Orchard: An Open-Source Agentic Modeling Framework

Orchard: An Open-Source Agentic Modeling Framework

Artificial Intelligence
Avatar
librarian
27 views
APWA: A Distributed Architecture for Parallelizable Agentic Workflows

APWA: A Distributed Architecture for Paralleli...

Artificial Intelligence
Avatar
librarian
25 views
OpenDeepThink: Parallel Reasoning via Bradley--Terry Aggregation

OpenDeepThink: Parallel Reasoning via Bradley-...

Artificial Intelligence
Avatar
librarian
29 views
Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs

Senses Wide Shut: A Representation-Action Gap ...

Artificial Intelligence
Avatar
librarian
26 views
Harnessing Agentic Evolution

Harnessing Agentic Evolution

Artificial Intelligence
Avatar
librarian
22 views
History Anchors: How Prior Behavior Steers LLM Decisions Toward Unsafe Actions

History Anchors: How Prior Behavior Steers LLM...

Artificial Intelligence
Avatar
librarian
31 views
D-VLA: A High-Concurrency Distributed Asynchronous Reinforcement Learning Framework for Vision-Language-Action Models

D-VLA: A High-Concurrency Distributed Asynchro...

Artificial Intelligence
Avatar
Yucheng Guo
25 views
Differentiable Learning of Lifted Action Schemas for Classical Planning

Differentiable Learning of Lifted Action Schem...

Artificial Intelligence
Avatar
Jonas Reiter
25 views
Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling

Achieving Gold-Medal-Level Olympiad Reasoning ...

Artificial Intelligence
Avatar
librarian
30 views
CAAFC: Chronological Actionable Automated Fact-Checker for misinformation / non-factual hallucination detection and correction

CAAFC: Chronological Actionable Automated Fact...

Artificial Intelligence
Avatar
Islam Eldifrawi
31 views
Formalize, Don't Optimize: The Heuristic Trap in LLM-Generated Combinatorial Solvers

Formalize, Don't Optimize: The Heuristic Trap ...

Artificial Intelligence
Avatar
librarian
31 views
Semantic Reward Collapse and the Preservation of Epistemic Integrity in Adaptive AI Systems

Semantic Reward Collapse and the Preservation ...

Artificial Intelligence
Avatar
librarian
32 views
ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents

ToolCUA: Towards Optimal GUI-Tool Path Orchest...

Artificial Intelligence
Avatar
Xuhao Hu
72 views
$δ$-mem: Efficient Online Memory for Large Language Models

$δ$-mem: Efficient Online Memory for Large Lan...

Artificial Intelligence
Avatar
librarian
60 views
Classifier Context Rot: Monitor Performance Degrades with Context Length

Classifier Context Rot: Monitor Performance De...

Artificial Intelligence
Avatar
librarian
36 views
Reward Hacking in Rubric-Based Reinforcement Learning

Reward Hacking in Rubric-Based Reinforcement L...

Artificial Intelligence
Avatar
Anas Mahmoud
31 views
On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment

On-Policy Self-Evolution via Failure Trajector...

Artificial Intelligence
Avatar
librarian
31 views
When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents

When Simulation Lies: A Sim-to-Real Benchmark ...

Artificial Intelligence
Avatar
Xiaolin Zhou
26 views
From Noise to Diversity: Random Embedding Injection in LLM Reasoning

From Noise to Diversity: Random Embedding Inje...

Artificial Intelligence
Avatar
librarian
28 views
BenchCAD: A Comprehensive, Industry-Standard Benchmark for Programmatic CAD

BenchCAD: A Comprehensive, Industry-Standard B...

Artificial Intelligence
Avatar
librarian
33 views
The Generalized Turing Test: A Foundation for Comparing Intelligence

The Generalized Turing Test: A Foundation for ...

Artificial Intelligence
Avatar
librarian
33 views
NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation

NanoResearch: Co-Evolving Skills, Memory, and ...

Artificial Intelligence
Avatar
librarian
66 views
From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World

From Controlled to the Wild: Evaluation of Pen...

Artificial Intelligence
Avatar
librarian
21 views
Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory

Remember the Decision, Not the Description: A ...

Artificial Intelligence
Avatar
Lizhen Qu
21 views
Shepherd: A Runtime Substrate Empowering Meta-Agents with a Formalized Execution Trace

Shepherd: A Runtime Substrate Empowering Meta-...

Artificial Intelligence
Avatar
librarian
32 views
SkillOS: Learning Skill Curation for Self-Evolving Agents

SkillOS: Learning Skill Curation for Self-Evol...

Artificial Intelligence
Avatar
librarian
45 views
AI Co-Mathematician: Accelerating Mathematicians with Agentic AI

AI Co-Mathematician: Accelerating Mathematicia...

Artificial Intelligence
Avatar
Daniel Zheng
42 views
On-line Learning in Tree MDPs by Treating Policies as Bandit Arms

On-line Learning in Tree MDPs by Treating Poli...

Artificial Intelligence
Avatar
Anvay Shah
32 views
Executable World Models for ARC-AGI-3 in the Era of Coding Agents

Executable World Models for ARC-AGI-3 in the E...

Artificial Intelligence
Avatar
Sergey Rodionov
47 views
Position: Embodied AI Requires a Privacy-Utility Trade-off

Position: Embodied AI Requires a Privacy-Utili...

Artificial Intelligence
Avatar
librarian
34 views
LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents

LongSeeker: Elastic Context Orchestration for ...

Artificial Intelligence
Avatar
librarian
34 views
A Foundation Model for Zero-Shot Logical Rule Induction

A Foundation Model for Zero-Shot Logical Rule ...

Artificial Intelligence
Avatar
librarian
36 views