01Agents
Tools
Agents and dev tools worth using, the releases that change the work, and status-page incidents worth watching.
Other
Run fast, private agents on-device with LFM2.5-24B-A2B
LiquidAI's LFM2.5-24B-A2B targets running agents on-device for private, local inference.
Open SWE: An Open-Source Framework for Internal Coding Agents
LangChain open-sources Open SWE, a framework for building internal coding agents.
Redesigning source control at Anthropic
Anthropic's merges per day grew more than tenfold and source control became its biggest development bottleneck; the post covers migrating to an in-house version control system in five months.
How to engineer an AI harness for game development
Builder essay on engineering an AI harness for game development — 136 points and 61 comments on HN, with the thread working through why LLMs fall over on game-y tasks.
Anthropic research: Distillation defenses
Anthropic says new methods reduced the amount of data harvested by distillers by around 90%, per early evidence in the Oct 12, 2026 post.
SWE-Duel: Towards a Self-Scaling Arena for Coding Agents
arXiv paper (submitted 8 Oct 2026) proposing SWE-Duel, a self-scaling arena for evaluating coding agents; authors Wei Minn, Zhensu Sun, Lwin Khin Shar, David Lo.
MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement
Technical report of the MiMo V2.6 series — scaling reinforcement learning towards self-improvement.
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?
Introduces Learn2Play Bench, a benchmark measuring how well LLM agents learn from experience in unfamiliar environments.
Anthropic research: Investigating unintended model actions
Describes examples of unintended model actions observed during evaluations and internal use of Claude — part of Anthropic's effort to publish more frequent standalone reports on model behavior and alignment.
GitHub Copilot weekly releases — October 5
Worth reading
SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces
Self-distills spatial intelligence from verified coding-agent traces; the paper opens from the premise of coding agents' widespread adoption.
SuperNav: An Agentic Navigation System for Any Task in Any Scene
Paper presents SuperNav, described as an agentic navigation system for diverse tasks and scenes.
How to build great out-of-the-box user experiences with Managed Deep Agents
LangChain on building out-of-the-box user experiences with Managed Deep Agents — the post's URL points to a Slack SDK for the deepagents framework.
RoboQuest: Generalist Physical Agents that Search, Inspect and Test
A benchmark for goal-directed embodied exploration — generalist physical agents that search, inspect and test. Physical-agent eval rather than coding-agent, but squarely agent-benchmark research.
LegalOn halves Codex costs while maintaining development speed
OpenAI customer story on Codex in production: LegalOn halves costs while maintaining development speed — a concrete cost-outcome data point for coding-agent deployments.
From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation
Proposes agentic language world models — interactive environment simulators built from traces, letting agents run in simulated worlds; relevant to anyone building agent training or eval environments.
Scaling Agentic Data for Long-Horizon Terminal Intelligence
Research on scaling agentic data for long-horizon terminal intelligence — the data side of long-horizon agentic performance.
Building effective agent automations
Reference implementation walkthrough of agent automations — covers sources, destination, agent, schedule, memory, and guardrails, plus common failure modes. By Lance Martin and CJ Avilla, 9 min read.
How Oracle turns days of work into minutes with ChatGPT and Codex
OpenAI customer story on Oracle's use of ChatGPT and Codex — headline claim is turning days of work into minutes.
MIMESIS: Learning User Simulators as Training Environments for Interactive Agents
Paper proposes learning user simulators as training environments for interactive agents, framing simulated users as a scalable alternative to costly human involvement.
Augment Code's next chapter
Worth reading
DecepEval: A Benchmark for Evaluating Deception in LLM Agents
Asks when LLM agents become more likely to deceive, and introduces a benchmark for evaluating deception in LLM agents.
WebFovea: When the Model Is Right but the Click Is Wrong -- Reliable Round Trips for Vision-Based Web Agents on Live Websites
On the failure mode where a vision-based web agent's model picks the right element but the click lands wrong — reliable round trips for agents running on live websites.
A Closer Look at Agentic BBO: Benchmarking LLM Agents for Black-Box Optimization
Introduces AgenticBBO-Bench, a unified benchmark for LLM agents on black-box optimization tasks.
AgentGarten: Code Worlds for Evolving Agents
Agents learn through interaction, and what they can learn is bounded by the environments they learn in — AgentGarten's answer is code worlds built for evolving agents.
Understanding and Enhancing Backdoor Persistency in LLM Agent Post-Training
Asks whether benign post-training can remove inherited backdoors in LLM agents, and examines how persistent those backdoors remain — security reading for anyone fine-tuning or sourcing agent models.
CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?
Introduces an executable benchmark for evaluating whether long-horizon agents can synthesize static-analysis checkers — a concrete yardstick for coding-agent evals on extended, multi-step work.
Base Models Can Reason By Taking a Cue From Training Data
Paper reports two opening tokens can bring a base model's reasoning performance close to that of a tuned model.
Claude Code in the cloud: a field guide to cloud sessions
Addy Osmani's field guide to running Claude Code on its own machine: what changes, which workflows pay off, and how to connect GitHub on the first try.
Introducing Mistral Large 4: Le chonk
Mistral ships a preview of Mistral Large 4 — a 1 trillion parameter, 49 billion active parameter model trained on their own cluster of 3,800 NVIDIA Grace Blackwell GPUs.
SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles
Co-evolves agent skills and the agents that use them through dynamic skill lifecycles, with memory-augmented RL strengthening LLM agents' abilities.
ASCENT: Online Test-Time Training of Long-Horizon Agents via Self-Distillation of Verified Experience
ASCENT proposes online test-time training for long-horizon agents via self-distillation of verified experience; the page excerpt says it lets an LLM agent keep learning.
SearchJev: A Fast and Calibrated System-1 Model for Search Agents
SearchJev is presented as a fast, calibrated System-1 model for search agents.
Beyond Semantic Similarity: Performance and Costs of Agentic Retrieval for Complex Tasks
Compares the performance and costs of agentic retrieval against semantic similarity for complex tasks.
Advancing computer use with Ironclad
OpenAI post on advancing computer use with Ironclad.
Introducing Mistral Large 4
Mistral announces Mistral Large 4.
AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model
Introduces AdvSim2Real, a training framework for web agents that defends against adaptive prompt injection by simulating attacks in a web world model.
OmniSeek: Native Tool Integration for Multi-turn Audio-Visual Reasoning
Adobe paper on native tool integration for multi-turn audio-visual reasoning; the page notes code, weights, and data are under Adobe's internal review.
socai-io
Socai-Io/Socai 0.6.4
Adds per-platform browser pacing, cloud session workers, and click-first deep reads on X; telemetry errors now redact provider API key values.
the-open-engine
The-Open-Engine/Zeroshot 10.10.1
Preserves the invoking shell's USER in local Claude processes so macOS Keychain login works without a wrapper; hosted processes still ignore native context.