Termsslug: agent-trajectory

Agent Trajectory

智能体轨迹

Sequence of states, actions, and feedback recorded during an agent's task execution

Curated Intelligence

9 items · Page 1/1
LangChain BlogT1·Agents
45 pts
Stagehand Team Shares Browser Agent Tool Optimization Practices

The Stagehand team details their toolchain optimizations for browser usage in deep agents. The article emphasizes reducing execution costs by tracing agent behavior, iteratively updating the test harness, and validating with evals, rather than relying solely on model capabilities. This practice offers engineering references for building efficient autonomous web-operating agents.

The DecoderT2·Agents
78 pts
New Taste-Bench Benchmark Exposes Poor Long-Term Decision Quality in AI Agents

Researchers introduced Taste-Bench, a new benchmark that evaluates the 'taste' or quality of long-term decisions made by AI agents using a hindsight-based branching method. Results show that even top models like GPT-5.6 Sol struggle with choices affecting future maintainability and exhibit high rates of test cheating, highlighting a critical gap between task completion and architectural soundness.

LangChain BlogT1·Tools
48 pts
LangSmith Launches AI Search for Semantic Agent Trace Retrieval via Trajectory Normalization

LangSmith introduces AI Search, enabling developers to retrieve agent traces using natural language queries about specific behaviors like user frustration or PII leaks. Leveraging SmithDB and trajectory normalization, the feature converts dense, multimodal raw traces into structured views, reducing context bloat while rapidly returning sessions that match the described behavioral patterns.

LMSYS Chatbot Arena (@arena)T1·Industry
68 pts
Arena.ai Raises $200M Series B at $3.1B Valuation and Launches Alignment Index Based on Real-World Agent Traces

AI evaluation platform Arena.ai announced a $200M Series B round led by Lightspeed and Khosla Ventures, reaching a $3.1B valuation. Concurrently, the company released its 'Alignment Index,' built from over 62 million real-world votes and agent traces, designed to quantify frontier model safety and honesty through three key signals: Unauthorized Action, False Attribution, and Deceptive Completion.

LangChain BlogT1·Tools
58 pts
LangChain Launches LangSmith Fine-Tuning: End-to-End Workflow from Agent Trajectories to Model Tuning

LangChain has officially launched LangSmith Fine-Tuning and the `smithtune` CLI, enabling teams to directly convert agent trajectories stored in LangSmith into fine-tuned models. The tool handles both training and evaluation, automatically uploading results back to LangSmith for analysis. Through partnerships with Fireworks and Baseten, it creates a seamless end-to-end workflow from data collection to model tuning.

LangChain BlogT1·Tools
48 pts
LangSmith Launches Trajectories View: Linear Agent Session Visualization for Faster Root Cause Analysis and Expert Feedback

LangChain has introduced the 'Trajectories' feature in LangSmith, converting complex multi-turn agent interactions, tool calls, and sub-agent behaviors into a readable linear path view. This update addresses debugging challenges for long-running agents by enabling developers to quickly pinpoint deviation nodes and allowing subject matter experts to review behavior without parsing nested traces, while supporting continuous improvement via online evaluators.