Artificial Intelligence

F$^3$: What Makes Good Experience in World-Action Models?
Avatar
librarian
0 views
WorldRuler: Interactive World Modeling under Configurable Rules
Avatar
librarian
0 views
Think Offline, Act in Real Time: Self-Improving Visual Game Agents through Code
Avatar
librarian
0 views
MoE-Context: Show the Model Only What It Needs
Avatar
librarian
3 views
KnowledgeClaw: Towards Agentic Knowledge Engineering via Omnimodal Hypergraphs
Avatar
librarian
4 views
OpenKAGE: Open-Ended Lifelong Learning in the Open World via Knowledge-Sharing Agent-Group Evolution
Avatar
librarian
3 views
Semantic Context Handoff with On-Demand Evidence for Long-Horizon Agents
Avatar
librarian
4 views
ARISE: Practical Self-Evolving Memory for Accurate and Cost-Efficient Enterprise Agents
Avatar
librarian
5 views
Thinking Fast, Anywhere: One System-1 for the Decision Points of Any Agent Workflow
Avatar
librarian
4 views
Evidence-Based Credit Assignment for Search-Augmented Language Models
Avatar
librarian
3 views
RSI-Prime: Training Models to Train Models
Avatar
librarian
17 views
WoRD: Diffusion-Based Posterior Inference for Online Goal Recognition
Avatar
librarian
7 views
The Resolution Hypothesis: Agent Evolution's Key Is Identifying Improvements
Avatar
librarian
13 views
Colombo: A Frontier-to-Frontier Autoresearch System for Oracle-Based Optimization
Avatar
librarian
15 views
Agent Trust Infrastructure (ATI): A Federated Identity, Trust, Attestation, and Accountability Architecture for Cross-Organization Autonomous AI Agents
Avatar
librarian
10 views
Remembered as Brief: Stored Preferences SilentlyRemove Decision-Critical Information
Avatar
librarian
14 views
SciWorkBench: A Benchmark for Real Scientific Workflows
Avatar
librarian
7 views
The Between-Round Decision in Autonomous Research: An LLM Controller That Reads the Whole Trajectory
Avatar
librarian
12 views
EvoDisco: Strategy Discovery for Evolving Agent Memory
Avatar
librarian
9 views
RegimeCouncil: Paired-Evidence Routing For Memory Conflict Governance In LLM Agents
Avatar
librarian
10 views
RAG in a Trenchcoat: When Minimal Memory Is Enough for Agentic Systems, and When It Isn't
Avatar
librarian
9 views
Procedure without Judgment: What Small Language Models Learn under an Exact Verifier
Avatar
librarian
15 views
SciResearch-Eval: Evaluating Scientific Judgment in Autonomous Experimental Agents
Avatar
librarian
20 views
Right Reason, Wrong Advice: Evaluating Recourse in LLM Explanations of Denied Requests
Avatar
librarian
16 views
Sage S2.1 Flash Technical Report

Sage S2.1 Flash Technical Report

Artificial Intelligence
Avatar
librarian
10 views
Turing Agent: Agentic Formal Verification for Mathematical Research
Avatar
librarian
14 views
Benchleaking Is Accelerating: Benchmark contamination has worsened sharply in the past month -- from post-training down to pre-training base models
Avatar
librarian
20 views
AdMem: Expectation-Grounded Procedural Memory for Long-Horizon Task-Solving Agents
Avatar
librarian
11 views
ToolGraph as a Q-Function for Test-Time Scaling of Tool-Use Agents
Avatar
librarian
11 views
GEAR$^2$: Pruned Experts Live On through Gated Reuse of Activated Experts and a Missing-Mass Residual
Avatar
librarian
15 views
GainCtrl: Predicting Remaining Gains for Efficient LLM Agent Execution
Avatar
librarian
12 views
GEM-MM: Reducing VLM Hallucination with Entropy-Guided Preference Alignment
Avatar
librarian
13 views