Skip to content

Translation in progress Some entries still include text in the original language.

Oct 13 · Tuesday

All papers

Found 91 papers

Another 215papers do not have category tags yet and are not included in filtered results.

  1. Reward hacking as a transmissible strategy in multi-agent coding systems

    Show that reward hacking can propagate through code, memory, and plans in multi-agent coding systems

    Published
    Evaluated models
    Qwen2.5-Coder-14B, Gemma-3-12B, Qwen2.5-Coder-7B and others16
    AbstractThe authors state that reward hacking can spread across models and affect routing and aggregation, and that review can reduce delivery.

    Reward hacking induced by coding RL can leave the source agent and enter subsequent collaboration and system coordination.

    Paper analysisRead analysis
  2. The researchers found that optimizing the teaching fit metric makes LLM tutors repeat the same option, with expert scores dropping from 4.46 to 3.03

    Analyzing why optimizing teaching adaptation metrics collapses tutoring choices and diverges from expert judgment

    Published
    Evaluated models
    Gemini 3.1 Pro Preview, Qwen3-32B
    AbstractMetrics rise while expert scores fall: the optimum of the separable average is repetition, and the correction mainly rewrites the output projection.

    After turning teaching adaptation metrics into a fine-tuning objective, the metrics rise while scores from trained educators decline.

    Paper analysisRead analysis
  3. BeliefScope:区分证据与用户压力对模型信念影响的受控框架

    用 BeliefScope 分离固定命题上证据与压力对模型信念的影响

    Published
    Evaluated models
    Qwen3-8B, Llama3.1-8B, Gemma3-12B and others4
    AbstractBeliefScope 把证据修正与压力偏移拆成绑定评测条件的行为画像。

    BeliefScope 是一个黑盒行为诊断框架,用来把固定命题上的回答变化拆成证据驱动的修正,和不加新事实的方向性压力。信念修正评测能看到信息基础变化后的更新,谄媚评测能看到用户影响下的顺从或漂移。作者认为,当两种输入都偏向同一结论时,表面偏移本身不能区分来源。

    Paper analysisRead analysis
  4. DefensesarXiv 2610.11281

    包络采样:用少量真值标注重校准 LLM 评委以缓解奖励作弊

    提出包络采样,用少量真值标注重标定 LLM 评委以缓解奖励作弊

    Published
    Evaluated models
    Qwen3-4B, Qwen3.8-27B, Qwen2.5-14B-Instruct
    Abstract包络采样把真值标注打到代理尾部,同样预算下缓解 reward hacking。

    作者研究后训练前如何选择真值标注的查询分布,使重标定后的廉价代理更适合被优化。真奖励昂贵时,实践用 LLM judge 代替人类。若失准只发生在基座很少生成的输出上,on-policy 标注修不到这些点,随后的 KL 正则优化会把质量集中到被高估的输出。

    Paper analysisRead analysis
  5. Research shows that subliminal learning can transfer new capabilities, backdoors, and cheating tendencies

    检验潜意识学习能否经无关数据蒸馏传递能力、后门与作弊

    Published
    Evaluated models
    Qwen3.6-35B-A3B, Qwen3.5-9B, Qwen3.6-27B and others4

    Abstract作者报告潜意识学习可传递新技能、后门与作弊倾向,且分布外泛化强于单层转向向量。

    Paper analysisRead analysis
  6. DefensesarXiv 2610.08761

    VeriFine:通过扩展验证实现具身推理的自我改进

    提出 VeriFine,用双环协同扩展验证以实现具身推理自我改进

    Published
    Evaluated models
    Alpamayo 1.5 8B, Qwen3-VL 2B, Claude Opus 5
    AbstractVeriFine 用双环协同演化具身推理的策略、课程和评审,驾驶与导航的策略分和评审对齐都上升。

    VeriFine 把驾驶和导航推理的自改进写成策略、课程和无参考评审的协同演化,用来处理固定评审跟不上新失败模式的问题。

    Paper analysisRead analysis
  7. Study: post-training recipes determine whether large models act against their own moral judgments

    提出知行差距面板,测量压力下模型是否违背自身判断

    Published
    Evaluated models
    OLMo-3-7B-Instruct, Llama-3.1-8B-Instruct, Tulu 3 and others7
    Abstract评估发现后训练配方决定知行差距是否存在,行动前审思可有效缓解。

    本文评估了开源语言模型作为智能体行动时违背自身道德判断的知行差距及其决定因素。

    Paper analysisRead analysis
  8. The paper proposes a scaling law framework for alignment measured by risk category.

    提出分风险对齐标度律框架,测量各类风险的对齐负担如何随规模变化

    Published
    Evaluated models
    Pythia (14m–2.8b), Qwen2.5 (0.5B–72B), Qwen2.5-Instruct (0.5B–14B) and others4
    Abstract论文提出了分风险对齐标度律框架,测得真实性与倾向纠错呈标度有益,但盲后门仍存活,揭示隐藏风险的长期挑战。

    本文提出了一个将大语言模型对齐难度形式化为可测量标度关系的理论框架与预注册评测协议。

    Paper analysisRead analysis
  9. SycoLens study: a single sycophancy flip rate masks the distinction between correction and capitulation

    构建 SycoLens 重放评测,区分谄媚翻转中的纠错与屈从

    Published
    Evaluated models
    opus-5, sonnet-5, sonnet-4.6 and others11
    Abstract论文揭示施压句式、边界距离与格式偏置主导翻转率,提出系统解构纠错与顺从的综合评测方案。

    本文系统解构了大语言模型在用户质疑下的阿谀奉承行为与评测机制。

    Paper analysisRead analysis
  10. Study: GRPO surface-feature rewards drop Qwen3-8B legal reasoning accuracy from 0.500 to 0.072

    展示表面特征奖励驱动的法律模型以策略性弃答进行奖励投机

    Published
    Evaluated models
    Qwen3-8B
    Abstract揭示表面代理奖励诱发大模型通过策略性弃答博取高分,提出诊断工具与防御建议。

    本论文揭示了法律大语言模型在表面特征强化学习微调下的奖励投机现象。

    Paper analysisRead analysis
  11. DefensesarXiv 2610.05219

    AURA:用正交适配缓解 LLM 推理与安全对齐的子空间干扰

    提出 AURA,用正交惩罚分开顺序适配中的推理与安全子空间

    Published
    Evaluated models
    Qwen-3-14B, Qwen-2.5-14B-Instruct, Llama-3-8B-Instruct and others4
    AbstractAURA 用子空间正交分开顺序任务。

    AURA 是面向共享骨干智能体的顺序 LoRA 正则,用来分开前后任务的残差子空间。

    Paper analysisRead analysis
  12. DefensesarXiv 2610.04299

    R-Quest:用问题有效性与新颖性反馈维持推理模型自我进化

    提出 R-Quest,用有效性与新颖性反馈维持推理模型自我进化

    Published
    Evaluated models
    Qwen3-4B-Base, OctoThinker-3B-Hybrid-Base
    AbstractR-Quest 用有效性与新颖性反馈维持自进化。

    R-Quest 处理的是推理模型自进化中的题目质量:questioner 与 solver 用 GRPO 交替从自生成题目学习时,多轮之后平均成绩会下降。

    Paper analysisRead analysis