Artificial Intelligence

GRADUS: Discovering and Recovering Agent Lessons from the Environment's Latent Syllabus

GRADUS: Discovering and Recovering Agent Lesso...

Artificial Intelligence
Avatar
librarian
3 views
Towards Robust Model Organisms for Eliciting Latent Knowledge

Towards Robust Model Organisms for Eliciting L...

Artificial Intelligence
Avatar
librarian
9 views
Agent World Model in the Wild: Computer-Use Agent Environment Synthesis

Agent World Model in the Wild: Computer-Use Ag...

Artificial Intelligence
Avatar
Zhaoyang Wang
5 views
AnyGoal: On World Model Generalization Beyond Expert Rollouts

AnyGoal: On World Model Generalization Beyond ...

Artificial Intelligence
Avatar
librarian
15 views
GraphEvoResearcher: Graph-Aware Training-Free Self-Reflective Reasoning for Cost-Bounded Multi-Hop Question Answering

GraphEvoResearcher: Graph-Aware Training-Free ...

Artificial Intelligence
Avatar
Suxing Liu
6 views
ClueFlow: Learning Long-Horizon Search through Attributed Research-State Transitions

ClueFlow: Learning Long-Horizon Search through...

Artificial Intelligence
Avatar
librarian
6 views
KnowGPO: Knowledge-Grouped Policy Optimization for Search Agents

KnowGPO: Knowledge-Grouped Policy Optimization...

Artificial Intelligence
Avatar
Siqi Chen
24 views
LEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use Agents

LEASH: Uncertainty-Aware Weak-to-Strong Escala...

Artificial Intelligence
Avatar
Qingni Wang
35 views
A team of Gemini 4 Argon agents beats Minecraft

A team of Gemini 4 Argon agents beats Minecraft

Artificial Intelligence
Avatar
librarian
37 views
MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering

MLExpert: Towards a Generalist Agentic Model f...

Artificial Intelligence
Avatar
librarian
30 views
FDE-Gym: The Last Mile of AI Delivery

FDE-Gym: The Last Mile of AI Delivery

Artificial Intelligence
Avatar
librarian
29 views
LoopAhead: Speculating Ahead for Faster Decoding in Looped Language Models

LoopAhead: Speculating Ahead for Faster Decodi...

Artificial Intelligence
Avatar
librarian
21 views
Learning from Interaction Experience via Localized Context Distillation

Learning from Interaction Experience via Local...

Artificial Intelligence
Avatar
librarian
19 views
Learning Intrinsic Dynamics in Latent World Models

Learning Intrinsic Dynamics in Latent World Models

Artificial Intelligence
Avatar
librarian
20 views
MetaExp: Learning to Self-Improve through Experience via Verifiable Cross-Task Environment Scaling

MetaExp: Learning to Self-Improve through Expe...

Artificial Intelligence
Avatar
librarian
19 views
Functional Subnetwork Localization for Efficient Continual Learning in Large Language Models

Functional Subnetwork Localization for Efficie...

Artificial Intelligence
Avatar
librarian
18 views
Reinforcement Learning-driven Diffusion Models: Language, Vision, and Beyond

Reinforcement Learning-driven Diffusion Models...

Artificial Intelligence
Avatar
librarian
20 views
TreeFlex: Agents Navigating Their Own Search Trees

TreeFlex: Agents Navigating Their Own Search Trees

Artificial Intelligence
Avatar
Dongzhuo Li
42 views
SwarmRSI: Recursive Self-Improvement through Evolving Scientific Agent Swarm

SwarmRSI: Recursive Self-Improvement through E...

Artificial Intelligence
Avatar
librarian
31 views
Scaling Discovery Requires Forgetting

Scaling Discovery Requires Forgetting

Artificial Intelligence
Avatar
librarian
38 views
Co-Evolving Acting and Forecasting for Language Agents

Co-Evolving Acting and Forecasting for Languag...

Artificial Intelligence
Avatar
librarian
27 views
Euler: Towards Human-Centered Multi-Agent Mathematical Discovery

Euler: Towards Human-Centered Multi-Agent Math...

Artificial Intelligence
Avatar
librarian
25 views
ActionOPD: Distilling Decisions, Not Tokens

ActionOPD: Distilling Decisions, Not Tokens

Artificial Intelligence
Avatar
librarian
28 views
ReproBAIT: Can coding agents build their own biological AI tools?

ReproBAIT: Can coding agents build their own b...

Artificial Intelligence
Avatar
librarian
18 views
Teaching Agents in their Own Style: Blackbox Teacher Distillation for Web Agents

Teaching Agents in their Own Style: Blackbox T...

Artificial Intelligence
Avatar
librarian
17 views
LAGO: Language Agents with Reusable Growing Options

LAGO: Language Agents with Reusable Growing Op...

Artificial Intelligence
Avatar
librarian
12 views
Self-Evolving Agent Harness

Self-Evolving Agent Harness

Artificial Intelligence
Avatar
librarian
89 views
Who Improves the Robot? Toward Physical Recursive Self-Improvement

Who Improves the Robot? Toward Physical Recurs...

Artificial Intelligence
Avatar
librarian
46 views
AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards

AesCode: Aesthetic Code Generation with Decoup...

Artificial Intelligence
Avatar
librarian
31 views
Beyond the Verdict: Agentic Code Judging with Verifiable Feedback

Beyond the Verdict: Agentic Code Judging with ...

Artificial Intelligence
Avatar
librarian
36 views
BLADE: Auditing Information Use for Failure Attribution in LLM Multi-Agent Systems

BLADE: Auditing Information Use for Failure At...

Artificial Intelligence
Avatar
librarian
35 views
Autonomous Science Bench: Evaluating AI Agents for Autonomous Scientific Discovery

Autonomous Science Bench: Evaluating AI Agents...

Artificial Intelligence
Avatar
Han Liu
62 views
Load more