Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
The work demonstrates that code-specific uncertainty estimation — rather than methods borrowed from natural language — meaningfully improves the ability to detect silently wrong programs, which is directly relevant to safe deployment of LLMs in agentic coding pipelines.
FrontierCode directly addresses a documented flaw in existing coding benchmarks — that passing tests does not equal mergeable code — by introducing maintainability-focused evaluation criteria that reveal current frontier models are far from solving real-world code quality.
Watch for the open-source release of SearchSwarm's harness, model weights, and training data, which could provide a practical foundation for building multi-agent deep research systems that scale beyond single-context-window limits.
Audit and security tooling for multi-agent systems needs to move beyond standard trace correlation — this substrate approach offers a concrete architectural pattern for binding delegation context at execution time rather than reconstructing it after the fact.
Benchmark results showing even GPT-5 topping out at 17.4% TSR highlight how far current MLLMs are from reliable spatial reasoning, giving practitioners a rigorous testbed to measure progress on active exploration and long-horizon planning.
Teams deploying agents in high-stakes domains (claims, code, contracts, clinical decisions) gain a concrete protocol for capturing human oversight as structured, auditable, and legally replayable records rather than ephemeral chat messages.
Benchmark scores for coding agents are increasingly untrustworthy — CapCode and CapReward offer a concrete methodology for building evaluations and training regimes that resist shortcut exploitation and produce more honest capability measurements.
Benchmark your agentic tooling against these metrics — 87% time reduction and 55% lower dissatisfaction — as the paper establishes a concrete empirical baseline for what autonomous end-to-end execution delivers over conversational search in real production settings.
Audit every step of a complex AI research pipeline — the explicit traceability and rubric-grounded synthesis in DuMate-DeepResearch offer a concrete blueprint for reducing hallucination and improving accountability in agentic coding and research systems.
Fine-tuning on DragOn's 3.5M drag-grounding tasks offers a concrete path to improving GUI agent accuracy on complex interactions — like resizing, highlighting, and slider control — that current models handle poorly.