paper-with-me

Papers

How to Speculate about Uncertainty in Agentic Coding? A Draft-Model Gate Method

2026-09-04 · Konstantin Grotov, Valentin Malykh arxiv

LLM agents deployed for software engineering fail expensively: they act confidently wrong, and bad actions are recognized only after costly execution and retry. We present Speculative Uncertainty (SU), a method that recovers a predictive failure signal for a black-box agent from its output tokens alone, with no access to logits, weights, activations, or repeated sampling. Inverting speculative decoding, a small open-weight draft model scores the agent's already-generated trajectory in a single forward pass. From these speculative cross-likelihoods we extract phase-aware features by separating the reasoning and action spans, and calibrate them against a verifiable objective. SU produces a failure-likelihood score that any downstream policy, such as routing, human intervention, or extra test-time compute, can consume directly. To show the signal is actionable, we instantiate one such policy, a pre-execution veto gate, on software engineering agents Qwen3-Coder-480B and closed-source Claude 3.5 Sonnet, cutting execution error rate by 6-8 percentage points and token cost by 14-19% in deployment, transferring to out-of-distribution benchmarks without retraining, and generalizing across agent models.

📄 PDF Abstract BibTeX arXiv:2609.05274

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Mirror Speculative Decoding: Breaking the Serial Barrier in LLM Inference

2025-10-15 · Nikhil Bhendawade, Kumari Nishu, Arnav Kundu, Chris Bartels 외 arxiv

Speculative decoding accelerates LLM inference by using a draft model to look ahead, but gains are capped by the cost of autoregressive draft generation: increasing draft size elevates acceptance rates but introduces add…

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation

2025-07-02 · Tianyu Liu, Qitan Lv, Hao Li, Xing Gao 외 arxiv

Speculative decoding (SD), where a small draft model is employed to propose draft tokens in advance and then the target model validates them in parallel, has emerged as a promising technique for LLM inference acceleratio…

Text Generation

DEER: Draft with Diffusion, Verify with Autoregressive Models

2025-12-17 · Zicong Cheng, Guo-Wei Yang, Jia Li, Zhijie Deng 외 arxiv

Efficiency, as a critical practical challenge for LLM-driven agentic and reasoning systems, is increasingly constrained by the inherent latency of autoregressive (AR) decoding. Speculative decoding mitigates this cost th…

Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

2024-02-07 · Zachary Ankner, Rishab Parthasarathy, Aniruddha Nrusimha, Christopher Rinard 외

To combat the memory bandwidth-bound nature of autoregressive LLM inference, previous research has proposed the speculative decoding frame-work. To perform speculative decoding, a small draft model proposes candidate con…

HiSpec: Hierarchical Speculative Decoding for LLMs

2025-10-01 · Avinash Kumar, Sujay Sanghavi, Poulami Das arxiv

Speculative decoding accelerates LLM inference by using a smaller draft model to speculate tokens that a larger target model verifies. Verification is often the bottleneck (e.g. verification is $4\times$ slower than toke…