AI and infrastructure news
Filter by type: Post30
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.
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.
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.
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.
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.
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.
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.
AI R&D agents need to revisit training strategy
A study published on August 22, 2026, analyzed 1,338 post-training trajectories. The overall strategy changed in 74 of 3,557 adjacent experiments.
Agents that update their model of the environment during inference
A post published on June 30, 2026, about ARC-AGI-3 says that learning during inference leads agents to build models of rules and mechanics, updating them with new evidence.
Autodata structures agents to create and evaluate datasets
Published on June 25, 2026, the material presents Autodata, a staged method in which AI agents create and analyze training and evaluation data, then apply meta-optimization.
AutoMem explores agent-managed memory
A post published on July 6, 2026 describes a paper on agents that write, search, and organize notes, with reported 2x to 4x gains in long games.
Autoresearch agent beats a manual harness after eight days
A post published on July 14, 2026, reports that an autoresearch agent improved over eight days and outperformed a manually tuned harness on benchmarks excluded from training.
Local hybrid search for agents: what zg offers
On September 2, 2026, Alibaba's Zvec team announced zg, a local search tool combining semantic search, BM25, hybrid search, and rg, with support for popular agents.
Iterative code improves scientific forecasts
A study published in Nature assessed combinations of forecasting methods across six fields: 24 of 55 combinations outperformed both methods from which they originated.
Evaluating rewards for coding agents
A July 4, 2026 post describes four reward signals for coding agents and discusses failures and corrections that can help detect reward hacking.
Validating results generated by research agents
An arXiv paper published on September 1, 2026, reports that checking manuscript claims against execution logs reduced the reported rate of serious errors to 4%.
A shell prompt mismatch increased latency in DSH
A post published on August 17, 2026 reports that different prompts in two DSH shell tools triggered a 3.5-second timeout; a change reduced one command's time from 3,600 ms to 158 ms.
Pandora’s Router balances estimation and routing costs
A paper published on August 22, 2026 proposes using cheap, noisy estimates before paying for better evaluations. On MATH, RAG, and EmbedLLM, it achieved or tied for the lowest average combined inspection cost and routing regret.
Agent serving: measure bottlenecks beyond inference
A paper published on August 21, 2026 presents AgentSysBench, covering 10 agentic applications, and reports that inference is not always the main serving bottleneck.
Survey maps self-improvement in AI agents
Published on July 19, 2026, the survey reviews 239 papers on improving agents through model updates or changes to components such as prompts, memory, and tools.
ThetaEvolve: test-time learning
Published on July 11, 2026, the open-source ThetaEvolve framework combines in-context learning and test-time reinforcement learning to explore open-ended optimization problems.
Let's assess your project
I reply with scope and a proposal.