AI Research news and analysis on Web Pulse: 10117 curated articles tracking the latest AI Research developments, tools, and research, updated continuously from vetted sources.
A new approach to coordinating multiple AI agents uses ticket-based queues and shared state to eliminate manual copy-pasting between tools, enabling automated handoffs without human intervention. The method addresses bot…
ByteDance's Seed research team released Seedance 2.5, a video generation model that produces 30-second clips in 4K resolution with support for 50 multimodal references, addressing key limitations in AI video production s…
AI, particularly superintelligence, is emerging as a new factor of production alongside land, labor, capital, and entrepreneurship, according to an economic analysis. The author argues that AI can function as an independ…
The article delineates four subtypes of corrigibility in AI alignment: sponge corrigibility, boundedness/myopia, reflectively stable taskishness, and deep corrigibility. These categories range from simple obedience to ad…
Enki Labs released evaluation results for its closed-source memory engine Enki, showing comparable answer accuracy to mem0 on the LongMemEval-S benchmark while storing roughly half the facts (138 vs 283). In a 25-instanc…
Florida International University researchers developed JaiLIP, a technique using subtle image modifications to bypass AI safety guardrails in vision-language models like BLIP-2, nearly doubling harmful outputs. The attac…
India and US mobilized private sector for AI and chip projects at a June 25 Washington roundtable, with officials from both countries seeking to derisk private capital through durable demand signals. Indian officials hig…
AI will not make mathematicians obsolete, as current systems cannot reliably verify mathematical proofs and require human oversight for correctness. Despite media hype, AI tools like Claude and ChatGPT struggle with comp…
An AI agent developer implemented a sleep consolidation system to manage memory stores that grow to tens of thousands of items, causing retrieval slowdowns and irrelevant memories. The system merges similar memories, pru…
Norax builds an entity graph from its memory store to improve retrieval for AI agents. The graph uses entity extraction, co-occurrence edges, community detection, and weighted edges to capture relationships between conce…
Norax developed a multi-signal memory architecture for AI agents that combines exact term matching, dense vector similarity, temporal decay, and entity graph reranking. The system outperforms single-signal retrieval by 4…
A developer built Norax, a 7th-generation autonomous AI agent with persistent memory, autonomous decision-making, and cost optimization. The agent uses a scratchpad for hot state, semantic/procedural/intel memory with hy…
A developer breaks down the five essential components of production-grade AI agents: planning, tool use, memory, constraints, and verification. The post argues that agent failures stem from workflow design around the mod…
A UBS report reveals Chinese AI models cost up to 50 times less than US counterparts, with prices as low as $2-$3 per million output tokens versus $15 for comparable US models. About 60% of companies are migrating worklo…
A new framework called 'belief webs' is proposed to unify beliefs, goals, and actions in intelligent agents, drawing from active inference, agent foundations, and machine learning. The framework addresses internal incons…
A developer built an AI agent using active inference that becomes curious on its own by minimizing surprise rather than chasing rewards. On a foraging task, the agent achieved 100% success by checking a hint before actin…
Shridhar Shah, a senior software engineer at Outshift by Cisco, built two AI agents to test theory of mind using the Sally-Anne false-belief test. One agent, which only tracks reality, fails the test like a toddler, whil…
A developer built a 90-line AI agent that mimics sleep to consolidate memories, achieving 100% recall compared to 75% for an identical agent without sleep. The agent replays daily experiences during an idle phase, summar…
A developer built a tiny Darwin Gödel Machine in ~150 lines of code that improves its own code by editing itself and keeping only changes that verifiably increase test scores. The program started by passing 1 of 8 tasks …
A developer created an autonomous multi-agent system that uses local LLMs, CadQuery, and OpenFOAM to design and optimize 3D-printable quadcopter propellers. The system employs a team of AI agents to propose designs and a…