Agents

LLM agents and the systems around them: harnesses and orchestration, tool use and MCP, multi-agent systems, agent memory and planning

600 articles · page 11 of 13

Agents

Editing agent reasoning history boosts long-horizon task performance

The authors propose AEWM, a world model that edits agent reasoning and action histories to remove noisy or outdated state, rather than predicting environment observations. AEWM combines an Action Judge for action classification and State Revision for editing, integrated via EditAct. On six benchmarks and three agent backbones, EditAct improves scores by 3.2–6.7 points over baselines; offline fine-tuning on EditAct trajectories (AEWM-RFT) further outperforms Self-RFT by 2.2–2.6 points without online guidance.

·2 min
Agents

Reinforcement learning trains video AI agents to use external tools effectively

The authors present VideoGen-Agent, a multimodal agent trained via multitask agentic reinforcement learning to orchestrate external tools for video generation. On the introduced VABench benchmark, the agent improves its base text-to-video generator from 56.5 to 75.6, and upgrading the generation tools further raises the score to 86.1 without additional agent training. Human raters prefer the upgraded configuration over the strongest standalone baseline in 84.3% of comparisons.

·3 min
Agents

Trajectory shortcut trees improve agents without outcome labels or annotations

Liu et al. developed DENSE, a method that extracts completed work, recovery evidence, and unresolved requirements from agent trajectories without knowing whether the original attempt ultimately succeeded. On Terminal-Bench 2.1, reruns guided by this distilled evidence improved strict pass rates across four recipient models by 7.12–15.64 percentage points while reducing their observed token use by 19.0–43.6%.

·2 min
Agents

Obstacle-aware harness improves safety of coding agents for robot manipulation

Bingxin Xu and colleagues evaluate whether coding agents—large language models that write robot controllers as programs—can respect a physical safety constraint, pairing each manipulation goal with an obstacle the robot must not touch. They find the agents prioritize task completion and collide in most cases, but their SafeHarness harness improves collision avoidance from 60.5% to 87.5% while raising task success to 71.9%.

·2 min
Agents

Cross-task failure diagnosis makes LLM agent harness training faster

The authors developed Ecdysis, a framework for improving the runtime code and instructions that govern an LLM agent’s execution. Rather than revising a harness after each failed task, it analyzes batches of failures for recurring patterns and uses multiple diagnostic roles to propose refinements. In the reported experiments, this reduced training time by up to 1.84× while increasing reasoning accuracy by 18.56% over existing harness-evolution methods.

·2 min