arXiv:2607. 09791v1 Announce Type: new Abstract: The multiplicative repetition penalty shipped across the LLM inference ecosystem (HuggingFace, vLLM, llama.
arXiv:2607.27836v2 Announce Type: replace Abstract: Large language model unlearning is consistently fragile under relearn attacks. On TOFU, fine-tuning on twenty forget examples substantially recover...
The study investigates why small language model agents tend to repeat a tool call that just failed. By recording the failed call and its error message in the transcript, the authors measure a negative corrective gain—agents are more likely to repeat the failed action, with a drop of about 1.03 nats per token. The problem is traced to the harness design rather than the model’s understanding of errors, and the authors show that replacing the verbatim call with a runtime-generated description of the failure can reduce this backfiring effect by 76%.
SiLR introduces a structure‑preserving admission and process reward mechanism for large language model (LLM) tool agents. Unlike traditional scalar‑score gates that can trap agents in plateau trajectories, SiLR shadow‑executes each proposal and admits it based on a product order over branch‑level violation states, ensuring safe and recoverable actions. Experiments on Gym‑ANM and CityLearn benchmarks show SiLR consistently recovers all multi‑action episodes and outperforms scalar gates, while also providing a robust reward signal for policy learning.
arXiv:2608. 10986v1 Announce Type: cross Abstract: A growing class of methods probes a language model by feeding it its own output: self-consistency, iterated refinement, agentic loops.
The paper evaluates the effectiveness of tolerance‑based conformance tests for INT8 quantized GEMM kernels used in large language models. By injecting nine faults into a Qwen3‑1.7B reference pipeline, the authors show that most faults shift outputs by at most one bfloat16 spacing, rendering a tolerance of one spacing blind to these errors. They further demonstrate that requantizing weight scales to the nearest power of two aligns CUTLASS and Triton implementations bit‑for‑bit and produces identical token sequences, with only minor perplexity changes.
The paper proposes invalidation contracts to manage cached recovery suggestions in LLM agents, attaching version stamps and cacheability hints to each suggestion so stale entries can be evicted without trial and error. The protocol separates realized savings into validity (protocol‑dependent) and compliance (planner‑dependent), showing that row‑level invalidation can significantly improve first‑try compliance and recover a substantial portion of token costs across multiple models, while table‑level invalidation can be detrimental. The study evaluates the approach across seven models, three serving paths, two domains, and about 9,400 episodes, demonstrating deterministic validity and high eviction precision.
arXiv:2604. 11943v3 Announce Type: replace-cross Abstract: An OS kernel that runs LLM inference internally can read the model's own next-token logit distribution before any text is generated, and act on it as a governance primitive.
arXiv:2607. 27539v1 Announce Type: new Abstract: Exact deletion from persistent language-model memory depends on how that memory represents a record.
TwinKV is a training‑free, attention‑free repair pass that identifies and swaps orphaned and redundant tokens in a KV cache, improving long‑context inference for small models. It works by detecting near‑duplicate keys and can be composed with existing eviction policies without altering their scoring rules. Experiments on Qwen3‑4B and Llama‑3.2‑1B across LongBench, LooGLE, RULER, and MMLU‑Pro show that TwinKV consistently improves performance for most configurations, especially at tighter compression ratios.
arXiv:2608. 08029v1 Announce Type: cross Abstract: Khatri et al.
arXiv:2607. 27275v1 Announce Type: new Abstract: Post-training quantization to 4-bit weights is widely reported to be nearly lossless.
arXiv:2609. 31181v1 Announce Type: new Abstract: Black-box model identification works by scoring a model's response to natural-language prompts.