Function Calling

Feeds to Scour
SubscribedAll
Scoured 305 posts in 7.4 ms

waldekmastykarz/atifact: Turn HAR files, Claude Code, Copilot CLI, and Codex CLI logs into standardized ATIF v1.7 trajectory JSON — ready for debugging, visualization, fine-tuning, and RL pipelines.

 🤖n8n, automation, AI agents, Gemini, Claude, openrouter, grok, chatgpt  Content type: Code
github.com··Hacker News

Brain-Prompt Injection: A Route-Safety Audit for BCI-LLM Agents

 🛡️AI Security  Content type: Academic
arxiv.org·

Translate-R1: Cost-Aware Translation Tool Use via Reinforcement Learning

 💬Prompt Engineering  Content type: Academic
arxiv.org·

AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation Models

 🤖Agentic AI  Content type: Academic
arxiv.org·

DexFuture: Hierarchical Future-State Visuomotor Targeting for Bimanual Dexterous Tool Use

 🎭Anthropic Claude  Content type: Academic
arxiv.org·

Less Context, Better Agents: Efficient Context Engineering for Long-Horizon Tool-Using LLM Agents

 🤖Agentic AI  Content type: Academic
arxiv.org·

Agentic Large Language Models for Automated Structural Analysis of 3D Frame Systems

 🎭Anthropic Claude  Content type: Academic
arxiv.org·

AURA: Intent-Directed Probing for Implicit-Need Surfacing in Situated LLM Agents

 🤖Agentic AI  Content type: Academic
arxiv.org·

TAPO: Tool-Aware Policy Optimization via Credit Transfer for Multimodal Search Agents

 🤖Agentic AI  Content type: Academic
arxiv.org·

Declarative Skills for AI Agents in Knowledge-Grounded Tool-Use Workflows

 💬Prompt Engineering  Content type: Academic
arxiv.org·

Beyond tokens: a unified framework for latent communication in LLM-based multi-agent systems

 🤖Agentic AI  Content type: Academic
arxiv.org·

Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents

 🎭Anthropic Claude  Content type: Academic
arxiv.org·

Humans' ALMANAC: A Human Collaboration Dataset of Action-Level Mental Model Annotations for Agent Collaboration

 👥CrewAI  Content type: Academic
arxiv.org·

From Risk Classification to Action Plan Remediation: A Guardrail Feedback Driven Framework for LLM Agents

 💬Prompt Engineering  Content type: Academic
arxiv.org·

Do More Agents Help? Controlled and Protocol-Aligned Evaluation of LLM Agent Workflows

 🦜LangChain  Content type: Academic
arxiv.org·

Beyond Similarity: Trustworthy Memory Search for Personal AI Agents

 🛡️AI Security  Content type: Academic
arxiv.org·

ToolChoiceConfusion: Causal Minimal Tool Filtering for Reliable LLM Agents

 🤖Agentic AI  Content type: Academic
arxiv.org·

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

 🤖Agentic AI  Content type: Academic
arxiv.org·

Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data

 🤖Transformers  Content type: Academic
arxiv.org·

SHIELDS: Automating OS Hardening with Iterative Multi-Agent Remediation

 🤖Agentic AI  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