In contrast, using only the current turn avoids this overhead but discards essential information. This trade-off limits the scalability of search agents. To address this challenge, we propose MemSearcher, an agent workflow that iteratively maintains a compact memory and combines the current turn with it. At each turn, MemSearcher fuses the user's question with the memory to generate reasoning traces, perform search actions, and update memory to retain only information essential for solving the task. This design stabilizes context length across multi-turn interactions, improving efficiency without sacrificing accuracy. To optimize this workflow, we introduce multi-context GRPO, an end-to-end RL framework that jointly optimize reasoning, search strategies, and memory management of MemSearcher Agents. Trained on the same dataset as Search-R1, MemSearcher achieves significant improvements over strong baselines on seven public benchmarks: +11% on Qwen2.5-3B-Instruct and +12% on Qwen2.5-7B-Instruct Notably, the 3B-based Mem-Searcher even outperforms 7B-based baselines, demonstrating that striking a balance between information integrity and efficiency yields both higher accuracy and lower computational overhead.

A computational bottleneck in current Vector-Symbolic Architectures (VSAs) is the ``clean-up'' step, which decodes the noisy vectors retrieved from the architecture. Clean-up typically compares noisy vectors against a ``codebook'' of prototype vectors, incurring computational complexity that is quadratic or similar. We present a new codebook representation that supports efficient clean-up, based on Kroneker products of rotation-like matrices. The resulting clean-up time complexity is linearithmic, i.e. $\mathcal{O}(N\,\text{log}\,N)$, where $N$ is the vector dimension and also the number of vectors in the codebook. Clean-up space complexity is $\mathcal{O}(N)$. Furthermore, the codebook is not stored explicitly in computer memory: It can be represented in $\mathcal{O}(\text{log}\,N)$ space, and individual vectors in the codebook can be materialized in $\mathcal{O}(N)$ time and space. At the same time, asymptotic memory capacity remains comparable to standard approaches. Computer experiments confirm these results, demonstrating several orders of magnitude more scalability than baseline VSA techniques.

Think you have a good pulse on how your cat is feeling? Tably is a new AI-powered app that can help confirm whether your suspicions are correct. Simply use your smartphone camera to take a picture of your feline friend and the app will use machine learning to decode its mood. Sylvester.AI, the company behind the app, writes that Tably is based on the Feline Grimace Scale, a proven tool used by scientists to determine pain in animals based on facial expressions. A scientist can score expressions both in real-time or from photographs based on the presence or prominence of things like whisker changes, ear positions, and more.

There is no longer any credible reason to deny our part in the climate crisis. We are now facing the destruction of vital ecosystems, and every year 12.6 million people die because of environmental pollution. Cutting edge smart city technologies may be our most useful weapon in the fight against the climate crisis, helping us to reduce our impact on the planet in future, and alleviate the damage we have already done. Part two of this series will focus on how smart cities can help us tackle the looming climate crisis, and which technologies will be used to ensure cities continue to be sustainable as our planet and population dramatically change. Once we have planned out cities that are adaptable and better suited to our needs, we can start implementing smart technologies to overhaul unsustainable utilities, transport and energy systems.

Computer scientist David Blaauw pulls a small plastic box from his bag. He carefully uses his fingernail to pick up the tiny black speck inside and place it on the hotel café table. At one cubic millimeter, this is one of a line of the world's smallest computers. I had to be careful not to cough or sneeze lest it blow away and be swept into the trash. Blaauw and his colleague Dennis Sylvester, both IEEE Fellows and computer scientists at the University of Michigan, were in San Francisco this week to present ten papers related to these "micro mote" computers at the IEEE International Solid-State Circuits Conference (ISSCC).