Attention analysis shows that LLM tool selection failures occur at the readout/decision stage, not because the model fails to attend to the correct tool definition.
International Conference on Learning Representations (ICLR) , year =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
By sorting KV-caches via mean K-norm ordering, cache merging becomes a commutative, associative, idempotent CvRDT that delivers identical results under any permutation and absorbs duplicates.
GSRQ applies a gain-shape variant of K-means inside residual quantization to improve directional fidelity, raising LongBench accuracy from 11.34 to 33.54 at 1-bit on LLaMA-3-8B.
citing papers explorer
-
Looking Is Not Picking: An Attention-Segment Account of Tool-Selection Failures in LLM Agents
Attention analysis shows that LLM tool selection failures occur at the readout/decision stage, not because the model fails to attend to the correct tool definition.
-
Cache Merging as a Convergent Replicated State for Multi-Agent Latent Reasoning
By sorting KV-caches via mean K-norm ordering, cache merging becomes a commutative, associative, idempotent CvRDT that delivers identical results under any permutation and absorbs duplicates.
-
GSRQ: Gain-Shape Residual Quantization for Sub-1-bit KV Cache
GSRQ applies a gain-shape variant of K-means inside residual quantization to improve directional fidelity, raising LongBench accuracy from 11.34 to 33.54 at 1-bit on LLaMA-3-8B.