HFEPX · Eval paper review
Haofei Yu, Yixing Chen, Yining Zhao, Xuyan Ye +5 more
Published
Oct 14, 2026
Citations
0
Trust level
Moderate
Usefulness score
27/100 (Low)
Extraction confidence
55% (Moderate)
Derived from extracted protocol signals and abstract evidence.
Rater population
Not reported
Signals refreshed
Oct 15, 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 secondary eval reference to pair with stronger protocol papers.
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
Training language agents is bottlenecked by the high cost of long-horizon rollouts, yet standard agentic reinforcement learning (RL) learns only from a terminal scalar reward, leaving the supervision in intermediate steps largely unused. Prior work exploits this supervision through value targets that estimate per-step success probabilities or observation targets that fit environment response. Both are hard to construct well: (1) value targets come from the same single scalar signal for each step in the trajectory, and (2) observation targets, such as web pages and terminal logs, are long and noisy and reach only one step ahead. We propose CoPE, which adds a third kind of multi-step action targets. On successful on-policy trajectories, CoPE trains the policy backbone to generate the action sequences that follows each history. Each action is also supervised when forecast from the preceding histories, forming a temporal ensemble that the shared backbone absorbs during training, and this enables acting and forecasting to co-evolve. The policy still acts one step at a time at inference, with no overhead. Across five benchmarks (ALFWorld, ScienceWorld, WebShop, $τ^2$-bench, and AppWorld), CoPE (1) achieves stronger aggregate performance than GRPO and RL baselines with predictive auxiliary targets across simulated environments, while improving overall performance on both realistic applications; (2) delivers up to $1.9\times$ and $2.0\times$ higher sample efficiency than ECHO and GRPO, respectively, on ScienceWorld; and (3) achieves these gains with a single policy backbone, without additional models, separate pretraining, or inference overhead. The codebase is available at https://github.com/ulab-uiuc/CoPE.
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.
"Training language agents is bottlenecked by the high cost of long-horizon rollouts, yet standard agentic reinforcement learning (RL) learns only from a terminal scalar reward, leaving the supervision in intermediate steps largely unused."
Simulation Env
Includes extracted eval setup.
"Training language agents is bottlenecked by the high cost of long-horizon rollouts, yet standard agentic reinforcement learning (RL) learns only from a terminal scalar reward, leaving the supervision in intermediate steps largely unused."
Not reported
No explicit QC controls found.
"Training language agents is bottlenecked by the high cost of long-horizon rollouts, yet standard agentic reinforcement learning (RL) learns only from a terminal scalar reward, leaving the supervision in intermediate steps largely unused."
ALFWorld, WebShop
Useful for quick benchmark comparison.
"Across five benchmarks (ALFWorld, ScienceWorld, WebShop, $τ^2$-bench, and AppWorld), CoPE (1) achieves stronger aggregate performance than GRPO and RL baselines with predictive auxiliary targets across simulated environments, while improving overall performance on both realistic applications; (2) delivers up to $1.9\times$ and $2.0\times$ higher sample efficiency than ECHO and GRPO, respectively, on ScienceWorld; and (3) achieves these gains with a single policy backbone, without additional models, separate pretraining, or inference overhead."
Not extracted
No metric anchors detected.
"Training language agents is bottlenecked by the high cost of long-horizon rollouts, yet standard agentic reinforcement learning (RL) learns only from a terminal scalar reward, leaving the supervision in intermediate steps largely unused."
No metric terms were extracted from the available abstract.
Training language agents is bottlenecked by the high cost of long-horizon rollouts, yet standard agentic reinforcement learning (RL) learns only from a terminal scalar reward, leaving the supervision in intermediate steps largely unused.
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: Simulation Env
Quality control reporting appears
No calibration/adjudication/IAA control explicitly detected.
Benchmark or dataset anchors are present
Detected: ALFWorld, WebShop
Metric reporting is present
No metric terms extracted.
