Human Feedback Types
missingNone explicit
No explicit feedback protocol extracted.
"Deep-research agents repeatedly decide what to search, read, and verify, often using large cloud-hosted language models for action proposal."
HFEPX · Eval paper review
Yuhao Zhou, Yang Zhou, Yuanxi Li, Jindi Lv +3 more
Published
Nov 19, 2026
Citations
0
Trust level
Moderate
Usefulness score
37/100 (Low)
Extraction confidence
60% (Moderate)
Derived from extracted protocol signals and abstract evidence.
Rater population
Not reported
Signals refreshed
Nov 19, 2026
This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.
Use this for comparison and orientation, not as your only source.
Best use
Background context only
Use if you need
A benchmark-and-metrics comparison anchor.
What to verify
Validate the evaluation procedure and quality controls in the full paper before operational use.
Main weakness
No major weakness surfaced.
Treat as adjacent context, not a core eval-method reference.
If you are doing eval pipeline work, start here
Deep-research agents repeatedly decide what to search, read, and verify, often using large cloud-hosted language models for action proposal. However, privacy and local control motivate running agents on users' devices, where limited memory and compute favor smaller models and complicate on-device training. Yet inference-time guidance faces three obstacles: exploring alternatives through real execution adds tool calls, prompted self-evaluation is bounded by the agent's judgment, and model-specific guidance risks repeated adaptation costs. We introduce Seer, an inference-time framework providing local guidance that separates the agent's action proposal from learned consequence prediction and value estimation. From a shared corpus of real research trajectories, we train two models: a tool-response simulator on observed call--response pairs and a value estimator on histories labeled with discounted terminal correctness. The simulator and estimator are trained offline and reused across agents without further training. Moreover, Seer executes only the selected action and adds only real tool responses to the committed history, avoiding tool calls on discarded candidates at additional inference cost. Across multiple deep-research benchmarks, Seer substantially improves agent performance for different language models. For instance, GAIA accuracy rises from 13.6% to 41.7% for Qwen3.5-4B and from 22.3% to 50.5% for Qwen3.5-9B. Furthermore, our analyses suggest that broader candidate coverage can compensate for imperfect simulation, while prediction and scoring errors limit the benefits of wider imagined search. These findings highlight the potential of reusable models for prediction and evaluation to strengthen small research agents through extra local computation without the real execution of the discarded candidates.
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.
None explicit
No explicit feedback protocol extracted.
"Deep-research agents repeatedly decide what to search, read, and verify, often using large cloud-hosted language models for action proposal."
Automatic Metrics, Simulation Env
Includes extracted eval setup.
"Deep-research agents repeatedly decide what to search, read, and verify, often using large cloud-hosted language models for action proposal."
Not reported
No explicit QC controls found.
"Deep-research agents repeatedly decide what to search, read, and verify, often using large cloud-hosted language models for action proposal."
GAIA
Useful for quick benchmark comparison.
"For instance, GAIA accuracy rises from 13.6% to 41.7% for Qwen3.5-4B and from 22.3% to 50.5% for Qwen3.5-9B."
Accuracy
Useful for evaluation criteria comparison.
"For instance, GAIA accuracy rises from 13.6% to 41.7% for Qwen3.5-4B and from 22.3% to 50.5% for Qwen3.5-9B."
Deep-research agents repeatedly decide what to search, read, and verify, often using large cloud-hosted language models for action proposal.
Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.
Human feedback protocol is explicit
No explicit human feedback protocol detected.
Evaluation mode is explicit
Detected: Automatic Metrics, Simulation Env
Quality control reporting appears
No calibration/adjudication/IAA control explicitly detected.
Benchmark or dataset anchors are present
Detected: GAIA
Metric reporting is present
Detected: accuracy