AI and infrastructure news
Filter by type: All103
- 8 days ago github.com
Open-source project generates interactive UI for chatbot responses with OpenUI
Open-source repository on GitHub streams chatbot responses as interactive interface, with maps, charts, tables and functional tools, built with OpenUI and compatible with OpenRouter and Ollama.
- 9 days ago github.com
Stealth browser automation via MCP repository: what changes for bot detection
An open source repository shows how AI agents can control real Chrome sessions via MCP and the Chrome DevTools Protocol, with navigation, network hooks and DOM extraction. The author claims it bypasses Cloudflare challenges.
Autonomous science limited by physical validation: allocating agents and validation bottlenecks
An arXiv paper argues that autonomous science is limited by physical validation capacity and proposes markets and institutions to allocate that scarce work.
HERMES: component-level harness with a resident LLM per code module
An arXiv paper proposes HERMES, where each repository component has a resident LLM that knows its code, with reported gains in migration and on four software engineering benchmarks.
DeLM: decentralized code agents with shared context, without a central coordinator
Stanford's article presents DeLM, which replaces a central coordinator with shared context and a task queue. According to the author, it is up to 2.49× faster and more accurate than the Claude Code and Codex baselines.
Agent-R1: modular training for multi-turn LLM agents
The paper presents a reinforcement-learning framework for training LLM agents in multi-turn interactions with tools and sequential environments.
Auditable self-improving agents
An article published on April 19, 2026 proposes a protocol for agents to suggest, evaluate, and implement improvements with auditable traceability and rollback.
Code agents: evaluating safety and performance
Microsoft reports a 14-billion-parameter coding agent scoring 45.3% on SWE-Bench Verified, and a training method that accounts for tests unintentionally broken while adding features.
Recursive agents exchange latent states to collaborate
A May 1, 2026 publication describes a paper on agents refining shared latent states and reports more precise collaboration, faster execution, and lower token use in experiments.
AutoSOTA automates iterative AI model improvement
Published on April 19, 2026, the post describes a system with eight specialized agents that reproduced and improved models, reporting 105 new state-of-the-art models across LLMs, computer vision, and time series.
- 18 days ago github.com
How to track research on agentic reasoning
A GitHub list collects articles and resources on agentic reasoning based on a survey about the topic. Learn how to turn this research tracking into a useful process for your team.
Evolving coding-agent harnesses with evidence
A paper published on April 29, 2026 presents a framework for improving coding-agent harnesses. On Terminal-Bench 2, pass@1 rose from 69.7% to 77.0% over ten iterations.
Measuring performance when scaling agent systems
A December 11, 2025 article examines how coordination, model capability, and system and task factors influence agent performance.
Dual-play proposes training LLM reasoning with less supervision
Published on December 15, 2025, the paper presents dual-play: two models take specialized roles, one creating questions and the other solving them, to reduce reliance on external supervision.
Controlled evolution for algorithmic code optimization
A January 14, 2026 article presents an iterative code evolution method evaluated on EffiBench-X, using diverse strategies, feedback-guided mutations, and experience across tasks.
Layered memory for long-horizon research agents
A post dated April 19, 2026 describes ML-Master 2.0’s Hierarchical Cognitive Caching, with short-, medium-, and long-term memory, and reports a 56.44% medal rate on MLE-Bench after a 24-hour run.
MemRL learns to prioritize agent memories at runtime
Published on January 13, 2026, the description presents MemRL, an approach that learns the utility of episodic memories without changing language-model weights.
PARE-Bench tests proactive agents in stateful apps
Published on April 25, 2026, the paper presents 143 tasks for evaluating agents that infer goals, choose when to intervene, and coordinate actions across apps.
- 18 days ago turingpost.com
AI research highlights agent memory and long-running tasks
A weekly roundup published on April 21, 2026, covers research on agent design, long-running task execution, memory transfer in coding agents, and distillation.
ReCode combines planning and action in LLM agents
Published on December 13, 2025, the article presents ReCode, a recursive code-generation approach that lets LLM agents switch between strategic planning and detailed actions.
Self-Harness: agents improve their own harnesses
Published on June 10, 2026, the paper explores agents that analyze failures and propose small harness changes, retaining those that pass regression tests.
Self-play for training software engineering agents
In a post published on December 23, 2025, Self-play SWE-RL alternates one agent between injecting and fixing bugs in real repositories, without human-labeled issues or tests.
- 18 days ago github.com
Stop hooks can keep agents on longer tasks
An Anthropic post dated December 27, 2025 describes using a stop hook to ask an agent to continue after it stops, presenting the technique as support for orchestrating longer tasks.
StructMem proposes temporal hierarchical memory for agents
Published on April 24, 2026, the StructMem paper proposes hierarchical memory for long-term conversational agents, with event relationships intended to support temporal reasoning and multi-hop questions.
TACO proposes context compression for terminal agents
The paper describes a framework that learns context-compression rules from terminal-agent interactions and reports tests on three benchmarks.
RoPoLL proposes geometric median for LLM judge panels
Published on July 2, 2026, the paper formalizes LLM judge panels under a contamination model and introduces RoPoLL, tested with 13 judges and corruption rates up to 50%.
AGI: definitions and benchmarks merit critical analysis
A publication dated October 16, 2025, discusses a paper defining AGI as the replication of human cognition. Its author welcomes discussion of varying capabilities but questions the benchmarks and the narrow view of AI.
- 18 days ago github.com
Agentic components for APIs: what the repository demonstrates
Published on GitHub on July 24, 2024, the repository gathers agentic components for Llama Stack APIs and highlights the use of tools and functions with Llama 3.1 models.
ADAS: search and evaluation for agent design
Published on August 26, 2024, the paper describes an iterative method for proposing agents from domain information and evaluating the proposals.
Autonomous research agents: applying the approach
Published on September 9, 2025, the paper describes reinforcement-learning-trained agents that search the web, navigate, use Python, and summarize prior results when context is limited.
Social agents: test generalization across scenarios
A post dated September 22, 2025 describes an MIT study that tunes prompts with small human-data sets and reports lower prediction error on new game variants.
Agent learning from its own interactions
A post published on October 10, 2025 examines using future states from an agent’s own interactions as supervision, without reward signals, to address long rollouts and rewards that are difficult to verify.
AutoToS uses tests and breadth-first search to refine functions
On August 23, 2024, an article described how AutoToS refines successor and goal-test functions using unit-test feedback and breadth-first search.
How to evaluate AI agents on workplace tasks
TheAgentCompany covers software development, project management, administration, and data science tasks to evaluate AI agents.
Data curation and agent autonomy: what to test
A post published on September 23, 2025 describes LIMI: 78 selected demonstrations scored 73.5% on AgencyBench, outperforming models trained on 10,000 samples.
- 18 days ago ai.meta.com
Meta presents open-weight 32-billion-parameter model for code research
On September 24, 2025, Meta presented Code World Model, a 32-billion-parameter model with open weights for research into code generation with world models.
Research as configurable code: NVIDIA’s approach
On September 7, 2025, a NVIDIA post described a system that turns natural-language research strategies into executable functions, using search, interchangeable language models, and sandboxed execution.
ToolUniverse and research-tool integration
A post published on September 30, 2025 describes a shared interface for discovering and running more than 600 local and remote research tools that use MCP.
TUMIX refines answers with diverse agents at inference time
A post published on October 11, 2025 describes agents with different tools solving problems independently and refining answers over multiple rounds, without retraining the base model.
163 procedures for scientific research agents
The article presents an open library of 163 procedures for research agents across 16 fields, including genomics, cheminformatics, medical imaging and study design.
arxiv.org
Let's assess your project
I reply with scope and a proposal.