JevAgentHarness is a new framework that benchmarks, deploys, and trains decision models to share control with large language models (LLMs) in agentic tasks. It introduces AgentDecisionBench to evaluate decision models from isolated questions to full agent control, revealing that accurate isolated decisions still miss many tasks and that naïve delegation can reduce success. By fitting confidence thresholds per choice and training a 4B decision model on states after agent mistakes, JevAgentHarness achieves high task success while cutting cost and speeding up execution, with results and resources made publicly available.
Large language model (LLM) agents now fix software, operate computers and serve customers, but their harnesses, the programs that run them, call a large LLM at every step, which makes long tasks slow...
arXiv:2610.02267v1 Announce Type: new Abstract: Agent harnesses make many small, typed decisions per task: which model to call, which tool to use, whether retrieved text is relevant, whether an input...
StoreBench is a live‑commerce environment where an autonomous agent runs a mid‑size online apparel store on a production‑grade backend, facing continuous customer orders, supplier price changes, and market shocks. The agent uses the same 29 merchant tools as a human operator, with a windowed operation budget that ties simulated time to actions, ensuring that model latency does not affect the simulation. Seven large language models were evaluated across 11 scenarios of 30–45 days and a full simulated year, but none matched the scripted smart‑triage policy, and human experts outperformed all models.
The paper introduces the concept of an agent’s "taste"—its ability to make effective long‑horizon decisions—and presents Taste‑Bench, a new benchmark that automatically generates decision‑fork questions from agent trajectories. Taste‑Bench evaluates models on choosing the best path without seeing future outcomes, revealing that top models answer only about 60% of questions correctly and that later‑appearing evidence makes forks harder. The authors also demonstrate that training a student model to mimic a teacher’s judgment improves decision quality and overall success on held‑out software engineering tasks.
arXiv:2608. 20318v1 Announce Type: new Abstract: Recursive self-improvement (RSI) asks whether an AI system can improve the process that produces AI systems, so that the next system inherits the improvement.
arXiv:2608. 05519v1 Announce Type: new Abstract: Agent benchmarks usually measure task completion and treat resource use as an auxiliary statistic.
arXiv:2609. 37968v1 Announce Type: new Abstract: Advances in the coding capabilities of LLM agents allow them to inspect and modify their own instructions, tools, and execution procedures.
arXiv:2609.23886v1 Announce Type: new Abstract: Software delegates more of its branches to models every year: which queue a ticket enters, whether a command is safe to run, whether a claim clears wit...
The paper introduces TalkMesh, a decentralized network of small language model agents that learn to communicate effectively during inference. Each agent proposes an answer, scores it with a confidence head, and the most confident agent broadcasts a hint; lower‑confidence agents revise their proposals if a new suggestion scores higher. This gossip‑based consensus, trained via group relative policy optimization, enables a mesh of three agents to match the accuracy of majority voting over 32 samples, and scales to larger meshes to significantly boost performance on benchmarks like GSM8K and MATH-500.
arXiv:2608. 08466v1 Announce Type: new Abstract: Modern LLM agents are often improved by modifying prompts, tools, or workflows manually, while the executable scaffold surrounding the model---the \emph{harness}---is typically treated as a fixed artifact after deployment.
JevAdvBench introduces the first adversarial benchmark for reinforcement‑learning‑based calibrated decision (RLCD) models, providing 812 typed questions across 66 scenarios and a black‑box attack suite of 9,744 single‑edit variants. The benchmark evaluates attacks by comparing each perturbed decision to the model’s own clean decision and to an identical re‑run, revealing that rewording changes decisions by only 1.2 percentage points while certain injected opinions can flip 12.1% of decisions and lower confidence below 0.8 in 38% of cases. These findings demonstrate that RLCD models can be significantly misled by seemingly innocuous input edits, underscoring the need to treat the state as untrusted in applications.
System1-Arena is a benchmark that evaluates which decisions can be handled by System‑1 models—those that output probabilities in a single forward pass—versus System‑2 models that generate reasoning steps. It contains 92,000 questions across 105 tasks from 268 public sources, grouped into text classification, applied decisions, evaluation and control, and agent/action, and also includes 138 closed‑loop environments such as web shopping, coding control, robotics, games, and driving. The study tests 30 models, showing that large System‑1 models can match or exceed fast closed LLMs in non‑agentic accuracy with better‑calibrated probabilities at lower latency, while reasoning LLMs are most accurate but far more expensive, and large open LLMs perform best in closed‑loop settings.