Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
ProfiLLM demonstrates that an agentic LLM pipeline can move beyond structured numerical features in a live, millisecond-latency industrial dispatcher and produce measurable improvements in real-world GMV and completion rates — validated by a 14-day online A/B test on DiDi's production system.
The work demonstrates that agentic, multi-agent prompt optimization can compound noisy real-world A/B test cycles into statistically robust improvements, offering a practical alternative to gradient-based prompt tuning for open-ended task-oriented dialogue systems.
MiniPIC removes the requirement for identical prefixes to reuse KV cache entries, enabling efficient caching of recurring structured inputs in retrieval-augmented and agentic workloads without the large server-side code changes or host-to-device transfer overhead of prior PIC approaches.
The framework and dataset directly extend multimodal medical AI to seven major Indian languages, addressing the lack of equitable AI-driven healthcare assistance in multilingual, low-resource settings like rural India that English-centric MLLMs cannot serve.
The evidence-first protocol directly reduces the conversational bias that causes standard LLM assistants to follow misleading user hypotheses, improving diagnostic accuracy over both direct prompting and reasoning-only baselines across multiple LLM backbones.
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.
PhysTool-Bench quantifies a critical and previously underexplored gap between MLLMs' strong digital API performance and their weak physical tool comprehension, pinpointing specific bottlenecks — perception and functional commonsense — that limit the development of practical embodied AI.
TabClaw's combination of transparent, editable execution plans with a self-evolving skill and memory system directly addresses the transparency and adaptability gaps the paper identifies in current LLM-based data-analysis agents.
Teams building agentic coding pipelines for real-world software engineering — where public test cases don't exist before implementation — can use DryRUN's approach to achieve competitive code generation quality without the manual overhead of authoring input-output examples.
Teams building multi-agent LLM pipelines can use behavioral economics game benchmarks as a cheap pre-screening tool to identify which open-weight models will cooperate effectively before investing in full-scale deployments.