rates, overlooking whether negotiated commitments actually create value once executed. To address this gap, we introduce TradeWar, a multi-country simulation benchmark that translates negotiation dialogues into concrete tariff and trade-share policies, enforces capacity and network constraints during settlement, and evaluates outcomes via an Economic Health Index (EHI). To solve this execution-grounded task, we propose TACTIC (Trade-aware Adaptive Consolidation and Theory-of-mind for International Commerce), an agent that iteratively refines its negotiation strategy across episodes-without updating base LLM weights-by leveraging prior experience, opponent behavior, and past settlement outcomes. Despite using zero-shot chain-of-thought (CoT) prompting, PromptLLM attains a 75% agreement rate but only 57.1 final EHI (*100), whereas TACTIC reaches 68.8. Across 20 sequential episodes and three seeds, TACTIC's final EHI improves from 58.2 to 73.2, compared with 65.2 for an ablation without cross-episode updates. Under technology-controls and energy-crisis shocks, TACTIC also exhibits smaller performance degradation than PromptLLM and MemoryLLM. These results indicate that CoT deliberation and interaction memory alone do not fully address delayed execution feedback, whereas settlement-grounded adaptation improves long-horizon negotiation in TradeWar.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.42004 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T07:29:33.661Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).