Search

7 results for “GSM8K”

1. Research · Safety & security

   Private-query AI assistants leak secrets through rejected drafts, new protocol plugs the hole

   Answer-Only Disclosure: Private-Context LLM Assistance over Web APIs with a Leakage Ledger

   A protocol called ADLER ensures the cloud sees only what the user sees, and a leakage ledger caps how much the answer reveals about private documents

   GSM8K: 5.4 s modelled communication time per answer (as reported)

   30 Oct 2026Australian Catholic University, Ant Group, University of Macau

2. Research · Safety & security

   LookAhead Defense uses the model's own safe behavior to block dormant poisoning.

   Defending Against Dormant Poisoning Attacks Across Language and Multimodal Agents

   It penalizes only updates that weaken safety, reducing harmful agent actions from 93.9% to 14.2%.

   ASB: 7% poison activation (as reported)

   20 Oct 2026UNC Chapel Hill, Kyung Hee University

3. Research · Agents

   Localized Context Distillation resolves the learning dilemma in interaction experience

   Learning from Interaction Experience via Localized Context Distillation

   The authors propose a method that identifies and revises only critical spans in a student's trajectory, outperforming both off-policy and on-policy context distillation across math, code, and agent tasks.

   AIME24: 61.3% accuracy (avg@12) (as reported)

   16 Oct 2026Tencent, The Chinese University of Hong Kong, Zhejiang University

4. Research · Agents

   Contrasting multiple trajectories sharpens skill learning for LLMs

   SkillCome: Group Contrast Skill Optimization with Dual Memory

   SkillCome generates several attempts per question and compares them to identify what separates success from failure, then stores patterns across rounds in a dual memory.

   ALFWorld: 95.9% accuracy (as reported)

   30 Sept 2026Fudan University, Ant Group, Shanghai Jiao Tong University

5. Research · Agents

   Multi-agent LLM scaling benefits depend on task type and aggregation method

   Multi-agent Scaling Across Disjunctive and Compensatory Tasks

   Disjunctive tasks see accuracy gains from revision but not from larger teams, while compensatory tasks show little benefit from averaging due to shared model biases.

   GSM8K: 54.44% pass@30 (as reported)

   28 Sept 2026

6. Research · Agents

   Three-stage training instills world model planning into LLM agents

   Internalizing the Future: A Unified Agentic Training Paradigm for World Model Planning

   The authors show that injecting latent predictive capability through mid-training, then structuring it via supervised fine-tuning and calibrating with reinforcement learning, enables agents to verbalize future rollouts and success estimates, outperforming reactive baselines.

   25 Jun 2026Fudan University, Shanghai Innovation Institute, Tencent Youtu Lab

7. Research · Agents

   Letting language models decide when to compact their context windows

   Self-Compacting Language Model Agents

   SelfCompact scaffold pairs a compaction tool with a lightweight rubric, enabling adaptive context summarization without fine-tuning.

   competition math (IMO-Answerbench, HMMT Nov 25/Feb 26): 18.1% accuracy improvement over no-summarization baseline (as reported)

   22 Jun 2026Johns Hopkins University, AppleCode