与「ICML2026」相关的搜索结果

🚨 Thrilled to share that our lab will be presenting the 🏆 Best Paper at the NExT-Game Workshop at #ICML2026# today! 🎤 When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games 🏆 Best Paper @ NExT-Game Workshop 📍 Conference Room S307 📅 Fri, Jul 10 🕐 13:00–13:20 KST Authors: @JerickShi @TerryJCZhang @bschoelkopf @conitzer @ZhijingJin 🤖 We introduce a three-stage endogenous promise protocol for repeated multi-agent games that asks not only whether LLM agents honor their public commitments when they can privately deviate, but also how model-on-model composition influences premeditated deception and persistent exploitation. 📊 Across six canonical games spanning binary and numerical action spaces, our evaluation of frontier models (GPT-5.2, Llama-4-Maverick, Claude-Opus-4.6) reveals: 🔹 Over 90% of promise-breaking instances are premeditated in agents' private plans. 🔹 Mixed-model groups with mismatched communication frameworks create systemic, persistent payoff gaps of up to 5.00 points from Round 0. 📄 Paper: #MultiAgentSystems# #LLMs# #GameTheory# #AI# #ICML2026#

I'm at #ICML2026# in Seoul 🇰🇷 — presenting tomorrow! ReviewArena: A Large-Scale Cross-Conference Dataset & Benchmark for LLM Peer Review, a spotlight at the AI for Science workshop. 🎤 Talk: Hall C, 14:00–14:10 KST 📌 Poster: Hall A, board #416# Come by!

📣 We are presenting 6 main conference papers 🚀and 14 workshop papers (including 🏆2 Best Papers🏆) at #ICML2026# in Korea! Also hosting one of the largest workshops, Trustworthy AI for Good, on July 10th 🌍❤️. We push the frontiers on #AISafety#, #MultiAgent#, and #CausalReasoning# at @JinesisLab! 🎉 Huge congratulations to all collaborators and co-authors. Excited to discuss these projects in Seoul! Feel free to reach out and talk to our 20+ members and collaborators in Korea @ZhijingJin, @_AndreiMuresanu, @iarthsingh, @ChanglingXavier, @davidguzman1120, @EmanuelTewolde, @ettogran, @FurkanDanismann, @Jerick1380, @PepijnCobben, @rishit_dagli, @_rfaulk, @SimkoSamuel, @TerryJCZhang, @vantru0ng, @zhxiao03, @x_angelohuang, @yahang_qi, @ozzaney0101, @_yongjinny. Happy for collaboration on any of the above topics 🤝 EuroSafeAI, University of Toronto, ETH Zürich, Max Planck Institute for Intelligent Systems Main conference spotlight 🌟 Safe Models Do Not Guarantee Safe Societies: The Case for Sociopolitical Risk Main conference posters 📌 CauSciBench: Can LLMs Automate Causal Inference in Real-World Scientific Research? 📌 Training with Honeypots: Reshaping How LLMs Fail 📌 CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social Dilemmas 📌 Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution 📌 LLM for Physics Research Requires Domain-Specialized Training and Tooling Workshop best papers 🏆When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games BEST PAPER@NExT-Game Workshop 🏆Transferability for General Reasoning: An Automated Curriculum for Multi-Domain LLM RL BEST PAPER@RLxF Workshop Workshop oral and spotlight 🎤 AF-ARENA: A Multi-Dimensional Evaluation Suite for Alignment Faking — AIWILD 🌟 Multi-Agent AI Systems Need Institutional Design, Not Just Model-Level Alignment — AI4GOOD Workshop papers 📄 The Wedge Questions: Latent Cultural Boundaries in LLMs via Persona Projection Divergence — Pluralistic Alignment 📄 GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory — NExT-Game 📄 Stargazer: A Scalable Model-fitting Benchmark Environment for AI Agents under Astrophysical Constraints — AI4Physics 📄 Test of Time: Rethinking Temporal Signal of Benchmark Contamination — FoGen 📄 CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social Dilemmas — AI4GOOD 📄 Weight-Level Defenses Improve LLM Agent Adversarial Robustness — AI4GOOD 📄 Evaluating Cooperation in LLM Social Groups through Elected Leadership — AI4GOOD 📄 Causal AI Scientist: Towards End-to-End Causal Inference with Large Language Models — AI4Research 📄What Game-Theoretic Benchmarks Miss: Strategic Silence in Multi-Agent LLMs — FAGEN 📄Proving Your Way to Cooperation: Formalizing Proof-Based Open Source Game Theory in Lean — AI4Math

We present our paper "Mitigating Reward Hacking via Adversarial Robustness" at EIML@ICML2026! We conjecture that reward hacking is often caused by flipped advantage-sign estimations, and propose SignCert-PO, a new algorithm built on the theory of randomized smoothing! 🧵

多智能体不用说话就能协作了 🧠 LatentMAS 入选 ICML 2026 Spotlight——Agent 直接在隐空间传递推理状态，跳过文字编解码。 准确率 +13.3%，速度 4.3 倍，token 用量少 83.7%。 不额外训练，插进现有 LLM 直接用。 这个方向你们觉得会成主流吗？

Excited to share that #LatentMAS# has been accepted to ICML 2026 as a spotlight! 💻Code: 📄Paper: We push multi-agent collaboration into the latent space — beyond human language. Most multi-agent systems rely on text: agents reason in words, exchange messages, and repeatedly decode/re-encode information. But language can be slow, lossy, and unnecessarily constrained. 💡LatentMAS takes a different path: LLM agents reason and communicate directly through hidden embeddings. No text decoding. No extra training. No token-level message passing. Instead, agents collaborate through: 🧠 Autoregressive Latent Thoughts — hidden-state-level reasoning steps 🔁 Latent Communication — information sharing via KV-cache transfer 📌 Input-output Alignment — keeping latent representations in-distribution 🚀 Training-free Collaboration — plug-and-play with existing LLMs Why it matters: ✅ Up to +14.6% better accuracy on complex reasoning tasks ⚡ 4-4.6x faster end-to-end inference ✂️ 70.8%–83.7% reduction in output token usage A step toward multi-agent systems that collaborate not by speaking more, but by thinking together in latent space. #MultiAgentSystems# #ModelCollaboration# #LatentReasoning# #LLM# #AgenticAI# #ICML#

现在很多人聊 AI Web3，都在盯着模型、应用、空投这些地方，但真到了一堆 AI Agent 上链执行任务、调用数据、协同交易、管理资产的时候，问题就会变得特别特别现实： 它的推理能不能被验证？ 它调用的数据靠不靠谱？ 它的记忆放在哪里？ 它和其他 Agent 协作时，出了问题谁来审计？ 底层协议有没有隐藏的 bug？ 这些东西听起来一点也不性感，而且作为乐观主义者，我平时也反感只提问题不给解决方案，但真出事的时候，以上的每一个都会是扎心的大问题。 —————————————————— 这也是我觉得 @0G_labs 近期的几个动作值得看的原因。 根据这次 APAC Hackathon 黑客松的最终数据，1.04M+ 社媒曝光、1145 名全球参与者、293 个最终提交项目，放在现在这个市场环境里，已经能说明 0G 生态不只有声音，是实实在在的有人在持续动手构建。 更关键的是，这批项目并没有只挂一个链上 AI 的概念，很多都实际落地应用到了 0G 存储、0G 算力、0G 链、隐私计算、Agentic ID。 这也说明 0G 的全栈基础设施，已经开始被开发者拿去做真实的东西了。 从我的视角看，黑客松最有价值的地方在于它能不能把开发者、场景和工具栈一起给跑通了,因为如果一个生态只有叙事，没有人愿意去动手搭东西，那热度一定会很快就消散了。 但是如果有几百个项目提交，有人用存储、有人用算力、有人用隐私计算、有人尝试 Agentic ID，这就说明 0G 的生态闭环开始有雏形了。 另一个点我觉得更硬，那就是 0G Lab 的这篇多智能体安全论文。 —————————————————— 他们联合新加坡国立、北大、北邮做了一个叫 Agora 的框架，专门拿来 debug 共识协议。 共识协议直白的说就是链和分布式系统最底层的记账规则，节点怎么达成一致、异常节点怎么处理、状态怎么同步、签名和执行结果怎么保证不出问题，很多核心风险都藏在这里。 Agora 的思路是让多个 Agent 分工协作，有人负责理解全局状态、有人负责设计异常场景、有人负责生成测试代码、有人负责跑结果和复盘问题。 最后在 Raft、EPaxos、HotStuff、BullShark 等主流共识协议里，挖出了 15 个之前没人发现的协议级深层逻辑漏洞（零日漏洞），论文也中了顶会（我特意去查了下，论文已被 ICML 2026 接收，这是全球人工智能和机器学习领域历史最悠久、规模最大、最具影响力的顶级学术会议之一，这含金量懂的都懂）。 因为 AI Agent 以后真的要在链上跑，光靠会聊天、会生成内容、会自动执行任务肯定不够，底层系统必须能被测试，能被验证，能提前把风险挖出来，毕竟安全才是第一位的。 所以模型会换、应用会换，但 AI Agent 需要的可信执行、链上存储、隐私保护、安全验证这些需求不会消失。 这才是我看 0G 的核心逻辑，它正在补齐 AI Agent 上链之前必须要具备的底层能力。 熊市里，真正做事的项目反而更容易看清楚 ，你们觉得呢？ @0G_labs @0g_cn

We post-train LLMs for math, for code, for instruction-following. Why not for scientific discovery? 🫎 MOOSE-Star (ICML 2026) : the first scalable SFT recipe for discipline-agnostic scientific hypothesis discovery. By @Yang_zy223 & @LidongBing from MiroMind.

Hello from #ICML2025#! 👋 Together with @GoogleResearch, we’re presenting over 140 papers, as well as hosting workshops, talks and demo sessions. Check out our schedule. →