Artificial Intelligence

OpenForgeRL: Train Harness-native Agents in Any Environment

OpenForgeRL: Train Harness-native Agents in An...

Artificial Intelligence
Avatar
librarian
27 views
Beyond Sycophancy: Structured Resistance and Compliance in LLM Moral Reasoning

Beyond Sycophancy: Structured Resistance and C...

Artificial Intelligence
Avatar
librarian
25 views
Detecting LLM-Generated Tokens in Human--LLM Coauthored Text

Detecting LLM-Generated Tokens in Human--LLM C...

Artificial Intelligence
Avatar
librarian
26 views
PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning

PATS: Policy-Aware Training Scaffolding for Ag...

Artificial Intelligence
Avatar
Yipeng Shi
31 views
AREX: Towards a Recursively Self-Improving Agent for Deep Research

AREX: Towards a Recursively Self-Improving Age...

Artificial Intelligence
Avatar
librarian
30 views
Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture Problems

Agentic Context Management: Solving Agent Memo...

Artificial Intelligence
Avatar
librarian
29 views
SoftReason: A Fully Differentiable Neuro-Soft-Symbolic Deductive Reasoning Architecture over High-Dimensional Perceptual Data

SoftReason: A Fully Differentiable Neuro-Soft-...

Artificial Intelligence
Avatar
Wael AbdAlmageed
28 views
PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoning

PRO-LONG: Programmatic Memory Enables Long-Hor...

Artificial Intelligence
Avatar
Alexis Fox
30 views
PoTRE: Test-Time Reasoning inspired by Cognitive Heterogeneity

PoTRE: Test-Time Reasoning inspired by Cogniti...

Artificial Intelligence
Avatar
librarian
26 views
Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations

Train the Model, Not the Reader: Decodability ...

Artificial Intelligence
Avatar
Hiskias Dingeto
26 views
ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D

ResearchArena: Evaluating Sabotage and Monitor...

Artificial Intelligence
Avatar
librarian
30 views
Agents in the Wild: Where Research Meets Deployment

Agents in the Wild: Where Research Meets Deplo...

Artificial Intelligence
Avatar
Grace Hui Yang
26 views
CodeRescue: Budget-Calibrated Recovery Routing for Coding Agents

CodeRescue: Budget-Calibrated Recovery Routing...

Artificial Intelligence
Avatar
librarian
24 views
WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting

WorldCupArena: Fine-Grained Evaluation of Lang...

Artificial Intelligence
Avatar
librarian
28 views
Rethinking Heterogeneous LLM Merging: A Weighted Model Averaging Perspective

Rethinking Heterogeneous LLM Merging: A Weight...

Artificial Intelligence
Avatar
librarian
28 views
Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering

Can We Break LLMs Out of Self-Loops? Fine-Grai...

Artificial Intelligence
Avatar
Sheldon Yu
24 views
Logical Judgments Under Pressure: Diagnosing Syllogistic Stability with Learned Soft Prefixes

Logical Judgments Under Pressure: Diagnosing S...

Artificial Intelligence
Avatar
librarian
26 views
AutoSynthesis: An agentic system for automated meta-analysis

AutoSynthesis: An agentic system for automated...

Artificial Intelligence
Avatar
librarian
48 views
When Words Are Safe But Actions Kill: Probing Physical Danger Beyond Text Safety in Hidden-State Risk Space

When Words Are Safe But Actions Kill: Probing ...

Artificial Intelligence
Avatar
librarian
42 views
Concept-Guided Spatial Regularization for World Models in Atari Pong

Concept-Guided Spatial Regularization for Worl...

Artificial Intelligence
Avatar
librarian
46 views
Long-Context Fine-Tuning with Limited VRAM

Long-Context Fine-Tuning with Limited VRAM

Artificial Intelligence
Avatar
librarian
40 views
MedFailBench: A Clinician-Built Open-Source Benchmark for Medical AI Safety Boundary Inspection

MedFailBench: A Clinician-Built Open-Source Be...

Artificial Intelligence
Avatar
Goktug Ozkan
44 views
Can We Trust Item Response Theory for AI Evaluation?

Can We Trust Item Response Theory for AI Evalu...

Artificial Intelligence
Avatar
Han Jiang
32 views
Benchmarking Multimodal Large Language Models for Scientific Visualization Literacy

Benchmarking Multimodal Large Language Models ...

Artificial Intelligence
Avatar
Patrick Do
35 views
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration

SearchOS-V1: Towards Robust Open-Domain Inform...

Artificial Intelligence
Avatar
librarian
36 views
The Industrialization of Research ; On AI-Driven Science and Its Consequences

The Industrialization of Research ; On AI-Driv...

Artificial Intelligence
Avatar
Emmanuel Jeannot
34 views
Pretraining Data Can Be Poisoned through Computational Propaganda

Pretraining Data Can Be Poisoned through Compu...

Artificial Intelligence
Avatar
Victoria Graf
31 views
Experience Memory Graph: One-Shot Error Correction for Agents

Experience Memory Graph: One-Shot Error Correc...

Artificial Intelligence
Avatar
Wenjun Wang
41 views
Reproducing human biases in route choice using large language models: Toward scalable behavioral modeling

Reproducing human biases in route choice using...

Artificial Intelligence
Avatar
Shuxian Xu
48 views
Interaction Scaling: Grounding the Third Axis of Test-Time Compute

Interaction Scaling: Grounding the Third Axis ...

Artificial Intelligence
Avatar
Bojie Li
47 views
Think Through a Bottleneck: Hourglass Reasoning for Rigorous Induction

Think Through a Bottleneck: Hourglass Reasonin...

Artificial Intelligence
Avatar
librarian
46 views
Filtering Harmful Actions Isn't Enough: Phantom Transfer in Agentic SDF

Filtering Harmful Actions Isn't Enough: Phanto...

Artificial Intelligence
Avatar
librarian
43 views
Load more