what makes an ai agent truly autonomous
a new paper argues that real agency requires internalized goals, identity, decision-making, self-regulation, and learning, not just external prompts.
aisummaries filed under research
a new paper argues that real agency requires internalized goals, identity, decision-making, self-regulation, and learning, not just external prompts.
aia new framework extracts decision traces from rule-based planners to supervise driving vision-language-action models, making their reasoning more faithful and causally connected to motion.
aia combined mcmc and gaussian process method extracts interpretable chemical equations and improves yield in experiments.
aia large-scale pipeline exploring 4-expert heterogeneous mixture-of-experts architectures reveals that alphabetical enumeration caused the search to be anchored to a single base family, limiting diversity.
aistudy finds sft, rft, and rift produce nearly identical weight changes in lora fine-tuning, while dft and offline grpo diverge.
aia breakdown of essential math disciplines for data science and a practical learning roadmap.
aia proposed browser api lets web apps share cached ai model and wasm files across origins using cryptographic hashes, reducing redundant downloads and storage.
aia 0.2b image inpainting model was converted from pytorch to onnx and deployed as a browser demo using webgpu, with help from claude code.
airesearch shows llms prioritize text style over content, enabling jailbreaks through role confusion.
aia pipeline uses semantic retrieval and human review to measure how well a computer science program covers evolving curricular standards.
aia new method extracts useful knowledge from large time-series models that don't fit scientific data, creating small, fast forecasters for sensor networks.
aia new model shows llm agents have hidden internal beliefs that shape group decisions, explaining how confidence can exceed initial levels.
aia new policy framework extends beyond permit/prohibit to handle obligations, waivers, and conflict resolution for llm-driven agents.
aiorbital ai data centers promise abundant solar power and cooling but must overcome radiation, heat rejection, and high maintenance costs.
aiaura iteratively learns human-consistency signals to audit llm-as-a-judge decisions with minimal human verification.
aiinformation lattice learning can be interpreted as a method for learning the structure of probabilistic graphical models by projecting probability distributions onto partition lattices and lifting rules back.
aia new forecasting algorithm achieves optimal regret for both general and smooth proper losses, overcoming previous limitations in u-calibration.
aimosaicleaks shows that deep research agents often expose private information when they search the web, and training them to be better at tasks makes the leakage worse.
ainavi-orbital runs a vision-language model on a low earth orbit satellite to classify scenes, describe content, and answer operator questions in plain english.
aiadding human collaborators to ai teams can hurt performance without structured coordination, but shared memory and approval gates help.
ai