Category
20,463 papers
A satisfaction floor, computable from two statistics of interaction logs, offers a way to monitor the power users retain in a deployed system, and simulations in random environments show the three quantities are correlated but far from interchangeable.
This work introduces PromptOps, a closedloop framework for monitoring and iteratively recalibrating LLM-as-a-Judge (LLMaaJ) systems and establishes prompt optimization for deployed LLM judges as an inherently iterative maintenance problem and demonstrates that PromptOps provides a practical abstraction for studying and...
Behavior-Conditioned Symbolic Synthesis is introduced---an approach for automated search of interpretable, deterministic symbolic programs that verifiably reproduce behavior---and applied to model both human and machine behavior across hundreds of challenging reasoning problems, pointing to underlying mechanisms remini...
The results show that verification success alone is insufficient evidence of independent cross-agent agreement, and that model capability does not guarantee agreement when formalizing the same source independently.
Reach audiences
Advertise in front of researchers, engineers, and readers.
EFXPLORER is proposed, a constrained exploration framework that maximizes exploration objectives subject to a constraint that preserves established task performance and incorporates a successor distance-based intrinsic reward that captures long-horizon dependencies.
Close-loop evaluation is proposed, an evaluation method for deployed agents that models evaluation as performance estimation under biased raters and censored outcomes, and it requires every level's conclusion to trace back to atomic data and to be computed by versioned rules.
A theoretical framework comparing Darwinian, Lamarckian, and agent-directed evolution following environmental change is developed, to preserve humanity's ability to guide its direction, limit its speed, and intervene when necessary.
The Trust Responsive Authorization Policy is empirically characterized, which maps an Authorization Readiness Score (ARS), a weighted combination of runtime trust, operational stability, and contextual risk, onto discrete authorization levels through an asymmetric rule: escalation requires consecutive observations abov...
Simulated collaboration reveals that, over the course of proof construction, AI agents are far more strongly drawn than humans to explicitly marked gaps; show a relative aversion to densely connected proof centers and to complex or surprising proof goals; and are relatively attracted to surprising proof bodies.
The Two-Ledger Model is proposed: a settlement ledger of FOCUS-conformant billing data joined to an attribution ledger of invocation-grain usage records built on OpenTelemetry GenAI telemetry, which proposes the attribution ledger as an invocation-grain FOCUS profile for standardization.
FlexFloor is presented, a system that enables earlier resource release during synchronous response generation while preserving the expert computation required by ongoing responses and supports faster development and iterative improvement of large language models and AI agents.
BlockLock is presented, which keeps shared batched prefill and pins only the numerical path of the protected request, and needs no custom kernel implementations and constrains only the protected requests.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
