arXiv AI
Aug 7
Continual Learning in Transition
arXiv:2608. 06216v1 Announce Type: cross Abstract: Classical continual learning (CL) has primarily focused on enabling models to update and retain knowledge through parameter-centric mechanisms, e.
RECAP: Regression Evaluation for Continual Adaptation of Prompts
arXiv:2606. 06698v1 Announce Type: new Abstract: Production agentic systems routinely face evolving constraints and must comply from the very next interaction.
Related stories
arXiv AI
Jun 17
SEAGym: An Evaluation Environment for Self-Evolving LLM Agents
arXiv:2606. 17546v1 Announce Type: new Abstract: Self-evolving LLM-based agents improve mainly by changing their agent harness: the structured execution layer around a base model, including prompts, memory, tools, middleware, runtime state, and the model-tool interaction loop.
arXiv Machine Learning
Jul 10
TTHE: Test-Time Harness Evolution
arXiv:2607. 08124v1 Announce Type: cross Abstract: The behavior of an LLM agent is determined not only by the underlying model, but also by its harness: the executable program that constructs context, invokes tools, verifies intermediate results, and recovers from failures.
arXiv Machine Learning
Jul 27
Toward User-Conditioned Evaluation of Personal LLM Agents under Temporal Interventions
arXiv:2607. 21635v1 Announce Type: new Abstract: Personal agents maintain memories, learned skills, tool configurations, and policy state that evolve with each user.
arXiv AI
Sep 17
Bad Genius: Counterfactual-Guided Harness Evolution Beyond Task-Specific Shortcuts
arXiv:2609. 18366v1 Announce Type: new Abstract: Reliable agent evaluation is complicated by automatic harness optimization, which repeatedly uses a released benchmark $B_{\mathrm{rel}}$ to guide a Proposer that edits prompts, memory, retrieval, tools, and control code around a fixed target agent.
arXiv AI
Aug 18
CAPO: Constraint-Aware Prompt Optimization for LLM Agents
arXiv:2608. 16068v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as agents that rely on system prompts to use tools and complete tasks.
arXiv Machine Learning
Jun 5
CLaaS: Continual learning as a service for sample efficient online learning
arXiv:2606. 05559v1 Announce Type: new Abstract: Deployed large language model agents must adapt to distribution shift in dynamic environments.
arXiv AI
Jul 16
Learning to Learn-at-Test-Time: Language Agents with Learnable Adaptation Policies
arXiv:2604. 00830v3 Announce Type: replace-cross Abstract: Test-Time Learning (TTL) enables language agents to iteratively refine their performance through repeated interactions with the environment at inference time.
arXiv AI
Sep 2
HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution
HarnessEvolve is a self‑evolving framework that improves agent harnesses—prompts, skills, tools, and execution logic—by learning from reference trajectories. It separates execution, evaluation, optimization, and gating into independent modules, addressing credit assignment failure, shortcut learning, and catastrophic forgetting. The approach uses reference trajectories to extract error signals, applies quality and performance gates to candidate updates, and validates updates on held‑out data, consistently outperforming state‑of‑the‑art baselines across diverse benchmarks.
Hugging Face Trending Papers
Aug 4
Fail-Fast, Restart-Smart: Early Failure Prediction and Restart for SWE Agentic Tasks
Software engineering (SWE) agents resolve repository-level issues through long trajectories that grow increasingly expensive as context accumulates. Failed runs tend to be longer and exhibit redundant exploration or looping, suggesting that some failures may be detectable before completion.
arXiv AI
Jun 11
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference
arXiv:2606. 05922v2 Announce Type: replace Abstract: AI agents rely on a harness of skills, tools, and workflows to solve complex problems.
arXiv Machine Learning
Aug 21
When to Retrain: An Empirical Study of Retraining Policies for Streaming ML Under Concept Drift, Budget, and Latency Constraints
arXiv:2608. 19488v1 Announce Type: new Abstract: Production machine learning systems degrade under concept drift, yet practitioners have little principled guidance on when to retrain.