arXiv subjects

Haoyu Zheng

Publications and source records attributed to Haoyu Zheng.

2 recordsLinked to original sources

arXiv2026

MAIGO: Mitigating Lost-in-Conversation with History-Cleaned On-Policy Self-Distillation

Large language models often solve tasks from a fully specified prompt but degrade when the same requirements unfold over multiple turns, known as the lost-in-conversation (LiC) gap. We trace part of this degradation to self-contamination: intermediate assistant replies enter later context and carry early deviations forward. Motivated by this mechanism, we propose MAIGO, an on-policy self-distillation method that reduces this contamination using history-cleaned references from the model's own policy. For middle turns, MAIGO removes prior assistant replies while preserving the user-visible sharded prefix; for answer turns, it distills from paired full-view references conditioned on the completed user-side dialogue. A reliability weight downweights middle-turn samples that disagree with the clean reference. MAIGO requires no verifier rewards, state labels, or inference-time scaffolding. Under the LiC paired-view protocol with deterministic verifiers, MAIGO improves Qwen2.5-7B-Instruct SHARDED accuracy from 52.8 to 66.1 and the SHARDED/FULL ratio from 66.5% to 84.1%, while keeping FULL accuracy within 2.3 points. These results show that self-contamination is a trainable component of the LiC gap.

cs.CL↗

arXiv2026

Scheduling LLM Inference with Uncertainty-Aware Output Length Predictions

To schedule LLM inference, the \textit{shortest job first} (SJF) principle is favorable by prioritizing requests with short output lengths to avoid head-of-line (HOL) blocking. Existing methods usually predict a single output length for each request to facilitate scheduling. We argue that such a \textit{point estimate} does not match the \textit{stochastic} decoding process of LLM inference, where output length is \textit{uncertain} by nature and determined by when the end-of-sequence (EOS) token is sampled. Hence, the output length of each request should be fitted with a distribution rather than a single value. With an in-depth analysis of empirical data and the stochastic decoding process, we observe that output length follows a heavy-tailed distribution and can be fitted with the log-t distribution. On this basis, we propose a simple metric called Tail Inflated Expectation (TIE) to replace the output length in SJF scheduling, which adjusts the expectation of a log-t distribution with its tail probabilities to account for the risk that a request generates long outputs. To evaluate our TIE scheduler, we compare it with three strong baselines, and the results show that TIE reduces the per-token latency by $2.31\times$ for online inference and improves throughput by $1.42\times$ for offline data generation.

cs.LG↗