RASSG: Repair-Aware Semantic Survival Gating for Streaming Tool Execution
cs.AI
Submitted: 2026-10-10
Updated: 2026-10-10
Code: https://github.com/daijinhu/RASSG
Sources
- Audio2Tool: Speak, Call, Act -- A Dataset for Benchmarking Speech Tool Use
- DuplexSLA: A Full-Duplex Spoken Language Model with Synchronized Speech, Language, and Action
- Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage
- Full-Duplex-Bench-v3: Benchmarking Tool Use for Full-Duplex Voice Agents Under Real-World Disfluency
- Low-Latency Sequence-to-Sequence Speech Recognition and Translation by Partial Hypothesis Selection
- PredGen: Accelerated Inference of Large Language Models through Input-Time Speculation for Real-Time Speech Interaction
- LTS-VoiceAgent: A Listen-Think-Speak Framework for Efficient Streaming Voice Interaction via Semantic Triggering and Incremental Reasoning
- Speculative Interaction Agents: Building Real-Time Agents with Asynchronous I/O and Speculative Tool Calling
- $\tau$-Voice: Benchmarking Full-Duplex Voice Agents on Real-World Domains
- Auditing Automated Evaluation, Error Propagation, and Runtime Mitigation in Tool-Using Language Agents
- Conveyor: Efficient Tool-aware LLM Serving with Tool Partial Execution
- Qwen3 Technical Report
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