SquidAgent: Parallelize Wisely, Coordinate Efficiently
cs.AI, cs.CL, cs.LG
Submitted: 2026-10-06
Updated: 2026-10-06
Code: https://github.com/tmllab/2026_
Sources
- VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction
- Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers
- False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
- Improving Factuality and Reasoning in Language Models through Multiagent Debate
- 'No' Matters: Out-of-Distribution Detection in Multimodality Long Dialogue
- Delving into the Temporal Challenges of Unified Video Protection Against Image-to-Video and Fine-Tuning-based Customization
- Is Gradient Ascent Really Necessary? Memorize to Forget for Machine Unlearning
- Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization
- Does Your Reasoning Model Implicitly Know When to Stop Thinking?
- Real-Time Aligned Reward Model beyond Semantics
- Deferred Exposure of Future Trajectories for Verifiable Reasoning in Autonomous Driving VLMs
- The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
- When Models Learn to Ask Why: Adaptive Causal Reasoning for Trustworthy Medical Vision-Language Models
- Estimating and Orthogonalizing Unknown Pre-training Gradients for Continual Fine-tuning of Large Language Models
- AgentConductor: Topology Evolution for Multi-Agent Competition-Level Code Generation
- From Agent Loops to Structured Graphs:A Scheduler-Theoretic Framework for LLM Agent Execution
- Internal Safety Collapse in Frontier Large Language Models
- When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skills
- Rethinking the Value of Multi-Agent Workflow: A Strong Single Agent Baseline
- From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems