Translate
Live intelligence

Latest AI updates

10 updates
AllModelsProductsIndustryResearchTutorialOpinion
Research

Terminal-Bench 2.1: Continuous Benchmark Maintenance Reveals Stale Evaluations

The paper introduces the concept of benchmark maintenance debt, where benchmarks become stale as models improve and infrastructure changes. The authors propose a continuous-validation workflow and apply it to Terminal-Bench 2.0, finding issues in roughly 30% of the benchmark and releasing repairs as Terminal-Bench 2.1. These repairs change evaluation results, with accuracy increasing by over 10 percentage points and leaderboard positions shifting by up to three ranks, while overall ranking remains highly correlated.

arxiv13h agoScore 79
benchmark maintenanceLLM evaluationcoding agents
Research

Study Finds Coding Agents Forget Previous Tasks During Continual Harness Evolution

A new empirical study investigates whether coding agent harnesses can evolve continuously across multiple tasks without catastrophic forgetting. Using six evolution directions across three software engineering datasetshare, the authors show that evolving on a new dataset can severely degrade performance on previously learned tasks—e.g., Meta-Harness drops from 94.0% to 32.0% on SWE-Bench after five rounds of further evolution. The paper provides insights for designing continual self-evolution methods for agent harnesses.

arxiv3d agoScore 78
agent self-evolutioncontinual learningcoding agents
Products Editor selected

Factory Releases Droid 1.0 With Programmatic Tool Calling Enabled by Default

Factory has released Droid 1.0, a model-independent coding agent harness that enables programmatic tool calling by default. Its Script tool runs JavaScript in a sandbox, coordinating multiple tool calls while returning only printed output to the model to limit context usage. The update also reduces the base prompt and loads tools on demand; Factory reports performance and cost improvements, but the cited benchmark results are self-reported.

Why it matters: The release offers developers a concrete approach to reducing coding-agent context overhead and coordinating tools across supported models.

MarkTechPost6d agoScore 86
FactoryDroidCoding agents
Tutorial

Amazon Bedrock AgentCore runtime adds session endpoints for live web app previews

AWS introduced session endpoints for Amazon Bedrock AgentCore runtime, giving each agent session an authenticated URL that forwards HTTP/1.1, HTTP/2 and WebSocket traffic to ports the developer explicitly allows. The post walks through a sample coding agent that keeps a Vite dev server running inside its microVM session, so developers can watch a site update in the browser as the agent saves files. It covers port configuration, SigV4 or JWT authentication, a local-endpoint proxy for browser clients, and the specific 403, 404 and 502 refusal codes the runtime returns.

AWS Machine Learning Blog6d agoScore 78
Amazon Bedrock AgentCorecoding agentsAWS
Products Editor selected

Microsoft and UC Berkeley Release TokenEconomizer to Cut Coding Agent Costs by Up to 30.9%

Microsoft Research and UC Berkeley researchers released TokenEconomizer, an Apache 2.0 open-source cost controller that plugs into Claude Code, Codex, GitHub Copilot CLI and Pi without modifying model weights or agent code. It learns per-repository policies from past traces through three mechanisms: micro-skills, tool pruning and failure-loop intervention. Across 277 SWE-Bench tasks and five agent-model settings, it reduced mean cost by 18.4% to 30.9%, and it was cheaper in all 30 repository-setting cells. Pass@1 improved in four of five settings and fell 1.0 point on Claude Code with Opus 4.8.

Why it matters: It gives teams a concrete, installable way to lower coding-agent token spend, backed by per-setting SWE-Bench numbers and an honest account of where savings are smaller.

MarkTechPostOct 31, 2026Score 87
Microsoft Researchcoding agentstoken efficiency
Research

Gym-Anything for Robotics uses coding agents to scale robotics simulation creation

The paper proposes Gym-Anything for Robotics, a framework in which coding agents build realistic robotics simulations, on the premise that simulation creation is itself a coding task that improves as coding agents improve. The authors select simulation domains based on U.S. GDP data and define criteria for good simulations and tasks, then apply an adversarial creation-audit loop. The resulting RoboWorld suite contains 25 simulations spanning 25 test and 175 training RL environments of varying difficulty. Frontier models reportedly average only 0.06 reward on RoboWorld test tasks, and the paper introduces in-context learning over repeated attempts, a privileged teacher-student setup, self-assisted learning, and code policies that generate demonstrations for training VLAs such as pi_0.5.

arxivOct 30, 2026Score 78
robotics simulationcoding agentsembodied AI
Products

MiniMax Open-Sources MCode Stack: 15 Agent Skills Its Coding Team Uses Daily

MiniMax has open-sourced MCode Stack, a collection of 17 SKILL.md agent skills and 5 checklists used by its MiniMax Code team, released under the MIT license on October 28, 2026. The stack focuses on harness engineering, including planning, context management, code review, and long-session handling, and installs into MiniMax Code or Claude Code. No benchmarks or eval results are published, so it serves as a practical playbook rather than proven performance. The skills are plain Markdown and compatible with agents supporting the SKILL.md format.

MarkTechPostOct 29, 2026Score 78
MiniMax Codeagent workflowsopen-source AI tools
Research Editor selected

Microsoft Research Open-Sources Agensh, an Orchestrator-Free Multi-Agent Harness Tested at 1,024 Agents

Microsoft Research has open-sourced Agensh (MIT), a decentralized harness for large teams of coding agents that removes the central orchestrator. Each worker runs the same five-step prompt-based loop, claims sub-tasks, and shares state through a Gitea repo, a Mattermost channel and a typed context board. On the five hardest ProgramBench tasks, more agents improved scores: with GPT-5.6-sol the mean rose from 19.31% with 1 agent to 28.78% with 128. The README reports GPT-6.1-sol reaching a 79.59%

Why it matters: It documents a concrete open-source multi-agent architecture with published scaling behavior and benchmarks, giving agent builders a reproducible alternative to orchestrator-worker designs.

MarkTechPostOct 25, 2026Score 85
Microsoft Researchmulti-agent systemscoding agents
Research

Study: Coding-Agent Harness Choice Barely Affects Pass Rates, but Can Triple Cost

A controlled study compared coding-agent harnesses such as Claude Code, OpenCode and mini-SWE-agent and found that switching between them changes pass rates little more than simply rerunning the same setup. Cost per task, however, can triple, with the system prompt resent at every step cited as the main driver.

The DecoderOct 24, 2026Score 68
coding agentsagent evaluationLLM inference cost
Products

Vercel Open-Sources durable-harness for Crash-Proof Coding Agents

Vercel released durable-harness, an Apache-2.0 TypeScript package that wraps existing coding agent harnesses (Pi, OpenCode, fx, Claude Code, Codex) and stores each session in a durable log via its Workflow SDK World. It records intent before model and tool calls and outcomes after, so a crashed function's turn can resume on a new function without re-running finished calls or double-billing tokens. It runs on Vercel Functions and Queues, locally, or self-hosted on Node.js 22+ with Postgres. The p

MarkTechPostOct 22, 2026Score 76
Vercelcoding agentsdurable execution