✨Cooperation and Exploitation in LLM Policy Synthesis for Sequential Social Dilemmas

📝 Summary:
This paper uses LLMs to synthesize agent policies for multi-agent environments. Dense feedback including social metrics consistently outperforms sparse reward-only feedback, guiding LLMs toward effective cooperative strategies in social dilemmas.

🔹 Publication Date: Published on Mar 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.19453
• PDF: https://arxiv.org/pdf/2603.19453
• Github: https://github.com/vicgalle/llm-policies-social-dilemmas

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#LLMs #MultiAgentSystems #SocialDilemmas #ReinforcementLearning #AIResearch

✨MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution

📝 Summary:
MemMA is a multi-agent framework that coordinates the memory cycle in LLM agents. It uses a Meta-Thinker for strategic guidance and in-situ self-evolving repair for memory construction and retrieval. MemMA consistently outperforms existing baselines.

🔹 Publication Date: Published on Mar 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.18718
• PDF: https://arxiv.org/pdf/2603.18718
• Github: https://github.com/ventr1c/memma

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#LLM #MultiAgentSystems #AIMemory #AIResearch #ArtificialIntelligence

✨GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning

📝 Summary:
GrandCode is a multi-agent reinforcement learning system that achieves grandmaster level in competitive programming. It orchestrates specialized agent modules and uses novel reward optimization techniques. GrandCode consistently beat all human participants, including legendary grandmasters, in li...

🔹 Publication Date: Published on Apr 3

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.02721
• PDF: https://arxiv.org/pdf/2604.02721
• Project Page: https://deep-reinforce.com/cp.html
• Github: https://github.com/deepreinforce-ai/codeforces

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#ReinforcementLearning #CompetitiveProgramming #AI #MultiAgentSystems #DeepLearning

✨When Reasoning Models Hurt Behavioral Simulation: A Solver-Sampler Mismatch in Multi-Agent LLM Negotiation

📝 Summary:
Reasoning-enhanced LLMs can over-optimize, making them better problem solvers but poor simulators of diverse, boundedly rational behavior. This solver-sampler mismatch means high model capability hurts simulation fidelity. Bounded reflection improves realism.

🔹 Publication Date: Published on Apr 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.11840
• PDF: https://arxiv.org/pdf/2604.11840
• Project Page: https://www.sandric.co

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#LLM #MultiAgentSystems #BehavioralSimulation #AI #AgentBasedModeling

✨From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company

📝 Summary:
OneManCompany OMC addresses static multi-agent systems by providing a framework for dynamic team assembly and governance. It uses portable agent identities and a hierarchical decision loop for self-organizing AI teams. OMC achieves 84.67% success on PRDBench, improving state-of-the-art by 15.48%.

🔹 Publication Date: Published on Apr 24

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.22446
• PDF: https://arxiv.org/pdf/2604.22446
• Project Page: https://1mancompany.github.io/OneManCompany/
• Github: https://github.com/1mancompany/OneManCompany

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#AI #MultiAgentSystems #SelfOrganizingAI #AIteams #AutonomousAgents

🔥 TradingAgents: Multi-Agents LLM Financial Trading Framework

💡 The paper introduces TradingAgents, a multi-agent framework that utilizes large language models for stock trading, simulating the collaborative dynamics of real-world trading firms. The framework consists of various agents, including fundamental analysts, sentiment analysts, technical analysts, and traders with different risk profiles, all powered by large language models. These agents work together to assess market conditions, manage risk, and make informed trading decisions. The framework also includes researcher agents that evaluate market conditions and a risk management team that monitors exposure.

The authors propose this framework as a solution to the limitations of existing single-agent systems and multi-agent frameworks that gather data independently. By simulating a dynamic and collaborative trading environment, TradingAgents aims to improve trading performance metrics such as cumulative returns and Sharpe ratio.

The results of the experiments show that the TradingAgents framework outperforms baseline models, with significant improvements in cumulative returns, Sharpe ratio, and maximum drawdown. The framework is made available to the public, demonstrating the potential of multi-agent large language model frameworks in financial trading. Overall, the paper contributes to the development of more sophisticated and collaborative trading systems, inspired by the dynamics of real-world trading firms.

📅 Published on Dec 28, 2024

🔗 Links:
• arXiv: https://arxiv.org/abs/2412.20138
• PDF: https://arxiv.org/pdf/2412.20138
• GitHub: https://github.com/tauricresearch/tradingagents ⭐ 66.0k

🚀 Spaces citing this paper:
• https://huggingface.co/spaces/shanghengdu/LLM-Agent-Optimization-PaperList
• https://huggingface.co/spaces/tahp0604/ai-stock-watchlist
• https://huggingface.co/spaces/Ervin2077/qiu

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#MultiAgentSystems #LargeLanguageModels #FinancialTrading #ArtificialIntelligenceInFinance #AgentBasedModeling

🔥 EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery

💡 The paper introduces EvoScientist, a multi-agent framework designed to enhance scientific discovery by learning from past interactions. The problem with current AI scientist systems is that they rely on static pipelines and fail to adapt based on accumulated interaction histories, leading to overlooked research directions, repeated failed experiments, and pursuit of infeasible ideas. To address this, EvoScientist uses three specialized agents: a Researcher Agent for idea generation, an Engineer Agent for experiment implementation, and an Evolution Manager Agent that distills insights from prior interactions into reusable knowledge. The framework also includes two persistent memory modules: an ideation memory that summarizes feasible research directions and records unsuccessful ones, and an experimentation memory that captures effective data processing and model training strategies. These modules enable the agents to retrieve relevant prior strategies, improving idea quality and code execution success rates over time. The results show that EvoScientist outperforms seven state-of-the-art systems in scientific idea generation, achieving higher novelty, feasibility, relevance, and clarity, and also improves code execution success rates through multi-agent evolution, demonstrating the effectiveness of persistent memory for end-to-end scientific discovery. Overall, the paper contributes a novel framework that enables AI scientists to learn from their past interactions and adapt their research strategies, leading to more effective and efficient scientific discovery.

📅 Published on Mar 9

🔗 Links:
• arXiv: https://arxiv.org/abs/2603.08127
• PDF: https://arxiv.org/pdf/2603.08127
• GitHub: https://github.com/EvoScientist/EvoScientist ⭐ 2.6k

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#MultiAgentSystems #EvolvingAI #ScientificDiscovery #ArtificialIntelligenceResearch #AutonomousScience

🔥 ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration

💡 The paper introduces ARIS, an open source research harness that enables autonomous research through adversarial multi agent collaboration. The problem addressed is the reliability of long term research outcomes, particularly in cases where AI generated claims may be unsupported or misreported. The central failure mode in long horizon research workflows is not a visible breakdown but rather a plausible unsupported success, where a long running agent can produce claims with incomplete or misreported evidential support.

To address this problem, ARIS uses a cross model adversarial collaboration approach, where an executor model drives forward progress while a reviewer from a different model family critiques intermediate artifacts and requests revisions. The ARIS architecture consists of three layers: the execution layer, which provides reusable skills and model integrations, the orchestration layer, which coordinates end to end workflows, and the assurance layer, which checks the integrity of experimental claims and ensures that they are supported by evidence.

The assurance layer includes a three stage process for checking claims, as well as a five pass scientific editing pipeline, mathematical proof checks, and visual inspection of rendered PDFs. The system also includes a prototype self improvement loop that records research traces and proposes harness improvements, which are adopted only after reviewer approval.

The contributions of the paper are the introduction of the ARIS research harness, which provides a reliable and autonomous way to conduct research, and the demonstration of its effectiveness in ensuring the integrity of research outcomes. The paper also highlights the importance of adversarial collaboration in ensuring the reliability of AI generated research claims. Overall, the paper presents a significant contribution to the field of autonomous research, providing a framework for ensuring the reliability and integrity of research outcomes.

📅 Published on May 4

🔗 Links:
• arXiv: https://arxiv.org/abs/2605.03042
• PDF: https://arxiv.org/pdf/2605.03042
• Project Page: https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep
• GitHub: https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep ⭐ 8.2k

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#AutonomousResearch #AdversarialMultiAgentCollaboration #ArtificialIntelligenceReliability #LongTermResearchOutcomes #MultiAgentSystems

🔥 QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading

💡 The paper introduces QuantAgent, a multi-agent large language model framework designed specifically for high-frequency trading. High-frequency trading requires rapid and precise decisions based on short-term market signals, which is different from traditional financial applications that involve long-term semantic reasoning. Existing large language models are not well-suited for high-frequency trading due to their lack of structured reasoning capabilities and domain-specific tools.

To address this problem, the QuantAgent framework decomposes trading into four specialized agents: Indicator, Pattern, Trend, and Risk. Each agent is equipped with domain-specific tools and structured reasoning capabilities to capture distinct aspects of market dynamics over short temporal windows. The Indicator agent focuses on technical indicators, the Pattern agent focuses on chart patterns, the Trend agent focuses on trend-based features, and the Risk agent focuses on risk management.

The results show that QuantAgent outperforms strong neural and rule-based baselines in terms of predictive accuracy and cumulative return over 4-hour trading intervals. The evaluation was conducted across ten financial instruments, including Bitcoin and Nasdaq futures, using zero-shot evaluations. The findings suggest that combining structured financial priors with language-native reasoning can unlock new potential for real-time decision systems in high-frequency financial markets.

The main contribution of the paper is the introduction of a multi-agent large language model framework that is specifically designed for high-frequency trading. The framework's ability to decompose trading into specialized agents and leverage domain-specific tools and structured reasoning capabilities makes it well-suited for the high-speed and precision-critical demands of high-frequency trading. The results demonstrate the effectiveness of the QuantAgent framework and highlight its potential for use in real-world high-frequency trading applications.

📅 Published on Sep 12, 2025

🔗 Links:
• arXiv: https://arxiv.org/abs/2509.09995
• PDF: https://arxiv.org/pdf/2509.09995
• Project Page: https://Y-Research-SBU.github.io/QuantAgent/
• GitHub: https://github.com/Y-Research-SBU/QuantAgent ⭐ 2.5k

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#HighFrequencyTrading #MultiAgentSystems #LargeLanguageModels #FinancialMachineLearning #AlgorithmicTrading

🔥 OpenRath: Session-Centered Runtime State for Agent Systems

💡 The paper introduces OpenRath, a programming model for multi-agent systems that addresses the issue of fragmented runtime state. In current agent systems, various aspects such as transcripts, tool effects, and memory events are recorded separately, making it difficult to inspect or reproduce the system's behavior. OpenRath solves this problem by introducing a central runtime abstraction called Session, which is a first-class value that can be passed between agents and workflows.

The Session abstraction is designed to be branchable, inspectable, replayable, backend-aware, and composable, allowing it to record various execution state information such as conversation chunks, sandbox placement, and tool evidence. This enables explicit fork, merge, and replay operations as runtime operations rather than reconstructing states from external traces.

OpenRath also defines other key concepts such as Sandbox, Tool, Agent, Memory, Workflow, and Selector, which work together to provide a comprehensive programming model for multi-agent systems. The Selector is particularly important as it turns control flow into runtime-routed decisions.

The paper presents the programming model, architecture, and evidence protocol of OpenRath, and claims that the Session abstraction provides agent systems with a first-class runtime value for auditable composition. The results of this work are limited to controlled runtime properties, and further evaluation is needed to compare the performance of OpenRath with other systems and to assess its availability and quality.

Overall, OpenRath contributes a novel programming model for multi-agent systems that provides a unified and explicit way to manage runtime state, making it easier to inspect, reproduce, and debug the behavior of these systems.

📅 Published on Jun 17

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2606.19409
• PDF: https://arxiv.org/pdf/2606.19409
• Project Page: https://docs.openrath.com

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#MultiAgentSystems #RuntimeStateManagement #AgentOrientedProgramming #SessionCenteredArchitecture #DistributedSystemDesign