Tag
A developer built a 6-agent AI system for satellite collision avoidance in 4 days for a hackathon, sharing lessons learned.
Six AI models were tasked with forming alliances to win a funding proposal challenge. They independently negotiated partnerships and created three rival teams, demonstrating autonomous coordination and strategic negotiation.
This paper introduces an automated mediator for human negotiation that uses a structured pipeline of LLM modules to conduct pre-mediation. In human-subject experiments, the system achieves preparation outcomes comparable to professional human mediators while reducing error in preference inference.
An insurance claims adjuster describes how auto lenders are deploying AI bots to dispute total loss vehicle valuations using inaccurate data, wasting adjusters' time and making it difficult to reach human representatives. The post seeks advice on bypassing these AI systems to speak with a live person.
PrefBench is a new benchmark designed to evaluate zero-shot LLM agents in personalized pricing negotiations with hidden preferences, assessing their ability to infer and adapt to user preferences in a negotiation setting.
Study shows LLM agents can model counterparty preferences in negotiation but fail to turn that knowledge into strategic bargaining to improve outcomes, limiting their effectiveness in multi-turn negotiations.
It is rumored that Tencent negotiated an investment with Liang Wenfeng (DeepSeek). Tencent initially demanded a 20% stake but was rejected, ultimately accepting 2%, sparking industry discussion about shifts in the AI competitive landscape.
Tencent tried to subscribe to 20% of DeepSeek at a $50 billion valuation but was rejected, ultimately securing only 2% shares, with DeepSeek demanding Tencent bind to its ecosystem, reflecting DeepSeek's strong position in AI investment.
This paper proposes a method to predict decisions of unfamiliar AI agents in negotiation games by combining tabular features with LLM-based text representations and hidden states from a frozen observer model, outperforming direct prompting approaches.
PACT introduces a head-to-head negotiation benchmark for LLMs using a 20-round buyer-seller bargaining game to test persuasion and adaptation. Top performers include GPT-5.5 and Opus 4.7, with ratings computed via Glicko-2 on an Elo-like scale.
Mediator.ai is a tool that applies Nash bargaining game theory and LLMs to facilitate fair cooperative negotiation, generating and scoring candidate agreements against both parties' stated needs until an optimal solution is found.
Anthropic conducted an experiment where employees used Claude-powered agents to trade books in a miniature market, studying agent representation and how model strength affects negotiating outcomes.