Tool Use

Feeds to Scour
SubscribedAll
Scoured 705 posts in 9.3 ms

MemToolAgent overview with a simple restaurant booking scenario where the agent retrieves similar memories, receives feedback on an invalid time format, and generates a reflection to update its memory

 🧠LLMs  Content type: Academic
arxiv.org·
Less-relevant results

Pega targets token tax on agentic application development

 🕵️AI Agents  Content type: Blog
computerweekly.com·

Tejas-TA/predikit: The missing bridge between your ML models and your AI agents.

 🕵️AI Agents  Content type: Code
github.com··Hacker News

FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse

 🕵️AI Agents  Content type: Academic
arxiv.org·

New comment by Ayaz_Saifi in "Ask HN: Who wants to be hired? (June 2026)"

 🕵️AI Agents

vishal-dehurdle/state-harness: Runtime safety net for LLM agents. Detects token spirals, kills doomed tasks early, tells you exactly why. Rust core, Python SDK. pip install state-harness

 🧠LLMs  Content type: Code

Pushing the Limits of LLM Tool Calling via Experiential Knowledge Integration and Activation

 🕵️AI Agents  Content type: Academic
arxiv.org·

New comment by pknerd in "Ask HN: Who wants to be hired? (June 2026)"

 🕵️AI Agents  Content type: Discussion

AGENTSERVESIM: A Hardware-aware Simulator for Multi-Turn LLM Agent Serving

 🧠LLMs  Content type: Academic
arxiv.org·

SecureClaw: Clawing Back Control of LLM Agents

 🕵️AI Agents  Content type: Academic
arxiv.org·

fix(channels): keep commentary progress bounded · openclaw/openclaw@2698387

 🧠LLMs  Content type: Code
github.com·

OCELOT: Inference-Leakage Budgets for Privacy-Preserving LLM Agents

 🖥️Inference Compute  Content type: Academic
arxiv.org·

New comment by gab18 in "Ask HN: Who wants to be hired? (June 2026)"

 🕵️AI Agents  Content type: Discussion

REFLECT: Intervention-Supported Error Attribution for Silent Failures in LLM Agent Traces

 🧠LLMs  Content type: Academic
arxiv.org·

feat: add commentary text emission to Claude CLI streaming parser · openclaw/openclaw@d03952c

 🧠LLMs  Content type: Code
github.com·

The Cold-Start Safety Gap in LLM Agents

 🧠LLMs  Content type: Academic
arxiv.org·

Beyond APIs: Probing the Limits of MLLMs in Physical Tool Use

 🦾Robotics  Content type: Academic
arxiv.org·

docs: document embedded helper classifier tests · openclaw/openclaw@77d0792

 🔓Open-source Models  Content type: Code
github.com·

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

 🧠LLMs  Content type: Academic
arxiv.org·

New comment by devananddev93 in "Ask HN: Who wants to be hired? (June 2026)"

 🕵️AI Agents  Content type: Discussion
Sign up or log in to see more results

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