Liangwei Yang

Rethinking Memory Mechanisms of Foundation Agents in the Second Half: A Survey bit.ly/4lS5uLQ As AI agents move beyond static benchmarks into long-horizon, real-world environments, memory becomes the critical infrastructure for bridging the utility gap. This survey unifies foundation agent memory across three dimensions: 🧠 Memory Substrate → internal (weights, KV cache, latent states) vs. external (vector stores, knowledge graphs, text records) 🔄 Cognitive Mechanism → sensory, working, episodic, semantic, and procedural memory, mapped from human cognition to agent architectures 👤 Memory Subject → who is memory serving? User-centric memory for personalization vs. agent-centric memory for skill accumulation and task transfer → Analyzes memory operations across single-agent and multi-agent topologies, including architecture, routing, and conflict resolution → Covers learning policies for memory management: prompting, fine-tuning, and RL-based approaches → Reviews 218 papers across 2023–2025 with evaluation benchmarks and metrics for both user- and agent-centric settings → Identifies six open challenges including continual learning, privacy-preserving memory, multimodal grounding, and real-world evaluation @Salesforce authors: Zixuan Ke @KeZixuan, Liangwei Yang @Liangwei_Yang, Juntao Tan @chrisjtan, Shelby Heinecke @shelbyh_ai, Huan Wang @huan__wang, Caiming Xiong @CaimingXiong #FutureOfAI #EnterpriseAI #LLMAgents

📢📱Unlock the Future of Mobile AI! 📱📢 (1/6) Say hello to MobileAIBench, our open source framework for assessing mobile-readiness of your LLMs and LMMs. Test and optimize more quickly than ever before – with benchmarks spanning NLP, multimodality, trust and safety. iOS app included! Dive into the 🧵or: Paper: bit.ly/3WoxX0u Code: bit.ly/3xWDUZp #AI #MobileAI #Benchmarking #NLP #LLMs

Need to evaluate quantized LLMs/LMMs across text, trust & safety, and multimodal tasks? Check out MobileAIBench – includes iOS app for on-device latency and utilization metrics. #OnDeviceAI #AIBenchmarking Paper: arxiv.org/abs/2406.10290 Code: bit.ly/3xWDUZp

Unlock the Future of Mobile AI! 📱 Say hello to MobileAIBench, our new open source framework for assessing mobile-readiness of your LLMs and LMMs. Quickly and easily test your models on a variety of benchmarks spanning NLP, multimodality, and trust & safety. Using our iOS app, test your model’s on-device performance such as memory consumption, latency etc.. Paper: arxiv.org/abs/2406.10290 Code: github.com/SalesforceAIRe… #AI #MobileAI #Benchmarking #NLP #LLMs

Welcome to check our repos and play with our xLAM resources, (github.com/SalesforceAIRe………), model (huggingface.co/Salesforce/xLA………) and AgentLite (github.com/SalesforceAIRe………) Library!

🎉🎉We are excited to release a full package for AI Agent R&D: 1) For Data & Training, 🎙️AgentOhana🎙️: Design Unified Data and Training Pipeline for Effective Agent Learning. 2) For model, 🔥xLAM-v0.1-R🔥: A strong large action model for AI Agent while maintaining abilities on general tasks. 3) For agent inference framework, 🤖AgentLite🤖: a lightweight agent/multi-agent library. AgentOhana aggregated, standardized and unified agent trajectories from distinct environments. xLAM-v0.1-r, fine-tuned on #Mixtral, outperforms #GPT-3.5-Turbo on the benchmarks (WebShop, HotpotQA, ToolBench, and MINT-Bench) and #GPT-4 on several of them. AgentLite is implemented with <1K lines of code, and magically supports quickly building LLM agents, designing new agent reasoning, new agent architectures and multi-agent orchestration. AgentOhana Paper: arxiv.org/abs/2402.15506… xLAM GitHub and Model:github.com/SalesforceAIRe… and huggingface.co/Salesforce/xLA… AgentLite Github: github.com/SalesforceAIRe… AgentLite Paper: arxiv.org/abs/2402.15538

Only four days left to our March SEA talks about social media and graph-based recommendations. w/ @s0f1ra (DeepMind) and L. Yang (Uni. of Illinois at Chicago). Don't forget to sign-up. meetup.com/sea-search-eng…