Large language models (LLMs) are widely used in retrieval-augmented generation (RAG) to incorporate external knowledge at inference time. However, when retrieved contexts are noisy, incomplete, or heterogeneous, a single generation process often struggles to reconcile evidence effectively. We propose MASS-RAG, a multi-agent synthesis approach to retrieval-augmented generation that structures evidence processing into multiple role-specialized agents. MASS-RAG applies distinct agents for evidence summarization, evidence extraction, and reasoning over retrieved documents, and combines their outputs through a dedicated synthesis stage to produce the final answer. This design exposes multiple intermediate evidence views, allowing the model to compare and integrate complementary information before answer generation. Experiments on four benchmarks show that MASS-RAG consistently improves performance over strong RAG baselines, particularly in settings where relevant evidence is distributed across retrieved contexts.

KV caching is essential for efficient autoregressive decoding, but its memory footprint grows linearly with context length and quickly becomes a bottleneck for long-context large language models (LLMs). We study whether feature-dimension compression can serve as an orthogonal second stage for KV-cache reduction, and introduce AURA-KV, an adaptive-rank subspace approximation method for KV caches. AURA-KV is training-free: it decomposes post-RoPE key and value caches into compact bases and coefficients, supports incremental decoding, and allocates rank adaptively across layers under a global memory budget. Because it compresses the feature dimension rather than selecting tokens or lowering precision, it can be combined with token eviction and quantization methods. Across LongBench, RULER, and InfiniteBench, AURA-KV preserves long-context performance on Llama-3-8B, Mistral-7B, and LongChat-7B under moderate compression and degrades gracefully under more aggressive budgets. In latency measurements, AURA-KV improves per-layer decoding speed by up to 2.75 ×, and by up to 3.23 × when combined with token-level cache reduction, with a small one-time prefill overhead.

Speculative decoding accelerates generation by verifying multiple drafted tokens in a single target-model forward pass, reducing sequential decoding iterations. Model-free variants avoid auxiliary draft models by reusing text and model states already available during generation, but their speedup depends on the reliability of the constructed drafts. We identify two limitations of existing reuse-based methods: lexically anchored retrieval has limited recall under surface-form variation, and deterministic span copying can be brittle when the retrieved context does not uniquely determine the continuation. We propose AdaPLD, a training-free method that adaptively improves both retrieval and draft construction. AdaPLD preserves high-precision lexical reuse while using semantic similarity to recover additional reuse opportunities when lexical matching fails. It further constructs branched reuse hypotheses to account for continuation uncertainty, rather than relying on a single copied span. Across diverse benchmarks, AdaPLD reduces target-model forward passes and achieves up to 3.10× decoding speedup.