Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
MDForge demonstrates that an LLM agent can autonomously design MD pipelines competitive with human experts and discover a wet-lab-validated picomolar binder, showing that agentic code generation with sparse feedback can replace expert-driven pipeline design in a domain where trial-and-error is computationally prohibitive.
The pluggable memory and RAG backends, native Snowflake Cortex support, and the split of `flow.py` into discrete DSL/definition/runtime layers give developers more control over CrewAI's internals and extend its LLM provider ecosystem.
GitHub Agentic Workflows moves from limited access to public preview, opening coding-agent-powered automation of tasks like issue triage and CI failure analysis to a broader set of users.
InterleaveThinker removes the architectural barrier that has prevented existing image generators from producing interleaved text-image sequences, extending a capability previously limited to frontier models like GPT-5 to any image generator via a plug-in multi-agent pipeline.
The experiment demonstrates that Haiku 4.5's tendency to honestly acknowledge logical inconsistencies — while a virtue in cooperative contexts — made its negotiating position progressively indefensible against an adversarial attacker, in contrast to Opus 4.8's strategy of holding a single, unreinterpreted constraint throughout.
The tool packages multi-model deliberation, MCP server access, and web-grounded search into a single Docker container, giving MCP-compatible agents a drop-in way to replace single-model responses with structured multi-LLM reasoning across both local and cloud providers.
AgentHarness introduces a concrete open-source pattern for separating verification from the main reasoning model in long-horizon agent loops, with purpose-built small weights that reportedly outperform much larger open-source models on BrowseComp benchmarks.
The research reframes where agent cost optimization efforts should focus — not on code generation, but on the iterative code review loop, where a structural "communication tax" drives the majority of token spend.
The paper fills a documented gap by writing down, for the first time in a consolidated form, the end-to-end practice for building production custom AI agents — knowledge the authors note has previously existed only in informal sources like podcasts, blogs, and leaked system prompts.
The paper demonstrates that replacing linear repository traversal with domain-scoped parallel agent spawning improves multi-file change localization for a small model, while also identifying that naive filesystem access and forced multi-agent consultation can actively harm performance or inflate costs.