AI Agents

Feeds to Scour
SubscribedAll
Scoured 154 posts in 6.3 ms

Skill-3D: Evolving Scene-Aware Skills for Agentic 3D Spatial Reasoning

 🔍Interpretability  Content type: Academic
arxiv.org·

Does Persona Make LLMs K-pop Fans? A Pilot Study of LLM-Based Online Concert Audience Agents

 🧠AI Research  Content type: Academic
arxiv.org·

SkillAxe: Sharpening LLM-Authored Agent Skills Through Evaluation-Guided Self-Refinement

 💬LLMs  Content type: Academic
arxiv.org·

Context-Fractured Decomposition Attacks on Tool-Using LLM Agents: Exploiting Artifact Provenance Gaps

 💬LLMs  Content type: Academic
arxiv.org·

CollabSim: A CSCW-Grounded Methodology for Investigating Collaborative Competence of LLM Agents through Controlled Multi-Agent Experiments

 💬LLMs  Content type: Academic
arxiv.org·

SkillJuror: Measuring How Agent Skill Organization Changes Runtime Behavior

 🖥️ML Systems  Content type: Academic
arxiv.org·

PerspectiveGap: A Benchmark for Multi-Agent Orchestration Prompting

 🔍Interpretability  Content type: Academic
arxiv.org·

InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning

 ⚙️Model Training  Content type: Academic
arxiv.org·

LLM Agent-Assisted Reverse Engineering with Quantitative Readability Metrics

 💬LLMs  Content type: Academic
arxiv.org·

Bayesian-Agent: Posterior-Guided Skill Evolution for LLM Agent Harnesses

 💬LLMs  Content type: Academic
arxiv.org·

APPO: Agentic Procedural Policy Optimization

 🎮Reinforcement Learning  Content type: Academic
arxiv.org·

TRACE: Trajectory Reasoning through Adaptive Cross-Step Evidence Aggregation for LLM Agents

 🎮Reinforcement Learning  Content type: Academic
arxiv.org·

The Cold-Start Safety Gap in LLM Agents

 💬LLMs  Content type: Academic
arxiv.org·

Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agents

 🎮Reinforcement Learning  Content type: Academic
arxiv.org·

Causal Agent Replay: Counterfactual Attribution for LLM-Agent Failures

 🎮Reinforcement Learning  Content type: Academic
arxiv.org·

DeployBench: Benchmarking LLM Agents for Research Artifact Deployment

 🖥️ML Systems  Content type: Academic
arxiv.org·

Runtime Skill Audit: Targeted Runtime Probing for Agent Skill Security

 🎮Reinforcement Learning  Content type: Academic
arxiv.org·

Memory Beyond Recall: A Dual-Process Cognitive Memory System for Self-Evolving LLM Agents

 🎮Reinforcement Learning  Content type: Academic
arxiv.org·

Beyond Compaction: Structured Context Eviction for Long-Horizon Agents

 🎮Reinforcement Learning  Content type: Academic
arxiv.org·

ToolChoiceConfusion: Causal Minimal Tool Filtering for Reliable LLM Agents

 💬LLMs  Content type: Academic
arxiv.org·

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help