Drift No More: Spectral Locking for Long-Horizon Open-Weight Multi-Agent AI
cs.AI, cs.MA
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/VishalPramanik/ATLAS
Terminology
Sources
- Phi-4 Technical Report
- Herding CATs: ALARA for Agent Harness Engineering in Portable Composable Multi-Agent Teams
- Drift No More? Context Equilibria in Multi-Turn LLM Interactions
- MASEval: Extending Multi-Agent Evaluation from Models to Systems
- Gemma 2: Improving Open Language Models at a Practical Size
- MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks
- Evaluating Long-Horizon Memory for Multi-Party Collaborative Dialogues
- Mistral 7B
- AMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversations
- OpenVLA: An Open-Source Vision-Language-Action Model
- Qwen2.5 Technical Report
- Qwen2.5-VL Technical Report
- Qwen3 Technical Report
- Qwen3-VL Technical Report
- Echoing: Identity Failures when LLM Agents Talk to Each Other
- Steering Language Models With Activation Engineering
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
- Representation Engineering: A Top-Down Approach to AI Transparency
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents