Rishi Khare

Interactive feedback changes how code LLMs perform and rank, a new study finds. Led by senior author Valerie Chen, a Carnegie Mellon PhD student and recent visiting researcher at CDS, the project also included Courant PhD student Jane Pan, CDS PhD student Jacob Pfau, and CDS Assistant Professor He He. The team simulated developer interactions to replace static coding benchmarks like HumanEval and MBPP. When models received human-style feedback—code edits, single-sentence prompts, or paragraph-length instructions—they sometimes improved by up to 9.3 percentage points in accuracy and moved as many as four spots in ranking. “Testing on new problems the models had never seen made feedback even more powerful,” said Chen. Read more: https://lnkd.in/eAPTP5NR

5

✨Spotlighting new research! Yunyi(Icy) Zhang, Ruby Jia, Xiaoxuan “Alicia” Cheng, and CourseKata co-founders Ji Son and Jim Stigler recent work shows that three simple changes to R documentation, including front-loading examples, pairing each code snippet with its output, and ordering examples from easy to hard, help novice programmers find the right example in under a minute (versus nearly two) and boost coding-task scores by about one point. Check out the paper here: https://zurl.co/QWhuC

11

JuliaC introduces a new way to build executables and shared libraries directly from Julia code. In this session, Jeff Bezanson and Kristoffer Carlsson explain the new compiler interface and show how JuliaC enables compact binaries and cross-language deployment. https://lnkd.in/g7D76Wwt #JuliaLang #JuliaProgramming #JuliaC #ScientificComputing #TechnicalComputing #HighPerformanceComputing #EmbeddedSystems #SystemsProgramming

7

Stanford Center for Research on Foundational Model's Marin project has released the first fully open model in JAX. It’s an 'open lab' sharing the entire research process - including code, data, and logs, to enable reproducibility and further innovation. Check out the project: https://goo.gle/44AMeLY

41

2 Comments

We’re excited to release our latest paper, “Sleep-time Agents: Beyond Scaling Inference at Test-Time”, a collaboration with Charlie Snell from UC Berkeley and Letta advisors and UC Berkeley Faculty Joseph Gonzalez Ion Stoica. We believe there's a fundamental paradigm shift waiting to be unlocked: AI systems that don't just think reactively when prompted, but proactively deepen their understanding during what we call "sleep-time"—the vast periods when they're not directly engaged with users. This is the fundamental insight behind sleep-time compute, a new paradigm we're introducing in our latest research paper. Sleep-time compute represents an exciting new scaling direction for stateful AI systems: by activating deep thinking during their vast idle periods, we can expand what these systems understand and how they reason - pushing AI capabilities beyond what's possible when computation is confined only to active interactions. Letta now allows developers to create sleep-time enabled agents, which have a sleep-time agent processing the message history of the main agent to asynchronously refine that main agent’s in-context memory. Sleep-time agents can also process files or other data to generate *learned context* for the main agent to be more prepared and personalized for future interactions. See details in our paper release: https://lnkd.in/gvz_3Gig If you’re interested in open research on agents, reasoning, memory, and scaling sleep/test-time compute - come join our team - are are actively hiring for research scientists! https://lnkd.in/gghg8SQg

91

2 Comments

🌟OLCF INTERN SPOTLIGHT🌟 OLCF Intern Guangxing Hu has spent the summer working with Oak Ridge National Laboratory HPC Systems Scientist Awais Khan on their project: Hierarchical and Scalable Caching for Deep Learning I/O on HPC Systems.✨ During his internship, he collaborated to incorporate memory tiers into ORNL's AI caching software, outlining the implementation approach, identifying potential challenges, and assessing the impact on cache efficiency and reducing the runtime of large-scale training jobs. His work helps to cut training time so researchers can iterate more quickly and organizations can deploy expanding access to powerful deep learning capabilities.💫 #AI #Innovation #BigScience

27

📢 LLMs can reason. But can they act, adapt, and collaborate over time? Researchers from UIUC, with collaborators from Meta, Amazon, and Google DeepMind, just released a deep survey on Agentic Reasoning for Large Language Models — and it reframes how we should think about “reasoning” altogether. The core shift: This work argues that strong benchmarks ≠ real intelligence. Instead of one-shot reasoning, agentic reasoning treats LLMs as interactive agents that: - Plan over long horizons - Use tools and external systems - Learn from feedback and memory - Coordinate with other agents They organize agentic reasoning into three layers: - Foundational → planning, tool use, search - Self-evolving → reflection, memory, continual improvement - Collective → multi-agent collaboration and role coordination Why this matters right now: - If you’re building or working with agents, this explains why: - Prompt tricks alone don’t scale to real-world tasks - Memory and feedback loops are becoming first-class design primitives - Multi-agent systems are less about “more agents” and more about reasoning structure It also clearly separates: - In-context reasoning (orchestration at inference time) vs Post-training reasoning (RL and fine-tuning to internalize behaviors) That distinction alone changes how you design agent systems. Feels like a roadmap for where agentic AI is actually headed — not just what demos look cool on Twitter. #AgenticAI #LLMResearch #AIEngineering #Meta #Amazon #Google

37

Computer Science PhD student Yue L. is creating GenAI and AR-based games that equip children with autism spectrum disorder with social and emotional skills. She proves that play, learning, and computer science can come together to empower a child's well-being 🎮 📲 Learn more about her visionary plan, which could save Ontario $1.4 billion in educational expenses, here: https://lnkd.in/g5_NARx8

15

1 Comment