Counterfactual Evidence Audits Predict LLM-Agent Susceptibility to Ranked Context
Research
Research News
New papers, breakthroughs and academic AI research
SovereignPA-Bench: Evaluating User-Owned Personal Agents under Evolving Intent, Platform Mediation, and Consent Constraints
Research
A Unified Framework for Bayesian Data Assimilation with Generative Models and Observation Interpolants
Research
From Positionwise Confidence to Prefix Scheduling: Verifier Skipping in Speculative Decoding
Research
Offline Policy Optimization with Posterior Sampling
Research
Rethinking the Evaluation of Harness Evolution for Agents
Research
WAM-OPD: Joint Video-Action Supervision for World Action Model Post-Training with On-Policy Distillation
Research
NARA: Anchor-Conditioned Representation Learning for Heterogeneous Vector Geoentities
Research
Rethinking RAG in Long Videos: What to Retrieve and How to Use It?
Research
How Artificial Intelligence LLM Engines Shape the Global Conflict Information Environment
Research
One Hypothesis Is Not Enough: Abductive Reasoning with Agentic Hypothesis Refinement over Knowledge Graphs
Research
Latent Goal Prediction from Language for Model-Based Planning
Research