跳到正文
Jones Ray

ScholarPulse 日报 2026-09-08

2026-09-08 学术简报:2 篇。该研究提出Speculative Uncertainty (SU)方法,通过小开放权重草稿模型从代理输出token中预测失败信号,显著降低软件工程代理在部署中的执行错误率和token成本。

今日速览

序号标题来源日期主题推荐等级
1How to Speculate about Uncertainty in Agentic Coding? A Draft-Model Gate MethodarXiv2026-09-04AI-Agent高
2CONTINUITY: Security-Context Contracts for Composable LLM Agent ControlsarXiv2026-09-04AI-Agent高

重点论文与技术动态

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

一句话结论

该研究提出Speculative Uncertainty (SU)方法,通过小开放权重草稿模型从代理输出token中预测失败信号,显著降低软件工程代理在部署中的执行错误率和token成本。

核心内容

方法与数据

价值判断

摘要 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.

2. CONTINUITY: Security-Context Contracts for Composable LLM Agent Controls

一句话结论

CONTINUITY框架通过显式安全上下文契约确保LLM代理执行的安全性,防止组件边界处的安全上下文不连续问题。

核心内容

方法与数据

价值判断

摘要 LLM agent systems increasingly combine provenance tracking, authorization, policy enforcement, protocol adapters, and execution controls. However, individually correct security mechanisms do not necessarily compose into an end-to-end secure system: security-critical context may be dropped, widened, rebound, or reinterpreted as actions cross component boundaries. We identify this failure mode as security-context discontinuity and introduce CONTINUITY, a framework for verifiable composition of agent security controls. CONTINUITY models each component with an assume-guarantee contract and carries authenticated security context across transitions using signed root grants, provenance commitments, role-bound transition receipts, bounded typed releases, transformation witnesses, and effect-bound execution permits. We formalize end-to-end consequence integrity, requiring every realized external effect to be backed by a valid and current authorization witness linking the principal, task, provenance, delegation, policy state, canonical action, and finality boundary. We implement a reference verifier and deterministic cross-layer fault-injection suite covering 32 fault classes across four application domains. In 2,560 parameterized attack instances spanning 128 fault-domain classes, the full CONTINUITY configuration commits no harmful external effect, while completing all 700 benign tasks and escalating all 200 ambiguous cases. These results show that secure agent execution requires not only sound individual controls, but explicit contracts that preserve their guarantees across the complete instruction-to-effect path.