GRASP: Gated Regression-Aware Skill Proposer for Self-Improving LLM Agents

• URL: http://arxiv.org/abs/2605.29668v1
• Date: Thu, 28 May 2026 09:30:09 GMT
• Title: GRASP: Gated Regression-Aware Skill Proposer for Self-Improving LLM Agents
• Abstract summary: GRASP (Gated Regression-Aware Skill Proposer) treats agent improvement as a sequence of edits to a bounded skill library.<n>We evaluate GRASP across five base models on clinical benchmarks.
• Score: 17.26555663132631
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLM agents acting in structured environments fail in operational rather than conversational ways, and reliability depends on procedural knowledge of the environment. Prior self-improvement methods accumulate natural-language guidance without checking that each new item preserves previously correct behavior, so a note that fixes one trajectory can silently regress another. We introduce GRASP (Gated Regression-Aware Skill Proposer), which treats agent improvement as a sequence of edits to a bounded skill library, admitting each candidate only if it produces a net improvement on a balanced held-out probe under a hard regression budget. We evaluate GRASP across five base models (gpt-oss-120b, DeepSeek V4 Flash, Gemini 3.1 Flash Lite, GPT-4.1, GPT-5.4) on two FHIR-based clinical benchmarks. On MedAgentBench, GRASP lifts gpt-oss-120b from 40.6% to 88.8%, exceeds the strongest of five self-improvement baselines by 21.0 points, and improves every other base model by 17.2 to 40.3 points. Ablations attribute the gain to comparative proposal generation, the acceptance gate, and the hard regression budget rather than to skill writing itself, which without validation is no better than using no skills. The mechanism generalizes beyond the clinical domain, improving agents on three of four non-clinical environments and remaining flat only where the action space is open-ended. Frozen libraries transfer across models, where skills from a stronger model improve weaker executors beyond what they learn for themselves while the reverse does not, an asymmetry that no ungated baseline reproduces.

Related papers

• When Not to Imitate: Boundary-Aware Skill Memory for Reliable Tool-Use LLM Agents [62.10623192614306]
  Extracting skills from past successes is critical for the efficient evolution of Large Language Model (LLM) agents.<n>We propose textbfBoundary-Aware Skill Memory (BASM), which augments each skill with explicit boundary fields.<n>BASM consistently outperforms success-distilled skill-memory baselines.
  arXiv  Detail & Related papers  (2026-08-23T10:16:06Z)
• PACE-Bench: Benchmarking Physics Adaptation via Code Evolution in Dynamic Environments [8.552837617531766]
  PACE-Bench is a simulator-grounded benchmark of 144 source-to-target adaptation pairs across six physics domains.<n>We show that simulator-grounded reflection is more reliable than self-revision.<n>Even revealing exact physical changes does not raise the performance ceiling.
  arXiv  Detail & Related papers  (2026-08-14T16:25:43Z)
• Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds [43.5891705224868]
  Self-evolving skill systems promise to improve agents by turning execution feedback into persistent skill updates without changing the underlying model.<n>We present a controlled evaluation framework across five benchmarks and three models.<n>Overall, persistent skill self-evolution is better understood as sparse, validation-filtered search with model- and benchmark-dependent returns.
  arXiv  Detail & Related papers  (2026-07-31T04:02:51Z)
• PACE: Two-Timescale Self-Evolution for Small Language Model Agents [7.324586777176562]
  We study whether frozen small language models (SLMs) can serve as effective self-evolving agents under resource constraints.<n>We propose PACE (Prompt And Control Logic Evolution), a two-timescale framework that coordinates low-risk prompt refinement with higher-risk control-logic updates.
  arXiv  Detail & Related papers  (2026-05-21T20:42:06Z)
• FORGE: Self-Evolving Agent Memory With No Weight Updates via Population Broadcast [3.774094352572544]
  FORGE wraps a Reflexion-style inner loop, where a dedicated reflection agent converts failed trajectories into reusable knowledge artifacts.<n>We evaluate on CybORG CAGE-2 a network-defense POMDP at a 30-step horizon against the B-line attacker.<n>Compared against both a zero-shot baseline and a Reflexion baseline (isolated single-stream learning), FORGE improves average evaluation return by 1.7-7.7$times$ over zero-shot.
  arXiv  Detail & Related papers  (2026-05-15T17:42:49Z)
• REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge [83.2858110368572]
  We propose textbfREAL (underlineREgression-underlineAware Reinforcement underlineLThought), a principled RL framework designed to optimize regression rewards.<n>We show that REAL consistently outperforms both regression-aware SFT baselines and standard RL methods.
  arXiv  Detail & Related papers  (2026-03-17T21:19:08Z)
• LLMs can Compress LLMs: Adaptive Pruning by Agents [0.0]
  Post-training pruning has emerged as a promising approach to reduce computational costs while preserving performance.<n>We introduce agent-guided pruning, where a foundation model acts as an adaptive pruning agent.<n>We evaluate our approach on Q3 models (4B and 8B parameters) at approximately 45% sparsity, demonstrating substantial improvements over structured pruning baselines.
  arXiv  Detail & Related papers  (2026-01-14T18:45:36Z)
• RefineBench: Evaluating Refinement Capability of Language Models via Checklists [71.02281792867531]
  We evaluate two refinement modes: guided refinement and self-refinement.<n>In guided refinement, both proprietary LMs and large open-weight LMs can leverage targeted feedback to refine responses to near-perfect levels within five turns.<n>These findings suggest that frontier LMs require breakthroughs to self-refine their incorrect responses.
  arXiv  Detail & Related papers  (2025-11-27T07:20:52Z)
• In-the-Flow Agentic System Optimization for Effective Planning and Tool Use [73.72524040856052]
  AgentFlow is a trainable, in-the-flow agentic framework that coordinates four modules (planner, executor, verifier, generator) through an evolving memory.<n>Flow-GRPO tackles long-horizon, sparse-reward credit assignment by converting multi-turn optimization into a sequence of tractable single-turn policy updates.<n>AgentFlow with a 7B-scale backbone outperforms top-performing baselines with average accuracy gains of 14.9% on search, 14.0% on agentic, 14.5% on mathematical, and 4.1% on scientific tasks.
  arXiv  Detail & Related papers  (2025-10-07T05:32:44Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback [59.078756231841574]
  Critique-GRPO is an online RL framework that integrates both natural language and numerical feedback for effective policy optimization.<n>We show Critique-GRPO consistently outperforms supervised learning and RL-based fine-tuning methods across eight challenging mathematical, STEM, and general reasoning tasks.
  arXiv  Detail & Related papers  (2025-06-03T17:39:02Z)
• S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning [51.84977135926156]
  We introduce S$2$R, an efficient framework that enhances LLM reasoning by teaching models to self-verify and self-correct during inference.<n>Our results demonstrate that Qwen2.5-math-7B achieves an accuracy improvement from 51.0% to 81.6%, outperforming models trained on an equivalent amount of long-CoT distilled data.
  arXiv  Detail & Related papers  (2025-02-18T13:40:22Z)
• Self-Play Preference Optimization for Language Model Alignment [75.83359213697854]
  Recent advancements suggest that directly working with preference probabilities can yield a more accurate reflection of human preferences. We propose a self-play-based method for language model alignment, which treats the problem as a constant-sum two-player game. Our approach, dubbed Self-Play Preference Optimization (SPPO), utilizes iterative policy updates to provably approximate the Nash equilibrium.
  arXiv  Detail & Related papers  (2024-05-01T17:59:20Z)
• Aligner: Efficient Alignment by Learning to Correct [10.056049435141645]
  We introduce Aligner, a model-agnostic, plug-and-play module that learns the correctional residuals between preferred and dispreferred answers. It can be applied to various open-source and API-based models with only one-off training, making it suitable for rapid iteration. Our experiments demonstrate performance improvements by deploying the same Aligner model across 11 different language models.
  arXiv  Detail & Related papers  (2024-02-04T09:24:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.