agentwall adds runtime safety for local ai agents
agentwall intercepts agent actions before execution, enforcing declarative safety policies to prevent harmful operations on local machines.
aitag research
summaries filed under research
stopping local ai agents early saves energy
agentstop reduces energy use in local ai agents by predicting task failure early, cutting token waste and battery drain on consumer devices.
airisk-aware policy learning for offline bandits
a new method learns safe decision rules from logged data using general risk measures like cvar, with strong theoretical guarantees.
aisix months of llm progress in five minutes
a lightning talk summary of major llm developments from november 2025 to may 2026, including coding agent breakthroughs and open-weight model advances.
aisandboxaq puts drug discovery ai into claude
sandboxaq integrates its physics-grounded quantitative models into anthropic's claude, letting researchers run complex simulations through plain language prompts.
ailatent bias in llms can flip decisions
instruction-tuned language models show fair outputs but retain biased internal representations that can reverse decisions when activated.
aiteamtr fine-tunes multi-agent llms with trust regions
a trust-region method for fine-tuning multi-agent llm teams avoids compounding errors from stale rollouts, outperforming baselines by 7.1%.
aiopen agent leaderboard compares full ai systems
a new open benchmark evaluates complete agent systems, not just models, across six diverse tasks to measure generality, quality, and cost.
aideepslide: ai for full presentation delivery
deepslide is a multi-agent system that helps prepare entire presentations, from planning and slide creation to rehearsal support.
aioracle price map learning for contextual pricing
a new method learns the optimal price as a smooth function of a scalar index, improving revenue in semiparametric dynamic pricing.
aitheory of mind gains don't always help human-ai chats
improving llm theory of mind on static tests often fails to boost real interactive task performance, a new study finds.
aistate-constrained dispatch cuts multi-agent alignment tax
a new framework uses state machines and online rlhf to enforce business rules in multi-agent systems, improving accuracy over gpt-4o on a recruitment benchmark.
aialpha-tcav fixes statistical flaws in concept-based explainability
a new framework replaces the unstable indicator function in tcav with a smooth parameterized function, reducing variance and unifying existing methods.
aiquantization undoes alignment in compressed llms
a study finds that aggressive quantization causes previously unbiased language models to develop new stereotypical behaviors, with a clear dose-response pattern.
aigds urges open code default after nhs retreat
the uk government digital service recommends keeping public sector code open by default, pushing back against the nhs decision to close repositories after vulnerability reports.
aiarxiv bans authors for unchecked ai-generated papers
arxiv will impose a one-year ban on authors who submit papers with clear signs of unverified llm output, such as hallucinated references.
aiinteger goal programming for meal plans with real serving sizes
a new mixed integer goal programming method creates personalized meal plans using whole servings and soft nutrient targets, avoiding fractional foods and infeasible diets.
aiturboquant compresses llm caches to 3 bits
google's turboquant uses polarquant and qjl to cut kv cache memory by over 5x without retraining or accuracy loss.
ainasa tests ai chip for autonomous spacecraft
nasa is testing a radiation-hardened processor that delivers up to 500 times the performance of current spaceflight computers, enabling ai-powered spacecraft to operate independently in deep space.
airegret metric exposes cost of strict false discovery control
a new weighted regret metric reveals deterministic online multiple testing procedures suffer linear regret from false negatives, and a decoupled wrapper fixes it.
ai