The Archive

Programmatic Search Agent extends agentic search beyond query reformulation by treating executable operations over candidate sets as primitive actions.

For all the data that AI systems continually amass and analyze, enterprise AI agents often suffer from a curious shortcoming: a lack of knowledge. More than data, knowledge is the understanding of what the data means in the context of individual organizations. AI agents need this understanding to reason about situations, make decisions, and ultimately…

KV-cache reuse in rolling agents exhibits history-dependent behavior; selective recomputation alignment reduces answer variation across request orders.

PACMI framework tracks memory dependencies and preserves history for long-term LLM agents, enabling graceful invalidation of outdated information.

Nexus: distributed execution fabric for LLM agents spanning cloud, edge, devices with permission control and fault-tolerant lifecycle management.

SO-RSI: second-order recursive self-improvement framework for formal verification agents that diagnoses root causes before structural workflow changes.

Dale Caldwell, former lieutenant governor for New Jersey. | Bloomberg via Getty Images New Jersey's lieutenant governor Dale Caldwell was forced to resign on September 25th after an investigation found he had sexually harassed a staffer and repeatedly violated ethics rules. The now-former Lt. governor has been making the media rounds trying to clear his name. But he took a particularly odd tactic during an interview on NJ PBS. Caldwell claims he's being unfairly targeted, and multiple AI agents back that up. He told host Rob Nelson that he "AIed" the report on the investigation "from multiple...

Study of coding agents for logging code removal identifies 10 patterns/11 reasons from Python and Java repositories.

VoCa: voice agent that coordinates speech with visual canvas interaction for multi-turn conversations, grounded in observational study of speech-boardwork coordination.

RETRACE reconstructs problem-level repair experience from messy CI histories to enable LLM agents to reuse debugged solutions.

Operational Validity Contract formalizes monitor alarm policies for LLM agents, distinguishing deployment constraints from probe calibration metrics.

We created a list of the most notable AI agents that can live in your text messages, from general assistants to agents designed for families, travel, and work.

Meta says FDA isn't sufficient to Muse reading messages. Apple begs to differ.

Apple will add new limits for "full disk access" on Mac in response to risks posed by AI agents, as reported earlier by TechCrunch. In an update on Friday, Apple says it's rolling out new controls to "ensure that users who genuinely wish to grant an app this extraordinary level of access can only do so with very explicit user action." The change comes just weeks after Inc's Jason Aten found that Meta's Muse AI somehow knew the contents of his messages, despite not giving the chatbot explicit permission to access them on his iPhone or Mac. Meta spokesperson Andy Stone pushed back on this repor...

Apple says it will add new controls around macOS’s Full Disk Access permission, warning that increasingly capable AI agents make broad access to users’ files, messages, mail, and browsing history riskier.

4DCodeBench benchmarks agent ability to reconstruct dynamic scenes from video as executable graphics programs, testing inverse graphics reasoning.

Dependency-Aware Group Policy Optimization traces read-write dependencies for improved credit assignment in terminal-using agents.

NeutronGym provides executable physics-graded environment for LLM agents to design neutron instruments via McStas simulation.

HazardWeaver: LLM agent framework for scientific route selection in multi-step hazard analysis workflows.

HyperBrowseComp: multilingual multimodal benchmark of 423 questions across 13 languages for web-browsing agent evaluation.

FLINT: structured composition framework for table-to-report generation using verifiable atomic insights to improve coherence and traceability over sequential agents.

FLINT: domain-specialized Text-to-SQL system for financial data using lookup agents and multi-hop joins, exceeding 50% on production benchmarks vs. generic systems.

D2K-Bench diagnostic evaluates LLM agent GPU kernel generation quality across algorithmic, dataflow, and low-level optimization guidance levels.

SLM-based intent matching for tool-call oversight in agents, enabling low-latency semantic validation of action relevance.

LLM agents exhibit systematic source preference in search/recommendation across domains; mitigation strategies proposed.

EvoRiskBench: evolving security benchmark for workspace agents via EP-Path-EF framework mapping entry points to runtime effects; nine entry-point categories, five effect categories.

Formalizes actionable indeterminacy in LLM agents: when to act, seek clarification, or repair constraints in preference reasoning with solver-grounded benchmark.

AI agents are becoming a standard part of development workflows, but general-purpose agents weren't built with specialized infrastructure software such as... AI agents are becoming a standard part of development workflows, but general-purpose agents weren’t built with specialized infrastructure software such as NVIDIA DOCA in mind. Without domain-specific knowledge, agents may fall back on guesswork. This is an issue in infrastructure development because every correction cycle takes time away from deployment. DOCA is the unified software platform… Source

RPG enables autonomous robot skill improvement through offline dataset reconstruction and simulation practice.