Challenge: Existing LLM agents are brittle in open-ended environments due to two limitations: 1) a closed action space; 2) myopic error recovery.
Approach: They propose a novel architecture that augments the action space and revises global strategies by adding a reflective replanning mechanism to the system.
Outcome: Experiments show that CAR outperforms baselines in a diagnostic benchmark with pruned toolsets to simulate tool scarcity.

Similar Papers

ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflection (2025.emnlp-main)

Copied to clipboard

Challenge: Recent advances in LLMs have significantly enhanced their reasoning capabilities, enabling LLM-based agents to perform complex multi-step decision making beyond static problem solving.
Approach: They propose a novel reasoning backbone that shifts reasoning from merely planning next actions to continuously reflecting on the agent’s state relative to its goal.
Outcome: The proposed model outperforms ReAct by 27.7% on average, achieving a 93.3% success rate in ALFWorld.
EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis (2026.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) are expected to be trained to act as agents in various real-world environments, but access to real systems is often restricted and manually built sandboxes are hard to scale.
Approach: They propose an automated framework for scalable tool-interaction environments via programmatic synthesis that synthesizes 191 environments and about 7K scenarios and applies them to Supervised Fine-Tuning and Reinforcement Learning for Qwen3 series models.
Outcome: The proposed framework significantly improves LLMs’ ability to solve tasks in complex environments involving multi-turn, multi-tool interactions.
ReCreate: Reasoning and Creating Domain Agents Driven by Experience (2026.acl-long)

Copied to clipboard

Challenge: Large Language Model (LLM) agents are reshaping the industrial landscape, but tasks differ widely, making them labor-intensive to build.
Approach: They propose an experience-driven framework for the automatic creation of domain agents . they leverage agent interaction histories to provide rich concrete signals on success or failure .
Outcome: The proposed framework outperforms human-designed agents and existing methods in experiments across diverse domains.
ARCHITECT: Uncertainty-Aware Dynamic Tool Learning via Causal Intervention for Open-World Agents (2026.acl-long)

Copied to clipboard

Challenge: Existing methods treat all generated tools as equally trustworthy, a "blind trust" assumption that is untenable for reliable agent deployment.
Approach: They propose a framework that moves beyond black-box reliability prediction to interpretable failure attribution.
Outcome: The proposed framework achieves state-of-the-art on four benchmarks including StableToolBench, MINT, T-Eval, and SWE-bench Lite.
FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models are being increasingly deployed as decision-making core of autonomous agents . however, in conversational benchmarks, these agents fail due to the cascading effects of incorrect decision- making .
Approach: They propose a framework that analyzes failure trajectories from baseline agents to identify most prevalent errors.
Outcome: Experiments show that the framework improves performance over open-source LLMs . the framework can be used to build reliable, multi-turn tool-use agents .
CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents (2026.acl-long)

Copied to clipboard

Challenge: Existing evaluations of Large Language Models (LLMs) focus on task completion, but neglect a crucial capability: the ability to devise and adjust cost-optimal plans in response to changing environments.
Approach: They propose a scalable, cost-centric benchmark to evaluate agents’ economic reasoning and replanning abilities.
Outcome: Evaluating leading open-sourced and proprietary models on CostBench reveals a substantial gap in cost-aware planning .
ToolDNA: Autonomous Evolution of Tool Metadata for Robust Dialogue Agents (2026.findings-acl)

Copied to clipboard

Challenge: Task-oriented dialogue systems face labor-intensive manual metadata tuning and sparse reinforcement learning (RL) rewards that fail to diagnose invocation errors.
Approach: They propose a framework that enables auto-evolution of policy networks and tool metadata via RL . a tool metadata loop coordinates metadata through policy-generated candidates during rollouts .
Outcome: The proposed framework achieves +11% problem resolution and +54% accuracy over commercial LLMs with prompt engineering and +25%/+35% over supervised fine-tuning.
Failure makes the agent stronger: Enhancing Accuracy through Structured Reflection for Reliable Tool Interactions (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to self-reflection rely on heuristic prompting or unidirectional reasoning traces.
Approach: They propose a structured reflection method that transforms the "from error to repair" process into a first-class, controllable, and trainable action.
Outcome: The proposed method improves multi-turn tool-call success rates and error recovery while reducing redundant calls.
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.
ToolCPT: Improving Tool Utilization in LLM Agents via Continuous Pre-training (2026.findings-acl)

Copied to clipboard

Challenge: Current approaches to enhancing tool use for LLM-based agents focus on post-training fine-tuning or test-time context extension.
Approach: They propose to enhance tool knowledge for LLM-based agents during continuous pre-training . they curate 5.1 million code artifacts from large-scale, high-quality code repositories .
Outcome: The proposed model outperforms existing methods on out-of-distribution tools on multiple benchmarks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations