Human Feedback Types
strongPairwise Preference
Directly usable for protocol triage.
"Large language model (LLM) agents are moving beyond prompting alone."
HFEPX · Eval paper review
Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills
Pengcheng Jiang, Jiacheng Lin, Zhiyi Shi, Zifeng Wang +30 more
Published
Dec 18, 2025
Citations
0
Trust level
Moderate
Usefulness score
55/100 (Medium)
Extraction confidence
70% (Moderate)
Derived from extracted protocol signals and abstract evidence.
Rater population
Not reported
Signals refreshed
Mar 9, 2026
Should you rely on this paper?
This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.
Use this for comparison and orientation, not as your only source.
Low-signal caution for protocol decisions
Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.
- The abstract does not clearly name benchmarks or metrics.
Best use
Secondary protocol comparison source
Use if you need
A secondary eval reference to pair with stronger protocol papers.
What to verify
Read the full paper before copying any benchmark, metric, or protocol choices.
Main weakness
The abstract does not clearly name benchmarks or metrics.
Human feedback signal
Detected
From extracted signals
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
55/100
Moderate-confidence candidate
Useful as a secondary reference; validate protocol details against neighboring papers.
If you are doing eval pipeline work, start here
Abstract
Large language model (LLM) agents are moving beyond prompting alone. ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learning with verifiable rewards can improve reasoning and tool use, and OpenClaw highlights a newer direction in which agents accumulate persistent memory and reusable skills. Yet the research landscape remains fragmented across post-training, retrieval, memory, and skill systems. This survey studies these developments under a single notion of \emph{adaptation}: improving an agent, its tools, or their interaction after pretraining. We organize the field with a four-paradigm framework spanning agent adaptation and tool adaptation. On the agent side, A1 (tool-execution-signaled) and A2 (agent-output-signaled) improve the agent itself through supervised fine-tuning, preference optimization, and reinforcement learning with verifiable rewards. On the tool side, T1 (agent-agnostic) provides reusable pre-trained modules any agent can call, while T2 (agent-supervised) uses the agent's outputs to train memory systems, skill libraries, or lightweight subagents. Using this framework, we review post-training methods, adaptive memory architectures, and agent skills; compare their trade-offs in cost, flexibility, and generalization; and summarize evaluation practices across deep research, software development, computer use, and drug discovery. We conclude by outlining open problems in agent-tool co-adaptation, continual learning, safety, and efficient deployment.
What we could verify
These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.
Evaluation Modes
strongAutomatic Metrics
Includes extracted eval setup.
"Large language model (LLM) agents are moving beyond prompting alone."
Quality Controls
missingNot reported
No explicit QC controls found.
"Large language model (LLM) agents are moving beyond prompting alone."
Benchmarks / Datasets
missingNot extracted
No benchmark anchors detected.
"Large language model (LLM) agents are moving beyond prompting alone."
Reported Metrics
missingNot extracted
No metric anchors detected.
"Large language model (LLM) agents are moving beyond prompting alone."
Benchmarks and datasets
No benchmark or dataset names were extracted from the available abstract.
Reported metrics
No metric terms were extracted from the available abstract.
Human feedback details
- Uses human feedback
- Yes
- Feedback types
- Pairwise Preference
- Rater population
- Not reported
- Expertise required
- General
Evaluation details
- Evaluation modes
- Automatic Metrics
- Agentic eval
- Tool Use
- Quality controls
- Not reported
- Evidence quality
- Moderate
- Use this page as
- Secondary protocol comparison source
Research brief
Metadata summary
Large language model (LLM) agents are moving beyond prompting alone.
Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.
Key takeaways
- Large language model (LLM) agents are moving beyond prompting alone.
- ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learning with verifiable rewards can improve reasoning and tool use, and OpenClaw highlights a newer direction in which agents accumulate persistent memory and reusable skills.
- Yet the research landscape remains fragmented across post-training, retrieval, memory, and skill systems.
Researcher actions
- Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
- Validate inferred eval signals (Tool-use evaluation) against the full paper.
- Use related-paper links to find stronger protocol-specific references.
Caveats
- Generated from abstract + metadata only; no PDF parsing.
- Signals below are heuristic and may miss details reported outside the abstract.
Recommended queries
Contribution summary
- Large language model (LLM) agents are moving beyond prompting alone.
- ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learning with verifiable rewards can improve reasoning and tool use, and OpenClaw highlights a newer direction in which agents…
- This survey studies these developments under a single notion of adaptation: improving an agent, its tools, or their interaction after pretraining.
Why it matters for eval
- Large language model (LLM) agents are moving beyond prompting alone.
- ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learning with verifiable rewards can improve reasoning and tool use, and OpenClaw highlights a newer direction in which agents…
Researcher checklist
-
Human feedback protocol is explicit
Detected: Pairwise Preference
-
Evaluation mode is explicit
Detected: Automatic Metrics
-
Quality control reporting appears
No calibration/adjudication/IAA control explicitly detected.
-
Benchmark or dataset anchors are present
No benchmark/dataset anchor extracted from abstract.
-
Metric reporting is present
No metric terms extracted.