Artificial Intelligence

RSI-Prime: Training Models to Train Models
Avatar
librarian
5 views
WoRD: Diffusion-Based Posterior Inference for Online Goal Recognition
Avatar
librarian
4 views
The Resolution Hypothesis: Agent Evolution's Key Is Identifying Improvements
Avatar
librarian
5 views
Colombo: A Frontier-to-Frontier Autoresearch System for Oracle-Based Optimization
Avatar
librarian
5 views
Agent Trust Infrastructure (ATI): A Federated Identity, Trust, Attestation, and Accountability Architecture for Cross-Organization Autonomous AI Agents
Avatar
librarian
5 views
Remembered as Brief: Stored Preferences SilentlyRemove Decision-Critical Information
Avatar
librarian
7 views
SciWorkBench: A Benchmark for Real Scientific Workflows
Avatar
librarian
4 views
The Between-Round Decision in Autonomous Research: An LLM Controller That Reads the Whole Trajectory
Avatar
librarian
6 views
EvoDisco: Strategy Discovery for Evolving Agent Memory
Avatar
librarian
5 views
RegimeCouncil: Paired-Evidence Routing For Memory Conflict Governance In LLM Agents
Avatar
librarian
4 views
RAG in a Trenchcoat: When Minimal Memory Is Enough for Agentic Systems, and When It Isn't
Avatar
librarian
4 views
Procedure without Judgment: What Small Language Models Learn under an Exact Verifier
Avatar
librarian
12 views
SciResearch-Eval: Evaluating Scientific Judgment in Autonomous Experimental Agents
Avatar
librarian
17 views
Right Reason, Wrong Advice: Evaluating Recourse in LLM Explanations of Denied Requests
Avatar
librarian
14 views
Sage S2.1 Flash Technical Report

Sage S2.1 Flash Technical Report

Artificial Intelligence
Avatar
librarian
9 views
Turing Agent: Agentic Formal Verification for Mathematical Research
Avatar
librarian
12 views
Benchleaking Is Accelerating: Benchmark contamination has worsened sharply in the past month -- from post-training down to pre-training base models
Avatar
librarian
18 views
AdMem: Expectation-Grounded Procedural Memory for Long-Horizon Task-Solving Agents
Avatar
librarian
8 views
ToolGraph as a Q-Function for Test-Time Scaling of Tool-Use Agents
Avatar
librarian
8 views
GEAR$^2$: Pruned Experts Live On through Gated Reuse of Activated Experts and a Missing-Mass Residual
Avatar
librarian
9 views
GainCtrl: Predicting Remaining Gains for Efficient LLM Agent Execution
Avatar
librarian
10 views
GEM-MM: Reducing VLM Hallucination with Entropy-Guided Preference Alignment
Avatar
librarian
12 views
The Frontier Must Grow - Self-proposed, interpreter-labelled training roughly doubles a 4B model's accuracy on a fresh exam as its verified frontier grows
Avatar
librarian
11 views
HEAMS: Holistic Evaluation of Agent Memory Systems
Avatar
librarian
24 views
CoReMem: Cost-Internalizing Memory for Successive Coding Tasks with Prospective Valuation
Avatar
librarian
31 views
Classical Energies Learn to Reason 1,000x Faster than Looped Models
Avatar
librarian
34 views
CapLite: Prompt-Injection Defense for Small Language Model Agents without Model-Written Security Artifacts
Avatar
librarian
36 views
Ballad: Bandit-Based LLM Routing for Automated Heuristic Discovery
Avatar
librarian
25 views
AnalogLayoutWorld: An Open Benchmark for Agentic Analog Layout Design
Avatar
librarian
36 views
Your Vision Foundation Model Is Secretly an EEG Foundation Model
Avatar
librarian
33 views
LiveGeo: Benchmarking Geographic Agents in Continuously Evolving Worlds
Avatar
librarian
15 views
AgentSSL: Can MLE Agents Leverage Unlabeled Data?
Avatar
librarian
16 views