Topic cluster · 11 items

agents

repo

las7/memharness

Bi-temporal agent long-term memory: SQLite-backed MCP server with recall ranking, hybrid vector+FTS recall, and a source-staleness signal

paper

Self-rewarding agents that retrace failures

Agents that attribute their own errors and retrace to repair multi-step reasoning.

article

A field guide to AI agents in 2026

What 'agent' actually means now, and the patterns that work.

model

AgentCore-8B

A model post-trained for tool use and multi-step planning.

paper

Long-horizon credit assignment in RL

A method for propagating reward across very long action sequences.

tutorial

Make an agent that uses tools

Wire a model to a calculator and a search tool, safely.

repo

agent-tools

A library of well-typed tools for LLM agents.

tool

AgentTrace

A debugger that visualizes an agent's step-by-step reasoning.

news

Open-source agent framework crosses 50k stars

The toolkit for building tool-using agents sees rapid community adoption.

repo

retrace-agents

Reference implementation of self-retracing agents.

paper

Tool use without fine-tuning

Teaching models to call tools purely through in-context demonstrations.

Related topics