Daily papers

AI engineering 4

  1. 1 ▲ 19 Zedong Liu et al.

    Read Less, Solve More: Token-Efficient Sparse Reading of External Content for AI Agents

    SparseRead cuts agent token use by up to 92.9% while preserving or improving quality in 97% of settings.

  2. 2 ▲ 12 Hao Kang et al.

    Evolving Infra: Agent-Adaptive LLM Serving at Scale

    Evolving Infra cuts P95 TTFT up to 14× by adapting compute splits and KV eviction to agent workloads.

  3. 3 ▲ 14 Saul Urso et al.

    Ensemble Routing for Prompt-Adaptive Cost-Aware LLM Inference

    PISA-E lowers inference cost by approximately 36% at selected operating points while preserving higher task performance.

  4. 4 ▲ 33 Genming Cui et al.

    SteerDistill: Quantizing LLM Agents via Closed-Loop Teacher Steering

    SteerDistill beats quantized agent baselines and uses 67% fewer training GPU hours on τ^2-Bench.