Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
The work addresses the practical economic and computational constraint of LLM-call costs in counterfactual recourse, showing that a structured agentic search strategy can produce more diverse, validated alternatives without increasing budget expenditure.
The study reveals that the gap between stage-level and end-to-end pipeline automation in real scientific workflows is a distinct, underexplored challenge not captured by existing coding agent benchmarks.
Devin Desktop consolidates local and cloud agent fleet management into a single editor interface, as described by Cognition.
The talk illustrates why standard code-level debugging is insufficient for agentic systems and presents a concrete framework — spanning telemetry, multi-scope evals, and automated analysis — for making nondeterministic AI agents production-ready.
OLW targets a gap that the A2A spec itself acknowledges — standardized discovery registries — offering a queryable, structured alternative to the hardcoded agent relationships that currently characterize multi-agent systems.
The paper formalizes a conceptual framework — including the new discipline of "Agentic Engineering" and the AaaS category — that attempts to give researchers and practitioners a structured vocabulary for understanding how LLM-driven agents differ fundamentally from traditional software systems.
The work demonstrates that an autonomous LLM-driven agent can produce physically interpretable, generalizable control policies through a fully auditable discovery process — without the black-box weight optimization that typically makes deep reinforcement learning opaque in scientific contexts.
SWE-Explore provides a fine-grained diagnostic lens on coding agent capabilities that binary benchmarks like SWE-bench cannot offer, enabling targeted measurement of where exploration quality breaks down before the repair stage.
The release allows a single `gemini-faf-mcp` binary to serve both local MCP clients and cloud-hosted deployments without any configuration changes, while also resolving a handshake compatibility issue with strict MCP clients.
The switch to SearXNG removes TinySearch's dependency on a single third-party search provider, addressing the fragility that made DuckDuckGo rate-limiting a blocking issue for agent workflows that rely on consistent web-search access.