Researchers have introduced BOHM, a zero-cost attribution method for compound AI systems that extracts hierarchical attribution trees directly from existing routing weights. The method provides multi-resolution attributi…
Researchers introduced NeuroNL2LTL, a neurosymbolic framework that translates natural language into Linear Temporal Logic (LTL) with formal correctness guarantees. The system uses a structure-preserving intermediate repr…
Researchers have developed Research Math Agents (RMA), an agentic framework that automates reasoning on research-level mathematical problems by decomposing proof-solving into specialized modules coordinated by multiple a…
Researchers have developed SciAtlas, a large-scale knowledge graph integrating over 43 million papers across 26 disciplines, 157 million entities, and 3 billion triplets to serve as a structured cognitive map for automat…
Researchers have developed A-LEMS, a measurement framework that redefines AI energy accounting from energy per inference to Energy per Successful Goal (EpG), aggregating total workflow energy across all execution attempt…
Researchers introduced ImProver 2, a neurosymbolic framework for automated proof optimization in Lean 4 that combines a data-efficient expert-iteration pipeline with a scaffold exposing formal structure and lightweight i…
Researchers have introduced EVE-Agent, a self-evolving search agent that requires each training example to include a source-grounded evidence span verifying its answer. The system uses a proposer-solver framework where a…
New research formalizes fundamental computational limits as design specifications for trustworthy AI systems, proving that transformer architectures have a fixed accuracy ceiling—the Deterministic Horizon—determined sole…
Researchers introduced PathCal, a training-free decoding controller that calibrates reasoning paths in large language models by distinguishing distinct types of reflection markers such as "wait" and "but." The system int…
Researchers have developed Inductive Deductive Synthesis (IDS), an AI system that jointly generates formally verified code and mathematical proofs, solving a long-standing challenge in automated software verification. In…
A new theory of accountability boundaries in agentic AI ecosystems identifies when AI capabilities can be safely modularized across organizations and when they must remain integrated. The framework introduces "accountabi…
A new survey from arXiv defines "AutoResearch" as the spectrum of AI-powered scientific workflow automation, moving from human-steered "Vibe Research" to emerging AI-led systems that coordinate larger portions of the dis…
Researchers have introduced the Foundation Protocol (FP), a graph-first coordination layer designed to manage interactions among autonomous agents, tools, humans, and institutions in an emerging human-AI society. The pro…
Researchers have developed GENSTRAT, a system that uses procedurally generated card games to evaluate strategic reasoning in large language models (LLMs). In a tournament of over 36,000 matches across 50 benchmark games,…
Researchers have identified a fundamental flaw in how AI agents are evaluated for knowledge work, finding that higher benchmark scores do not reliably indicate real-world performance. The team proposes a three-step frame…
Researchers introduced parallel context compaction for long-horizon LLM agent serving, addressing the problem of growing conversation histories exceeding context windows. The method provides fine-grained, predictable con…
Researchers introduced Ontological Knowledge Blocks (OKBs), a programmable governance infrastructure that compiles regulatory obligations into machine-checkable constraints over structured evidence graphs, addressing the…
Researchers have developed DART, a modular runtime that addresses the failure of structured tool agents mid-execution by certifying semantically recoverable boundaries before restoring from a local checkpoint. The system…
Researchers have developed the Ventilator Decision Support System (VDSS), a human-in-the-loop multi-agent framework that coordinates modular decision components through structured interfaces to provide traceable, persona…
Researchers have developed GEM-4D, a geometry-grounded video world model that generates physically consistent video predictions for robot manipulation by injecting dense 4D correspondence supervision from a pretrained ge…