| Challenge: | Unlike fine-tuning or static retrieval methods, DC adapts LMs’ problem-solving skills on the fly, without modifying their underlying parameters. |
| Approach: | They propose a lightweight framework that endows a black-box LM with a persistent, evolving memory. |
| Outcome: | The proposed framework enables models to store and reuse accumulated strategies, code snippets, and general problem-solving insights at inference time. |
Similar Papers
TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining (2025.acl-long)
Copied to clipboard
Jeffrey Li, Mohammadreza Armandpour, Seyed Iman Mirzadeh, Sachin Mehta, Vaishaal Shankar, Raviteja Vemulapalli, Samy Bengio, Oncel Tuzel, Mehrdad Farajtabar, Hadi Pouransari, Fartash Faghri
| Challenge: | Large language models (LLMs) trained on historical web data inevitably become outdated. |
| Approach: | They propose a web-scale dataset for time-continual pretraining of LLMs derived from 114 dumps of Common Crawl (CC) they also design time-stratified evaluations to assess how well various continual learning methods adapt to new data while retaining past knowledge. |
| Outcome: | The proposed benchmarks show that autoregressive meta-schedules combined with a fixed-ratio replay of older data can achieve comparable held-out loss to re-training from scratch, while requiring significantly less computation (2.6x). |
Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing frameworks treat memory as a static append-only archive . Existing systems focus on passive accumulation, resulting in a 'passive accumulation' of memory. |
| Approach: | They propose a framework for experience-driven agent evolution that integrates procedural memory with contextual information to create a high-quality experience pool. |
| Outcome: | Experiments on BFCL-V3 and AppWorld show that ReMe outperforms memoryless Qwen3-8B. |
Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling (2026.findings-acl)
Copied to clipboard
Ivan Rodkin, Daniil Orel, Konstantin Smirnov, Arman Bolatov, Bilal Elbouardi, Besher Hassan, Yuri Kuratov, Aydar Bulatov, Preslav Nakov, Timothy Baldwin, Artem Shelmanov, Mikhail Burtsev
| Challenge: | Reasoning is a core capability of large language models, yet how multi-step reasoning is learned and executed remains unclear. |
| Approach: | They evaluate how large language models learn multi-step reasoning without memorization . they find that most neural architectures trained from scratch can learn rule inference . |
| Outcome: | The proposed framework fails to solve a natural-language proxy task with high accuracy. |
Enhancing Efficiency and Exploration in Reinforcement Learning for LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches allocate an equal number of rollouts to all questions during the RL process, which is inefficient. |
| Approach: | They propose a mechanism for dynamically allocating rollout budgets based on the difficulty of the problems, enabling more efficient RL training. |
| Outcome: | The proposed model improves response precision while preserving exploratory ability to uncover potential correct pathways. |
DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to developing LLM-powered coding agents struggle with sub-optimal decision-making. |
| Approach: | They propose a novel inference time compute scaling approach that recovers from sub-optimal decisions by branching out a trajectory at certain key decision points by taking an alternative action given the history of the trajectory and execution feedback of the previous attempt. |
| Outcome: | The proposed approach achieves a pass@1 rate of 47% on the SWE-Bench Lite benchmark, outperforming state-of-the-art (SOTA) open-source frameworks. |
Check Your Work: Structured Checklist Feedback for Improving Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models have been driven by verifiable feedback in deterministic domains like mathematics and code. |
| Approach: | They propose to decompose granular, prompt-specific checklists into a scalar reward and use them to transform them into skalar rewards. |
| Outcome: | The proposed approach yields an 11.8% win-rate improvement on AlpacaEval 2.0 using Qwen3-8B, outperforming holistic reward models and existing checklist baselines. |
Gated Differentiable Working Memory for Long-Context Language Modeling (2026.acl-long)
Copied to clipboard
Lingrui Mei, Shenghua Liu, Yiwei Wang, Yuyao Ge, Baolong Bi, Jiayu Yao, Jun Wan, Ziling Yin, Jiafeng Guo, Xueqi Cheng
| Challenge: | Long contexts break transformers, attention scores dilute, model cannot adapt to novel patterns at inference time. |
| Approach: | They propose a framework that gates the memory consolidation process by estimating Contextual Utility . they propose GDWM to maintain a form of working memory with constant contexts . |
| Outcome: | The proposed framework achieves comparable or superior performance on sparse-information tasks with 4 fewer gradient steps compared to uniform baselines. |
On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning (2026.acl-long)
Copied to clipboard
Changyu Liu, Yiyang Liu, Taowen Wang, Qiao Zhuang, James Chenhao Liang, Wenhao Yang, Renjing Xu, Qifan Wang, Dongfang Liu, Cheng Han
| Challenge: | Existing vision-language-action models are unsuitable for simulated or physical-world deployments . current methods fail when confronted with inherent real-world dynamic variability. |
| Approach: | They propose a test-time reinforcement learning framework that enables on-the-fly policy adaptation during inference. |
| Outcome: | Empirical results show that the proposed framework improves adaptability, stability and task success in dynamic, previously unseen scenarios. |
Discarding the Crutches: Adaptive Parameter-Efficient Expert Meta-Learning for Continual Semantic Parsing (2025.coling-main)
Copied to clipboard
| Challenge: | Continual Semantic Parsing (CSP) enables parsers to generate SQL from natural language questions in task streams, using minimal annotated data to handle dynamically evolving databases in real-world scenarios. |
| Approach: | They propose a Adaptive PET eXpert meta-learning approach that assists experts in adaptively warming up, ensuring better model initialization. |
| Outcome: | The proposed method outperforms existing methods on two benchmarks and achieves superior performance without data replay or ideal settings. |
Bridging the Language Gap: Dynamic Learning Strategies for Improving Multilingual Performance in LLMs (2025.coling-main)
Copied to clipboard
Somnath Kumar, Vaibhav Balloli, Mercy Ranjit, Kabir Ahuja, Sunayana Sitaram, Kalika Bali, Tanuja Ganu, Akshay Nambi
| Challenge: | Large language models (LLMs) excel in diverse applications but still struggle with non-Latin scripts and low-resource languages. |
| Approach: | They propose a dynamic learning approach that optimizes prompt strategy, embedding model, and LLM per query at runtime. |
| Outcome: | The proposed approach achieves 10-15% improvements in multilingual performance over pre-trained models and 4x gains compared to fine-tuned, language-specific models. |